<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE article PUBLIC "-//NLM//DTD Journal Publishing DTD v2.3 20070202//EN" "journalpublishing.dtd">
<article article-type="brief-report" dtd-version="2.3" xml:lang="EN" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">
<front>
<journal-meta>
<journal-id journal-id-type="publisher-id">Front. Earth Sci.</journal-id>
<journal-title>Frontiers in Earth Science</journal-title>
<abbrev-journal-title abbrev-type="pubmed">Front. Earth Sci.</abbrev-journal-title>
<issn pub-type="epub">2296-6463</issn>
<publisher>
<publisher-name>Frontiers Media S.A.</publisher-name>
</publisher>
</journal-meta>
<article-meta>
<article-id pub-id-type="publisher-id">944301</article-id>
<article-id pub-id-type="doi">10.3389/feart.2022.944301</article-id>
<article-categories>
<subj-group subj-group-type="heading">
<subject>Earth Science</subject>
<subj-group>
<subject>Brief Research Report</subject>
</subj-group>
</subj-group>
</article-categories>
<title-group>
<article-title>Sparse Gaussian Process Regression for Landslide Displacement Time-Series Forecasting</article-title>
<alt-title alt-title-type="left-running-head">Yang et al.</alt-title>
<alt-title alt-title-type="right-running-head">Landslide Displacement Time-series Forecasting</alt-title>
</title-group>
<contrib-group>
<contrib contrib-type="author">
<name>
<surname>Yang</surname>
<given-names>Weiqi</given-names>
</name>
<xref ref-type="aff" rid="aff1">
<sup>1</sup>
</xref>
</contrib>
<contrib contrib-type="author" corresp="yes">
<name>
<surname>Feng</surname>
<given-names>Yuran</given-names>
</name>
<xref ref-type="aff" rid="aff1">
<sup>1</sup>
</xref>
<xref ref-type="corresp" rid="c001">&#x2a;</xref>
<uri xlink:href="https://loop.frontiersin.org/people/1816456/overview"/>
</contrib>
<contrib contrib-type="author">
<name>
<surname>Wan</surname>
<given-names>Jian</given-names>
</name>
<xref ref-type="aff" rid="aff1">
<sup>1</sup>
</xref>
</contrib>
<contrib contrib-type="author">
<name>
<surname>Wang</surname>
<given-names>Lingling</given-names>
</name>
<xref ref-type="aff" rid="aff2">
<sup>2</sup>
</xref>
</contrib>
</contrib-group>
<aff id="aff1">
<sup>1</sup>
<institution>Department of Civil Engineering</institution>, <institution>Sichuan College of Architectural Technology</institution>, <addr-line>Deyang</addr-line>, <country>China</country>
</aff>
<aff id="aff2">
<sup>2</sup>
<institution>School of Economic and Management</institution>, <institution>Dalian Ocean University</institution>, <addr-line>Dalian</addr-line>, <country>China</country>
</aff>
<author-notes>
<fn fn-type="edited-by">
<p>
<bold>Edited by:</bold> <ext-link ext-link-type="uri" xlink:href="https://loop.frontiersin.org/people/1411481/overview">Jingren Zhou</ext-link>, Sichuan University, China</p>
</fn>
<fn fn-type="edited-by">
<p>
<bold>Reviewed by:</bold> <ext-link ext-link-type="uri" xlink:href="https://loop.frontiersin.org/people/1650431/overview">Peng Tang</ext-link>, Jiangxi University of Science and Technology, China</p>
<p>
<ext-link ext-link-type="uri" xlink:href="https://loop.frontiersin.org/people/1799884/overview">Zhanfeng Fan</ext-link>, Chengdu University, China</p>
</fn>
<corresp id="c001">&#x2a;Correspondence: Yuran Feng, <email>fengyuran20171101@163.com</email>
</corresp>
<fn fn-type="other">
<p>This article was submitted to Geohazards and Georisks, a section of the journal Frontiers in Earth Science</p>
</fn>
</author-notes>
<pub-date pub-type="epub">
<day>30</day>
<month>06</month>
<year>2022</year>
</pub-date>
<pub-date pub-type="collection">
<year>2022</year>
</pub-date>
<volume>10</volume>
<elocation-id>944301</elocation-id>
<history>
<date date-type="received">
<day>15</day>
<month>05</month>
<year>2022</year>
</date>
<date date-type="accepted">
<day>09</day>
<month>06</month>
<year>2022</year>
</date>
</history>
<permissions>
<copyright-statement>Copyright &#xa9; 2022 Yang, Feng, Wan and Wang.</copyright-statement>
<copyright-year>2022</copyright-year>
<copyright-holder>Yang, Feng, Wan and Wang</copyright-holder>
<license xlink:href="http://creativecommons.org/licenses/by/4.0/">
<p>This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.</p>
</license>
</permissions>
<abstract>
<p>Landslide hazards are complex nonlinear systems with a highly dynamic nature. Accurate forecasting of landslide displacement and evolution is crucial for the prevention and mitigation of landslide hazards. In this study, a probabilistic landslide displacement forecasting model based on the quantification of epistemic uncertainty is proposed. In particular, the displacement forecasting problem is cast as a time-series regression problem with limited training samples and must be solved by statistical inference. The epistemic uncertainty of the landslide displacement series is depicted by the statistical properties of the function space constituted by the nonlinear mappings generated by the sparse Gaussian process regression. Data for our study was collected from the study area located in northwestern China. Other state-of-the-art probabilistic forecasting models have also been utilized for comparative analysis. The experimental results confirmed the superiority of the sparse Gaussian process in the modeling of landslide displacement series in terms of forecasting accuracy, uncertainty quantification, and robustness to overfitting.</p>
</abstract>
<kwd-group>
<kwd>landslide displacement</kwd>
<kwd>time-series</kwd>
<kwd>probabilistic forecasting</kwd>
<kwd>epistemic uncertainty</kwd>
<kwd>sparse Gaussian process</kwd>
</kwd-group>
</article-meta>
</front>
<body>
<sec id="s1">
<title>1 Introduction</title>
<p>In southwest China, landslides are among the most devastating natural disasters, causing damage to life, property, and local infrastructure (<xref ref-type="bibr" rid="B2">Aggarwal et al., 2020</xref>; <xref ref-type="bibr" rid="B6">Fan &#x26; Cai 2021</xref>; <xref ref-type="bibr" rid="B36">Zhou et al., 2021</xref>). Over 7,000 landslides occurred in China in 2016 as reported in the annual report provided by the China Institute of Geo-Environment Monitoring (<xref ref-type="bibr" rid="B30">Tang et al., 2020</xref>). The factors that trigger landslides vary, including heavy rainfall, reservoir water fluctuations, earthquakes, and human activities (<xref ref-type="bibr" rid="B7">Fan et al., 2022</xref>; <xref ref-type="bibr" rid="B18">Li et al., 2022</xref>). Reliable early warning systems that accurately quantify future landslide deformation assist experts in the evaluation of incoming landslide hazards (<xref ref-type="bibr" rid="B29">Tang et al., 2021</xref>). Therefore, landslide displacement time-series forecasting plays an important role in the prevention of geo-hazards.</p>
<p>According to literature review, landslide displacement forecasting can be categorized into two major types: deterministic and probabilistic forecasting. Majority of the studies involving deterministic forecasting approaches were based on statistical models or machine-learning models in predicting the actual value of incoming landslide displacement. <xref ref-type="bibr" rid="B15">Lewis and Reinsel (1985)</xref> applied autoregressive time-series models to predict landslide displacement. <xref ref-type="bibr" rid="B25">Lu and Rosenbaum (2003)</xref> proposed using the GM (1,1) model to perform a multivariate regression analysis of landslide displacement. <xref ref-type="bibr" rid="B24">Liu et al. (2012)</xref> used an exponential model to conduct time-series regression on landslide displacement. With the advancement of artificial intelligence (AI) technologies, machine learning and deep learning have become more popular in recent years. For instance, <xref ref-type="bibr" rid="B23">Lian et al. (2015)</xref> trained an artificial neural network (ANN) to predict short-term landslide displacement. <xref ref-type="bibr" rid="B37">Zhu et al. (2017)</xref> used a least-squares support vector machine optimized by a genetic algorithm to predict landslide displacement empirically. <xref ref-type="bibr" rid="B35">Xu et al. (2019)</xref> compared multiple data mining algorithms on their performance in predicting landslide displacement in the Heifangtai Region, China. <xref ref-type="bibr" rid="B21">Li et al. (2018)</xref> proposed using an extreme learning machine (ELM) integrated with parametric copula models to forecast the faster seasonal landslide displacement. The tail correlation is quantified, and the risk boundaries are computed using value-at-risk and tail-value-at-risk. <xref ref-type="bibr" rid="B22">Li et al. (2020)</xref> applied a deep-learning algorithm called the deep belief network (DBN) to predict incoming landslide displacement in the temporal domain. The research utilized the exponentially weighted moving average (EWMA) model to set up decision boundaries for identifying faster seasonal displacement and achieved promising results. All the above studies were performed under deterministic forecasting and offered reliable solutions for determining future landslide research.</p>
<p>Compared with the deterministic forecasting approaches, probabilistic forecasting estimates the probability distribution of future landslide displacement and is more complicated in practice. Using the same input data as the deterministic forecasting models, the output of probabilistic forecasting models consists of a prediction interval (PI) with a probability density function. For a PI, the two independent quantiles are fitted to the upper and lower bounds, and an accurate prediction is defined as the actual value that falls within the PI. <xref ref-type="bibr" rid="B26">Ma et al. (2018)</xref> proposed using a bootstrap-based ELM to construct PIs for landslide incremental displacement. <xref ref-type="bibr" rid="B34">Xing et al. (2019)</xref> revised the structure of long short-term memory (LSTM) network to generate probabilistic forecasting of landslide displacement and produced high-quality PIs for future displacement. <xref ref-type="bibr" rid="B11">Jiang et al. (2021)</xref> proposed a hybrid grey wolf optimizer to optimize the ELM structure for PI construction and achieved improved probabilistic prediction performance using field data. However, there is currently limited studies on probabilistic forecasting of landslide displacement.</p>
<p>In recent years, Gaussian process regression (GPR) has demonstrated superior predictive strength in many regression tasks (<xref ref-type="bibr" rid="B9">He and Kusiak 2017</xref>; <xref ref-type="bibr" rid="B27">Schulz et al., 2018</xref>; <xref ref-type="bibr" rid="B17">Li et al., 2021a</xref>; <xref ref-type="bibr" rid="B16">Li et al., 2021b</xref>; <xref ref-type="bibr" rid="B5">Deringer et al., 2021</xref>; <xref ref-type="bibr" rid="B10">Jamei et al., 2021</xref>; <xref ref-type="bibr" rid="B33">West et al., 2021</xref>; <xref ref-type="bibr" rid="B8">Fuhg et al., 2022</xref>; <xref ref-type="bibr" rid="B28">Tamhidi et al., 2022</xref>). Generally, GPR is a nonlinear, nonparametric regression tool useful for interpolating data points scattered in a high-dimensional input space. GPR is based on the Bayesian probability theory and has very close connections with other regression techniques, such as kernel ridge regression (KRR) and linear regression with radial basis functions (<xref ref-type="bibr" rid="B5">Deringer et al., 2021</xref>).</p>
<p>In this study, a novel landslide displacement probabilistic forecasting model integrated with a sparse Gaussian process (SGP) is proposed. The SGP is a nonparametric approach based on Bayesian theory and has the advantage of requiring fewer training samples compared with other over-parametrized regression models. Compared with the original Gaussian process, SGP adopts inducing variable points and variational inference to approximate the model parameters. Gradient descent optimization was utilized to optimize the SGP for predicting probabilistic landslide displacement.</p>
<p>The main contributions of this paper can be concluded as follows:<list list-type="simple">
<list-item>
<p>&#x2022; A new probabilistic landslide displacement model via the quantification of epistemic uncertainty is proposed.</p>
</list-item>
<list-item>
<p>&#x2022; The SGP is incorporated within the probabilistic forecasting framework to tackle the interference complexity.</p>
</list-item>
</list>
</p>
<p>The remainder of this paper is organized as follows; <xref ref-type="sec" rid="s2">Section 2</xref> introduces the basics of the Gaussian process and the sparse Gaussian process, <xref ref-type="sec" rid="s3">Section 3</xref> describes the case study area and the data collection process, <xref ref-type="sec" rid="s4">Section 4</xref> summarizes the experimental results and <xref ref-type="sec" rid="s5">Section 5</xref> concludes the paper.</p>
</sec>
<sec id="s2">
<title>2 Methodology</title>
<sec id="s2-1">
<title>2.1 Gaussian Process</title>
<p>The Gaussian process (GP) has been widely applied in probabilistic forecasting (<xref ref-type="bibr" rid="B19">Li et al., 2022a</xref>). A typical GP defines distribution over functions such that, if we pick any two or more points in a function, the observations of the outputs follow a joint multivariate Gaussian distribution (<xref ref-type="bibr" rid="B27">Schulz et al., 2018</xref>; <xref ref-type="bibr" rid="B32">Wen et al., 2022</xref>). In general, a Gaussian process states that in a multivariate dataset, any finite number of variables follows a joint Gaussian distribution.</p>
<p>In a regression type of a problem, a GP combined with a Gaussian likelihood generates a posterior GP over the model output. With a given input <inline-formula id="inf1">
<mml:math id="m1">
<mml:mi mathvariant="bold">x</mml:mi>
</mml:math>
</inline-formula>, and output <inline-formula id="inf2">
<mml:math id="m2">
<mml:mi>y</mml:mi>
</mml:math>
</inline-formula> of a function <inline-formula id="inf3">
<mml:math id="m3">
<mml:mrow>
<mml:mi>f</mml:mi>
<mml:mrow>
<mml:mo>(</mml:mo>
<mml:mo>)</mml:mo>
</mml:mrow>
</mml:mrow>
</mml:math>
</inline-formula>, a GP model can be written as (1):<disp-formula id="e1">
<mml:math id="m4">
<mml:mrow>
<mml:mi mathvariant="bold">y</mml:mi>
<mml:mo>&#x3d;</mml:mo>
<mml:mi>f</mml:mi>
<mml:mrow>
<mml:mo>(</mml:mo>
<mml:mi mathvariant="bold">x</mml:mi>
<mml:mo>)</mml:mo>
</mml:mrow>
<mml:mo>&#x2b;</mml:mo>
<mml:mi mathvariant="italic">&#x3f5;</mml:mi>
</mml:mrow>
</mml:math>
<label>(1)</label>
</disp-formula>where <inline-formula id="inf4">
<mml:math id="m5">
<mml:mrow>
<mml:mi>f</mml:mi>
<mml:mrow>
<mml:mo>(</mml:mo>
<mml:mi mathvariant="bold">x</mml:mi>
<mml:mo>)</mml:mo>
</mml:mrow>
</mml:mrow>
</mml:math>
</inline-formula> is the latent variable; <inline-formula id="inf5">
<mml:math id="m6">
<mml:mi mathvariant="script">E</mml:mi>
</mml:math>
</inline-formula> follows <inline-formula id="inf6">
<mml:math id="m7">
<mml:mrow>
<mml:mi mathvariant="script">E</mml:mi>
<mml:mo>&#x223c;</mml:mo>
<mml:mi mathvariant="script">E</mml:mi>
<mml:mrow>
<mml:mo>(</mml:mo>
<mml:mn>0</mml:mn>
<mml:mo>,</mml:mo>
<mml:msubsup>
<mml:mi>&#x3c3;</mml:mi>
<mml:mi mathvariant="italic">&#x3f5;</mml:mi>
<mml:mn>2</mml:mn>
</mml:msubsup>
<mml:mo>)</mml:mo>
</mml:mrow>
</mml:mrow>
</mml:math>
</inline-formula> and <inline-formula id="inf7">
<mml:math id="m8">
<mml:mrow>
<mml:msubsup>
<mml:mi>&#x3c3;</mml:mi>
<mml:mi mathvariant="italic">&#x3f5;</mml:mi>
<mml:mn>2</mml:mn>
</mml:msubsup>
</mml:mrow>
</mml:math>
</inline-formula> is the variance of the noise. Here, epistemic uncertainty is caused by the limited representation capability of displacements. Thus, we can specify the distribution of latent variable <inline-formula id="inf8">
<mml:math id="m9">
<mml:mrow>
<mml:mi mathvariant="bold">f</mml:mi>
<mml:mo>&#x3d;</mml:mo>
<mml:mi>f</mml:mi>
<mml:mrow>
<mml:mo>(</mml:mo>
<mml:mi mathvariant="bold">x</mml:mi>
<mml:mo>)</mml:mo>
</mml:mrow>
</mml:mrow>
</mml:math>
</inline-formula> as <inline-formula id="inf9">
<mml:math id="m10">
<mml:mrow>
<mml:mi mathvariant="bold">f</mml:mi>
<mml:mo>&#x223c;</mml:mo>
<mml:mi mathvariant="script">E</mml:mi>
<mml:mrow>
<mml:mo>(</mml:mo>
<mml:mn>0</mml:mn>
<mml:mo>,</mml:mo>
<mml:mi>C</mml:mi>
<mml:mrow>
<mml:mo>(</mml:mo>
<mml:mi mathvariant="bold">x</mml:mi>
<mml:mo>,</mml:mo>
<mml:mi mathvariant="bold">x</mml:mi>
<mml:mo>)</mml:mo>
</mml:mrow>
<mml:mo>)</mml:mo>
</mml:mrow>
</mml:mrow>
</mml:math>
</inline-formula> where <inline-formula id="inf10">
<mml:math id="m11">
<mml:mrow>
<mml:mi>C</mml:mi>
<mml:mrow>
<mml:mo>(</mml:mo>
<mml:mo>)</mml:mo>
</mml:mrow>
</mml:mrow>
</mml:math>
</inline-formula> is the covariance function.</p>
<p>In the GP, suppose <inline-formula id="inf11">
<mml:math id="m12">
<mml:mrow>
<mml:mover accent="true">
<mml:mrow>
<mml:msub>
<mml:mi mathvariant="bold">y</mml:mi>
<mml:mi mathvariant="italic">i</mml:mi>
</mml:msub>
</mml:mrow>
<mml:mo stretchy="true">&#x5e;</mml:mo>
</mml:mover>
</mml:mrow>
</mml:math>
</inline-formula> is the predicted value for a new input <inline-formula id="inf12">
<mml:math id="m13">
<mml:mrow>
<mml:msub>
<mml:mi mathvariant="bold">x</mml:mi>
<mml:mi>i</mml:mi>
</mml:msub>
</mml:mrow>
</mml:math>
</inline-formula>, the combination of <inline-formula id="inf13">
<mml:math id="m14">
<mml:mi mathvariant="bold">f</mml:mi>
</mml:math>
</inline-formula> and <inline-formula id="inf14">
<mml:math id="m15">
<mml:mrow>
<mml:mover accent="true">
<mml:mrow>
<mml:msub>
<mml:mi mathvariant="bold">y</mml:mi>
<mml:mi>i</mml:mi>
</mml:msub>
</mml:mrow>
<mml:mo stretchy="true">&#x5e;</mml:mo>
</mml:mover>
</mml:mrow>
</mml:math>
</inline-formula> should follow a joint Gaussian distribution expressed as (2):<disp-formula id="e2">
<mml:math id="m16">
<mml:mrow>
<mml:mi>p</mml:mi>
<mml:mrow>
<mml:mo>(</mml:mo>
<mml:mrow>
<mml:mi mathvariant="bold">f</mml:mi>
<mml:mo>,</mml:mo>
<mml:mrow>
<mml:mover accent="true">
<mml:mrow>
<mml:msub>
<mml:mi mathvariant="bold">y</mml:mi>
<mml:mi>i</mml:mi>
</mml:msub>
</mml:mrow>
<mml:mo stretchy="true">&#x5e;</mml:mo>
</mml:mover>
</mml:mrow>
</mml:mrow>
<mml:mo>)</mml:mo>
</mml:mrow>
<mml:mo>&#x3d;</mml:mo>
<mml:mi mathvariant="script">N</mml:mi>
<mml:mrow>
<mml:mo>(</mml:mo>
<mml:mrow>
<mml:mrow>
<mml:mo>[</mml:mo>
<mml:mrow>
<mml:mtable>
<mml:mtr>
<mml:mtd>
<mml:mn mathvariant="bold">0</mml:mn>
</mml:mtd>
</mml:mtr>
<mml:mtr>
<mml:mtd>
<mml:mn>0</mml:mn>
</mml:mtd>
</mml:mtr>
</mml:mtable>
</mml:mrow>
<mml:mo>]</mml:mo>
</mml:mrow>
<mml:mo>,</mml:mo>
<mml:mrow>
<mml:mo>[</mml:mo>
<mml:mrow>
<mml:mtable>
<mml:mtr>
<mml:mtd>
<mml:mi mathvariant="bold-italic">C</mml:mi>
</mml:mtd>
<mml:mtd>
<mml:mrow>
<mml:msub>
<mml:mi mathvariant="bold-italic">C</mml:mi>
<mml:mi mathvariant="bold-italic">&#x2217;</mml:mi>
</mml:msub>
</mml:mrow>
</mml:mtd>
</mml:mtr>
<mml:mtr>
<mml:mtd>
<mml:mrow>
<mml:msubsup>
<mml:mi mathvariant="bold-italic">C</mml:mi>
<mml:mi mathvariant="bold-italic">&#x2217;</mml:mi>
<mml:mi mathvariant="bold-italic">T</mml:mi>
</mml:msubsup>
</mml:mrow>
</mml:mtd>
<mml:mtd>
<mml:mrow>
<mml:mover accent="true">
<mml:mi mathvariant="bold-italic">C</mml:mi>
<mml:mo>&#x2dc;</mml:mo>
</mml:mover>
</mml:mrow>
</mml:mtd>
</mml:mtr>
</mml:mtable>
</mml:mrow>
<mml:mo>]</mml:mo>
</mml:mrow>
</mml:mrow>
<mml:mo>)</mml:mo>
</mml:mrow>
</mml:mrow>
</mml:math>
<label>(2)</label>
</disp-formula>where <inline-formula id="inf15">
<mml:math id="m17">
<mml:mrow>
<mml:mi mathvariant="bold-italic">C</mml:mi>
<mml:mo>&#xa0;</mml:mo>
<mml:mo>&#x3d;</mml:mo>
<mml:mo>&#xa0;</mml:mo>
<mml:mi>C</mml:mi>
<mml:mrow>
<mml:mo>(</mml:mo>
<mml:mi mathvariant="bold">x</mml:mi>
<mml:mo>,</mml:mo>
<mml:mi mathvariant="bold">x</mml:mi>
<mml:mo>)</mml:mo>
</mml:mrow>
</mml:mrow>
</mml:math>
</inline-formula>; <inline-formula id="inf16">
<mml:math id="m18">
<mml:mrow>
<mml:msub>
<mml:mi mathvariant="bold-italic">C</mml:mi>
<mml:mi mathvariant="bold-italic">&#x2a;</mml:mi>
</mml:msub>
<mml:mo>&#x3d;</mml:mo>
<mml:mi mathvariant="bold-italic">C</mml:mi>
<mml:mrow>
<mml:mo>(</mml:mo>
<mml:msub>
<mml:mi mathvariant="bold">x</mml:mi>
<mml:mi>i</mml:mi>
</mml:msub>
<mml:mo>,</mml:mo>
<mml:mi mathvariant="bold">x</mml:mi>
<mml:mo>)</mml:mo>
</mml:mrow>
</mml:mrow>
</mml:math>
</inline-formula>; and <inline-formula id="inf17">
<mml:math id="m19">
<mml:mrow>
<mml:mrow>
<mml:mover accent="true">
<mml:mi mathvariant="bold-italic">C</mml:mi>
<mml:mo>&#x2dc;</mml:mo>
</mml:mover>
</mml:mrow>
<mml:mo>&#x3d;</mml:mo>
<mml:mi>C</mml:mi>
<mml:mrow>
<mml:mo>(</mml:mo>
<mml:msub>
<mml:mi mathvariant="bold">x</mml:mi>
<mml:mi>i</mml:mi>
</mml:msub>
<mml:mo>,</mml:mo>
<mml:msub>
<mml:mi mathvariant="bold">x</mml:mi>
<mml:mi>i</mml:mi>
</mml:msub>
<mml:mo>)</mml:mo>
</mml:mrow>
</mml:mrow>
</mml:math>
</inline-formula>. According to Bayesian inference, the posterior distribution of the target prediction <inline-formula id="inf18">
<mml:math id="m20">
<mml:mrow>
<mml:mover accent="true">
<mml:mrow>
<mml:msub>
<mml:mi mathvariant="bold">y</mml:mi>
<mml:mi>i</mml:mi>
</mml:msub>
</mml:mrow>
<mml:mo stretchy="true">&#x5e;</mml:mo>
</mml:mover>
</mml:mrow>
</mml:math>
</inline-formula> conditioned on the training set <inline-formula id="inf19">
<mml:math id="m21">
<mml:mi mathvariant="bold">y</mml:mi>
</mml:math>
</inline-formula> is expressed as (3)&#x2013;(5).<disp-formula id="e3">
<mml:math id="m22">
<mml:mrow>
<mml:mi>p</mml:mi>
<mml:mrow>
<mml:mo>(</mml:mo>
<mml:mrow>
<mml:mrow>
<mml:mover accent="true">
<mml:mrow>
<mml:msub>
<mml:mi mathvariant="bold">y</mml:mi>
<mml:mi>i</mml:mi>
</mml:msub>
</mml:mrow>
<mml:mo stretchy="true">&#x5e;</mml:mo>
</mml:mover>
</mml:mrow>
<mml:mtext>&#x7c;</mml:mtext>
<mml:mi mathvariant="bold">y</mml:mi>
</mml:mrow>
<mml:mo>)</mml:mo>
</mml:mrow>
<mml:mo>&#x3d;</mml:mo>
<mml:mi mathvariant="script">N</mml:mi>
<mml:mrow>
<mml:mo>(</mml:mo>
<mml:mrow>
<mml:msub>
<mml:mi>&#x3bc;</mml:mi>
<mml:mo>&#x2217;</mml:mo>
</mml:msub>
<mml:mo>,</mml:mo>
<mml:msubsup>
<mml:mi>&#x3c3;</mml:mi>
<mml:mo>&#x2217;</mml:mo>
<mml:mn>2</mml:mn>
</mml:msubsup>
</mml:mrow>
<mml:mo>)</mml:mo>
</mml:mrow>
</mml:mrow>
</mml:math>
<label>(3)</label>
</disp-formula>
<disp-formula id="e4">
<mml:math id="m23">
<mml:mrow>
<mml:msub>
<mml:mi>&#x3bc;</mml:mi>
<mml:mo>&#x2217;</mml:mo>
</mml:msub>
<mml:mo>&#x3d;</mml:mo>
<mml:msub>
<mml:mi mathvariant="bold-italic">C</mml:mi>
<mml:mi mathvariant="bold-italic">&#x2217;</mml:mi>
</mml:msub>
<mml:msup>
<mml:mi mathvariant="bold-italic">K</mml:mi>
<mml:mrow>
<mml:mo>&#x2212;</mml:mo>
<mml:mn>1</mml:mn>
</mml:mrow>
</mml:msup>
<mml:mi mathvariant="bold">y</mml:mi>
</mml:mrow>
</mml:math>
<label>(4)</label>
</disp-formula>
<disp-formula id="e5">
<mml:math id="m24">
<mml:mrow>
<mml:msubsup>
<mml:mi>&#x3c3;</mml:mi>
<mml:mo>&#x2217;</mml:mo>
<mml:mn>2</mml:mn>
</mml:msubsup>
<mml:mo>&#x3d;</mml:mo>
<mml:mrow>
<mml:mover accent="true">
<mml:mi mathvariant="bold-italic">C</mml:mi>
<mml:mo>&#x2dc;</mml:mo>
</mml:mover>
</mml:mrow>
<mml:mo>&#x2212;</mml:mo>
<mml:msubsup>
<mml:mi mathvariant="bold-italic">C</mml:mi>
<mml:mi mathvariant="bold-italic">&#x2217;</mml:mi>
<mml:mi mathvariant="bold-italic">T</mml:mi>
</mml:msubsup>
<mml:msup>
<mml:mi mathvariant="bold-italic">K</mml:mi>
<mml:mrow>
<mml:mo>&#x2212;</mml:mo>
<mml:mn>1</mml:mn>
</mml:mrow>
</mml:msup>
<mml:msub>
<mml:mi mathvariant="bold-italic">C</mml:mi>
<mml:mi mathvariant="bold-italic">&#x2217;</mml:mi>
</mml:msub>
</mml:mrow>
</mml:math>
<label>(5)</label>
</disp-formula>where <inline-formula id="inf20">
<mml:math id="m25">
<mml:mrow>
<mml:mi mathvariant="bold-italic">K</mml:mi>
<mml:mo>&#xa0;</mml:mo>
<mml:mo>&#x3d;</mml:mo>
<mml:mo>&#xa0;</mml:mo>
<mml:mi mathvariant="bold-italic">C</mml:mi>
<mml:mo>&#x2b;</mml:mo>
<mml:msubsup>
<mml:mi>&#x3c3;</mml:mi>
<mml:mi mathvariant="italic">&#x3f5;</mml:mi>
<mml:mn>2</mml:mn>
</mml:msubsup>
<mml:msub>
<mml:mi mathvariant="bold-italic">I</mml:mi>
<mml:mi>n</mml:mi>
</mml:msub>
</mml:mrow>
</mml:math>
</inline-formula> and <inline-formula id="inf21">
<mml:math id="m26">
<mml:mrow>
<mml:msub>
<mml:mi mathvariant="bold-italic">I</mml:mi>
<mml:mi>n</mml:mi>
</mml:msub>
</mml:mrow>
</mml:math>
</inline-formula> denotes the identity matrix of <inline-formula id="inf22">
<mml:math id="m27">
<mml:mrow>
<mml:mi>n</mml:mi>
<mml:mo>&#xd7;</mml:mo>
<mml:mi>n</mml:mi>
</mml:mrow>
</mml:math>
</inline-formula>.</p>
</sec>
<sec id="s2-2">
<title>2.2 Sparse Approximation of the Gaussian Process</title>
<p>In practice, with a higher-dimensional dataset, the GP often faces the challenge of high computational cost (<xref ref-type="bibr" rid="B20">Li, 2022b</xref>). Sparse approximation offers a reliable solution to overcome the computational limitations of the GP model. Here, the principle behind sparse approximation is using a subset of the dataset to train the GP model. Within the SGP, the selection of the subset is performed repeatedly using greedy algorithms.</p>
<p>The scheme of GP approximation using a subset <italic>m</italic> of GP regression models with <italic>n</italic> data points can be achieved using <xref ref-type="disp-formula" rid="e6">(6)</xref>&#x2013;<xref ref-type="disp-formula" rid="e7">(7)</xref>:<disp-formula id="e6">
<mml:math id="m28">
<mml:mrow>
<mml:msub>
<mml:mi>f</mml:mi>
<mml:mrow>
<mml:mi>S</mml:mi>
<mml:mi>R</mml:mi>
</mml:mrow>
</mml:msub>
<mml:mrow>
<mml:mo>(</mml:mo>
<mml:mrow>
<mml:msub>
<mml:mi mathvariant="bold">x</mml:mi>
<mml:mi>i</mml:mi>
</mml:msub>
</mml:mrow>
<mml:mo>)</mml:mo>
</mml:mrow>
<mml:mo>&#x3d;</mml:mo>
<mml:munderover>
<mml:mstyle displaystyle="true">
<mml:mo>&#x2211;</mml:mo>
</mml:mstyle>
<mml:mrow>
<mml:mi>j</mml:mi>
<mml:mo>&#x3d;</mml:mo>
<mml:mn>1</mml:mn>
</mml:mrow>
<mml:mi>m</mml:mi>
</mml:munderover>
<mml:msub>
<mml:mtext>&#x3b1;</mml:mtext>
<mml:mi>j</mml:mi>
</mml:msub>
<mml:mi>C</mml:mi>
<mml:mrow>
<mml:mo>(</mml:mo>
<mml:mrow>
<mml:msub>
<mml:mi mathvariant="bold">x</mml:mi>
<mml:mi>i</mml:mi>
</mml:msub>
<mml:mo>,</mml:mo>
<mml:mi mathvariant="bold">x</mml:mi>
</mml:mrow>
<mml:mo>)</mml:mo>
</mml:mrow>
</mml:mrow>
</mml:math>
<label>(6)</label>
</disp-formula>
<disp-formula id="e7">
<mml:math id="m29">
<mml:mrow>
<mml:msub>
<mml:mi mathvariant="bold">&#x3b1;</mml:mi>
<mml:mi mathvariant="bold-italic">m</mml:mi>
</mml:msub>
<mml:mo>&#x223c;</mml:mo>
<mml:mi mathvariant="script">N</mml:mi>
<mml:mrow>
<mml:mo>(</mml:mo>
<mml:mn mathvariant="bold">0</mml:mn>
<mml:mo>,</mml:mo>
<mml:msubsup>
<mml:mi mathvariant="bold-italic">K</mml:mi>
<mml:mrow>
<mml:mi mathvariant="bold-italic">mm</mml:mi>
</mml:mrow>
<mml:mrow>
<mml:mo>&#x2212;</mml:mo>
<mml:mn>1</mml:mn>
</mml:mrow>
</mml:msubsup>
<mml:mo>)</mml:mo>
</mml:mrow>
</mml:mrow>
</mml:math>
<label>(7)</label>
</disp-formula>where the associated mean and variance of <inline-formula id="inf23">
<mml:math id="m30">
<mml:mrow>
<mml:msub>
<mml:mi>f</mml:mi>
<mml:mrow>
<mml:mi>S</mml:mi>
<mml:mi>R</mml:mi>
</mml:mrow>
</mml:msub>
<mml:mrow>
<mml:mo>(</mml:mo>
<mml:mrow>
<mml:msub>
<mml:mi mathvariant="bold">x</mml:mi>
<mml:mi>i</mml:mi>
</mml:msub>
</mml:mrow>
<mml:mo>)</mml:mo>
</mml:mrow>
</mml:mrow>
</mml:math>
</inline-formula> can be obtained using <xref ref-type="disp-formula" rid="e8">(8)</xref>&#x2013;<xref ref-type="disp-formula" rid="e9">(9)</xref>:<disp-formula id="e8">
<mml:math id="m31">
<mml:mrow>
<mml:msub>
<mml:mi>&#x3bc;</mml:mi>
<mml:mrow>
<mml:mi>S</mml:mi>
<mml:mi>R</mml:mi>
</mml:mrow>
</mml:msub>
<mml:mrow>
<mml:mo>(</mml:mo>
<mml:mrow>
<mml:msub>
<mml:mi>f</mml:mi>
<mml:mrow>
<mml:mi>S</mml:mi>
<mml:mi>R</mml:mi>
</mml:mrow>
</mml:msub>
<mml:mrow>
<mml:mo>(</mml:mo>
<mml:mrow>
<mml:msub>
<mml:mi mathvariant="bold">x</mml:mi>
<mml:mi>i</mml:mi>
</mml:msub>
</mml:mrow>
<mml:mo>)</mml:mo>
</mml:mrow>
</mml:mrow>
<mml:mo>)</mml:mo>
</mml:mrow>
<mml:mo>&#x3d;</mml:mo>
<mml:msubsup>
<mml:mi mathvariant="bold-italic">C</mml:mi>
<mml:mi mathvariant="bold-italic">m</mml:mi>
<mml:mi mathvariant="bold-italic">T</mml:mi>
</mml:msubsup>
<mml:mrow>
<mml:mo>(</mml:mo>
<mml:mrow>
<mml:msub>
<mml:mi mathvariant="bold">x</mml:mi>
<mml:mi>i</mml:mi>
</mml:msub>
</mml:mrow>
<mml:mo>)</mml:mo>
</mml:mrow>
<mml:msup>
<mml:mrow>
<mml:mrow>
<mml:mo>(</mml:mo>
<mml:mrow>
<mml:msub>
<mml:mi mathvariant="bold-italic">C</mml:mi>
<mml:mrow>
<mml:mi mathvariant="bold-italic">mn</mml:mi>
</mml:mrow>
</mml:msub>
<mml:msub>
<mml:mi mathvariant="bold-italic">C</mml:mi>
<mml:mrow>
<mml:mi mathvariant="bold-italic">nm</mml:mi>
</mml:mrow>
</mml:msub>
<mml:mo>&#x2b;</mml:mo>
<mml:msubsup>
<mml:mi>&#x3c3;</mml:mi>
<mml:mi>n</mml:mi>
<mml:mn>2</mml:mn>
</mml:msubsup>
<mml:msub>
<mml:mi mathvariant="bold-italic">C</mml:mi>
<mml:mrow>
<mml:mi mathvariant="bold-italic">mm</mml:mi>
</mml:mrow>
</mml:msub>
</mml:mrow>
<mml:mo>)</mml:mo>
</mml:mrow>
</mml:mrow>
<mml:mrow>
<mml:mo>&#x2212;</mml:mo>
<mml:mn>1</mml:mn>
</mml:mrow>
</mml:msup>
<mml:msub>
<mml:mi mathvariant="bold-italic">C</mml:mi>
<mml:mrow>
<mml:mi mathvariant="bold-italic">mn</mml:mi>
</mml:mrow>
</mml:msub>
<mml:mi mathvariant="bold">y</mml:mi>
</mml:mrow>
</mml:math>
<label>(8)</label>
</disp-formula>
<disp-formula id="e9">
<mml:math id="m32">
<mml:mrow>
<mml:msub>
<mml:mi>&#x3c3;</mml:mi>
<mml:mrow>
<mml:mi>S</mml:mi>
<mml:mi>R</mml:mi>
</mml:mrow>
</mml:msub>
<mml:mrow>
<mml:mo>(</mml:mo>
<mml:mrow>
<mml:msub>
<mml:mi>f</mml:mi>
<mml:mrow>
<mml:mi>S</mml:mi>
<mml:mi>R</mml:mi>
</mml:mrow>
</mml:msub>
<mml:mrow>
<mml:mo>(</mml:mo>
<mml:mrow>
<mml:msub>
<mml:mi mathvariant="bold">x</mml:mi>
<mml:mi>i</mml:mi>
</mml:msub>
</mml:mrow>
<mml:mo>)</mml:mo>
</mml:mrow>
</mml:mrow>
<mml:mo>)</mml:mo>
</mml:mrow>
<mml:mo>&#x3d;</mml:mo>
<mml:msubsup>
<mml:mi>&#x3c3;</mml:mi>
<mml:mi>n</mml:mi>
<mml:mn>2</mml:mn>
</mml:msubsup>
<mml:msubsup>
<mml:mi mathvariant="bold-italic">C</mml:mi>
<mml:mi mathvariant="bold-italic">m</mml:mi>
<mml:mi mathvariant="bold-italic">T</mml:mi>
</mml:msubsup>
<mml:mrow>
<mml:mo>(</mml:mo>
<mml:mrow>
<mml:msub>
<mml:mi mathvariant="bold">x</mml:mi>
<mml:mi>i</mml:mi>
</mml:msub>
</mml:mrow>
<mml:mo>)</mml:mo>
</mml:mrow>
<mml:msup>
<mml:mrow>
<mml:mrow>
<mml:mo>(</mml:mo>
<mml:mrow>
<mml:msub>
<mml:mi mathvariant="bold-italic">C</mml:mi>
<mml:mrow>
<mml:mi mathvariant="bold-italic">mn</mml:mi>
</mml:mrow>
</mml:msub>
<mml:msub>
<mml:mi mathvariant="bold-italic">C</mml:mi>
<mml:mrow>
<mml:mi mathvariant="bold-italic">nm</mml:mi>
</mml:mrow>
</mml:msub>
<mml:mo>&#x2b;</mml:mo>
<mml:msubsup>
<mml:mi>&#x3c3;</mml:mi>
<mml:mi>n</mml:mi>
<mml:mn>2</mml:mn>
</mml:msubsup>
<mml:msub>
<mml:mi mathvariant="bold-italic">C</mml:mi>
<mml:mrow>
<mml:mi mathvariant="bold-italic">mm</mml:mi>
</mml:mrow>
</mml:msub>
</mml:mrow>
<mml:mo>)</mml:mo>
</mml:mrow>
</mml:mrow>
<mml:mrow>
<mml:mo>&#x2212;</mml:mo>
<mml:mn>1</mml:mn>
</mml:mrow>
</mml:msup>
<mml:msub>
<mml:mi mathvariant="bold-italic">C</mml:mi>
<mml:mi mathvariant="bold-italic">m</mml:mi>
</mml:msub>
<mml:mrow>
<mml:mo>(</mml:mo>
<mml:mrow>
<mml:msub>
<mml:mi mathvariant="bold">x</mml:mi>
<mml:mi>i</mml:mi>
</mml:msub>
</mml:mrow>
<mml:mo>)</mml:mo>
</mml:mrow>
</mml:mrow>
</mml:math>
<label>(9)</label>
</disp-formula>and the posterior mean of <inline-formula id="inf24">
<mml:math id="m33">
<mml:mrow>
<mml:msub>
<mml:mi mathvariant="bold">&#x3b1;</mml:mi>
<mml:mi mathvariant="bold-italic">m</mml:mi>
</mml:msub>
</mml:mrow>
</mml:math>
</inline-formula> can be computed by <xref ref-type="disp-formula" rid="e10">(10)</xref>:<disp-formula id="e10">
<mml:math id="m34">
<mml:mrow>
<mml:msub>
<mml:mi mathvariant="bold">&#x3b1;</mml:mi>
<mml:mi mathvariant="bold-italic">m</mml:mi>
</mml:msub>
<mml:mo>&#x3d;</mml:mo>
<mml:msup>
<mml:mrow>
<mml:mrow>
<mml:mo>(</mml:mo>
<mml:mrow>
<mml:msub>
<mml:mi mathvariant="bold-italic">C</mml:mi>
<mml:mrow>
<mml:mi mathvariant="bold-italic">mn</mml:mi>
</mml:mrow>
</mml:msub>
<mml:msub>
<mml:mi mathvariant="bold-italic">C</mml:mi>
<mml:mrow>
<mml:mi mathvariant="bold-italic">nm</mml:mi>
</mml:mrow>
</mml:msub>
<mml:mo>&#x2b;</mml:mo>
<mml:msubsup>
<mml:mi>&#x3c3;</mml:mi>
<mml:mi>n</mml:mi>
<mml:mn>2</mml:mn>
</mml:msubsup>
<mml:msub>
<mml:mi mathvariant="bold-italic">C</mml:mi>
<mml:mrow>
<mml:mi mathvariant="bold-italic">mm</mml:mi>
</mml:mrow>
</mml:msub>
</mml:mrow>
<mml:mo>)</mml:mo>
</mml:mrow>
</mml:mrow>
<mml:mrow>
<mml:mo>&#x2212;</mml:mo>
<mml:mn>1</mml:mn>
</mml:mrow>
</mml:msup>
<mml:msub>
<mml:mi mathvariant="bold-italic">C</mml:mi>
<mml:mrow>
<mml:mi mathvariant="bold-italic">mn</mml:mi>
</mml:mrow>
</mml:msub>
<mml:mi mathvariant="bold">y</mml:mi>
</mml:mrow>
</mml:math>
<label>(10)</label>
</disp-formula>
</p>
</sec>
<sec id="s2-3">
<title>2.3 Objective Function</title>
<p>To train the SGP model, a covariance function must be selected to define the similarity of any two sets of input points, giving rise to the covariance matrix. A popular selection of the covariance function is the squared exponential (SE) function, which is written by <xref ref-type="disp-formula" rid="e11">(11)</xref>:<disp-formula id="e11">
<mml:math id="m35">
<mml:mrow>
<mml:mi>C</mml:mi>
<mml:mrow>
<mml:mo>(</mml:mo>
<mml:mrow>
<mml:msub>
<mml:mi>x</mml:mi>
<mml:mi>i</mml:mi>
</mml:msub>
<mml:mo>,</mml:mo>
<mml:msub>
<mml:mi>x</mml:mi>
<mml:mi>j</mml:mi>
</mml:msub>
</mml:mrow>
<mml:mo>)</mml:mo>
</mml:mrow>
<mml:mo>&#x3d;</mml:mo>
<mml:msup>
<mml:mi>&#x3b7;</mml:mi>
<mml:mn>2</mml:mn>
</mml:msup>
<mml:mi>e</mml:mi>
<mml:mi>x</mml:mi>
<mml:mi>p</mml:mi>
<mml:mrow>
<mml:mo>[</mml:mo>
<mml:mrow>
<mml:mo>&#x2212;</mml:mo>
<mml:mfrac>
<mml:mn>1</mml:mn>
<mml:mn>2</mml:mn>
</mml:mfrac>
<mml:munderover>
<mml:mstyle displaystyle="true">
<mml:mo>&#x2211;</mml:mo>
</mml:mstyle>
<mml:mrow>
<mml:mi>k</mml:mi>
<mml:mo>&#x3d;</mml:mo>
<mml:mn>1</mml:mn>
</mml:mrow>
<mml:mi>d</mml:mi>
</mml:munderover>
<mml:msup>
<mml:mrow>
<mml:mrow>
<mml:mo>(</mml:mo>
<mml:mrow>
<mml:mfrac>
<mml:mrow>
<mml:msub>
<mml:mi>x</mml:mi>
<mml:mi>i</mml:mi>
</mml:msub>
<mml:mo>&#x2212;</mml:mo>
<mml:msub>
<mml:mi>x</mml:mi>
<mml:mi>j</mml:mi>
</mml:msub>
</mml:mrow>
<mml:mrow>
<mml:msub>
<mml:mi>l</mml:mi>
<mml:mi>k</mml:mi>
</mml:msub>
</mml:mrow>
</mml:mfrac>
</mml:mrow>
<mml:mo>)</mml:mo>
</mml:mrow>
</mml:mrow>
<mml:mn>2</mml:mn>
</mml:msup>
</mml:mrow>
<mml:mo>]</mml:mo>
</mml:mrow>
</mml:mrow>
</mml:math>
<label>(11)</label>
</disp-formula>where <inline-formula id="inf25">
<mml:math id="m36">
<mml:mrow>
<mml:msup>
<mml:mi>&#x3b7;</mml:mi>
<mml:mn>2</mml:mn>
</mml:msup>
</mml:mrow>
</mml:math>
</inline-formula> is the signal variance, and <inline-formula id="inf26">
<mml:math id="m37">
<mml:mi>l</mml:mi>
</mml:math>
</inline-formula> is the characteristic length scale. Thus, to estimate the parameters <inline-formula id="inf27">
<mml:math id="m38">
<mml:mrow>
<mml:mi mathvariant="bold">&#x398;</mml:mi>
<mml:mo>&#x3d;</mml:mo>
<mml:mrow>
<mml:mo>{</mml:mo>
<mml:mrow>
<mml:mi>&#x3b7;</mml:mi>
<mml:mo>,</mml:mo>
<mml:mi>l</mml:mi>
</mml:mrow>
<mml:mo>}</mml:mo>
</mml:mrow>
</mml:mrow>
</mml:math>
</inline-formula>, the objective function of SGP is to maximize the likelihood function expressed in <xref ref-type="disp-formula" rid="e12">(12)</xref>:<disp-formula id="e12">
<mml:math id="m39">
<mml:mrow>
<mml:mi mathvariant="bold">&#x2112;</mml:mi>
<mml:mrow>
<mml:mo>(</mml:mo>
<mml:mi mathvariant="bold">&#x398;</mml:mi>
<mml:mo>)</mml:mo>
</mml:mrow>
<mml:mo>&#x3d;</mml:mo>
<mml:mfrac>
<mml:mn>1</mml:mn>
<mml:mn>2</mml:mn>
</mml:mfrac>
<mml:msup>
<mml:mi mathvariant="bold">y</mml:mi>
<mml:mi mathvariant="bold-italic">T</mml:mi>
</mml:msup>
<mml:msup>
<mml:mi mathvariant="bold-italic">K</mml:mi>
<mml:mrow>
<mml:mo>&#x2212;</mml:mo>
<mml:mn>1</mml:mn>
</mml:mrow>
</mml:msup>
<mml:mi mathvariant="bold">y</mml:mi>
<mml:mo>&#x2b;</mml:mo>
<mml:mfrac>
<mml:mn>1</mml:mn>
<mml:mn>2</mml:mn>
</mml:mfrac>
<mml:mi mathvariant="bold">log</mml:mi>
<mml:mrow>
<mml:mo>&#x7c;</mml:mo>
<mml:mi mathvariant="bold-italic">K</mml:mi>
<mml:mo>&#x7c;</mml:mo>
</mml:mrow>
<mml:mo>&#x2b;</mml:mo>
<mml:mfrac>
<mml:mi>n</mml:mi>
<mml:mn>2</mml:mn>
</mml:mfrac>
<mml:mi mathvariant="bold">log</mml:mi>
<mml:mrow>
<mml:mo>&#x7c;</mml:mo>
<mml:mrow>
<mml:mn mathvariant="bold">2</mml:mn>
<mml:mi mathvariant="bold-italic">&#x3c0;</mml:mi>
</mml:mrow>
<mml:mo>&#x7c;</mml:mo>
</mml:mrow>
</mml:mrow>
</mml:math>
<label>(12)</label>
</disp-formula>
</p>
</sec>
<sec id="s2-4">
<title>2.4 State-Of-The-Art Probabilistic Forecasting Models</title>
<p>To demonstrate the outperformance of the proposed probabilistic forecasting approach using SGP, three popular state-of-the-art approaches were selected to perform a comparative analysis, including the quantile regression gradient boosting machine (QRGBM), the kernel density estimation (KDE), and the k-nearest neighbor (KNN). These state-of-the-art approaches are presented below.</p>
<p>QRGBM is a meta-algorithm technique that combines an ensemble of weak regression trees as a weighted sum to reduce both bias and variance (<xref ref-type="bibr" rid="B14">Landry et al., 2016</xref>). Similar to the traditional gradient boosting tree, it combines the advantages of both the regression and gradient boosting algorithms, which enables it to model complex nonlinear relationships that may include interactions among predictors.</p>
<p>KDE is a classic nonparametric estimation method used in a wide variety of probabilistic forecasting tasks (<xref ref-type="bibr" rid="B3">Botev et al., 2010</xref>; <xref ref-type="bibr" rid="B13">Kim &#x26; Scott 2012</xref>). It does not require <italic>a priori</italic> assumption that the data should follow a certain distribution, which is the key difference between the KDE and other parametric approaches.</p>
<p>KNN is a probabilistic forecasting approach that computes the probability distribution of the mean multiple nearest neighbors (<xref ref-type="bibr" rid="B12">Keller et al., 1985</xref>; <xref ref-type="bibr" rid="B1">Abu Alfeilat et al., 2019</xref>). The main advantage of KNN is that it does not assume the smoothness of the functions in forecasting tasks. It has been widely applied as a state-of-the-art forecasting algorithm in various engineering applications.</p>
</sec>
<sec id="s2-5">
<title>2.5 Measurement Metrics</title>
<p>To assess the quality of the tested algorithms in terms of probabilistic forecasting of landslide instant displacement, the evaluation metric namely Continuous Ranked Probability Score (CRPS) was utilized in this study. The CRPS was designed to quantify the difference between a continuous forecasted probability distribution (i.e., prediction) and a deterministic observation value (i.e., the ground truth value). The CRPS can be computed using <xref ref-type="disp-formula" rid="e13">(13)</xref>&#x2013;<xref ref-type="disp-formula" rid="e14">(14)</xref> (<xref ref-type="bibr" rid="B31">Ton et al., 2018</xref>):<disp-formula id="e13">
<mml:math id="m40">
<mml:mrow>
<mml:mrow>
<mml:mover accent="true">
<mml:mi>F</mml:mi>
<mml:mo>&#x5e;</mml:mo>
</mml:mover>
</mml:mrow>
<mml:mrow>
<mml:mo>(</mml:mo>
<mml:mrow>
<mml:msub>
<mml:mi>y</mml:mi>
<mml:mi>i</mml:mi>
</mml:msub>
</mml:mrow>
<mml:mo>)</mml:mo>
</mml:mrow>
<mml:mo>&#x3d;</mml:mo>
<mml:munderover>
<mml:mstyle displaystyle="true">
<mml:mo>&#x222b;</mml:mo>
</mml:mstyle>
<mml:mrow>
<mml:mo>&#x2212;</mml:mo>
<mml:mi>&#x221e;</mml:mi>
</mml:mrow>
<mml:mrow>
<mml:msub>
<mml:mi>y</mml:mi>
<mml:mi>i</mml:mi>
</mml:msub>
</mml:mrow>
</mml:munderover>
<mml:mi>p</mml:mi>
<mml:mrow>
<mml:mo>(</mml:mo>
<mml:mrow>
<mml:mrow>
<mml:mrow>
<mml:mover accent="true">
<mml:mrow>
<mml:msub>
<mml:mi>y</mml:mi>
<mml:mi>i</mml:mi>
</mml:msub>
</mml:mrow>
<mml:mo stretchy="true">&#x5e;</mml:mo>
</mml:mover>
</mml:mrow>
<mml:mo>&#x7c;</mml:mo>
</mml:mrow>
<mml:msub>
<mml:mi>x</mml:mi>
<mml:mi>i</mml:mi>
</mml:msub>
</mml:mrow>
<mml:mo>)</mml:mo>
</mml:mrow>
<mml:mi>d</mml:mi>
<mml:msub>
<mml:mi>x</mml:mi>
<mml:mi>i</mml:mi>
</mml:msub>
</mml:mrow>
</mml:math>
<label>(13)</label>
</disp-formula>
<disp-formula id="e14">
<mml:math id="m41">
<mml:mrow>
<mml:mi>H</mml:mi>
<mml:mrow>
<mml:mo>(</mml:mo>
<mml:mrow>
<mml:msub>
<mml:mi>y</mml:mi>
<mml:mi>i</mml:mi>
</mml:msub>
<mml:mo>&#x2212;</mml:mo>
<mml:mrow>
<mml:mover accent="true">
<mml:mrow>
<mml:msub>
<mml:mi>y</mml:mi>
<mml:mi>i</mml:mi>
</mml:msub>
</mml:mrow>
<mml:mo stretchy="true">&#x5e;</mml:mo>
</mml:mover>
</mml:mrow>
</mml:mrow>
<mml:mo>)</mml:mo>
</mml:mrow>
<mml:mo>&#x3d;</mml:mo>
<mml:mrow>
<mml:mo>{</mml:mo>
<mml:mrow>
<mml:mtable>
<mml:mtr>
<mml:mtd>
<mml:mn>1</mml:mn>
</mml:mtd>
<mml:mtd>
<mml:mrow>
<mml:mi>if</mml:mi>
<mml:msub>
<mml:mi>y</mml:mi>
<mml:mi>i</mml:mi>
</mml:msub>
<mml:mo>&#x2265;</mml:mo>
<mml:mrow>
<mml:mover accent="true">
<mml:mrow>
<mml:msub>
<mml:mi>y</mml:mi>
<mml:mi>i</mml:mi>
</mml:msub>
</mml:mrow>
<mml:mo stretchy="true">&#x5e;</mml:mo>
</mml:mover>
</mml:mrow>
</mml:mrow>
</mml:mtd>
</mml:mtr>
<mml:mtr>
<mml:mtd>
<mml:mn>0</mml:mn>
</mml:mtd>
<mml:mtd>
<mml:mrow>
<mml:mi>o</mml:mi>
<mml:mi>t</mml:mi>
<mml:mi>h</mml:mi>
<mml:mi>e</mml:mi>
<mml:mi>r</mml:mi>
<mml:mi>w</mml:mi>
<mml:mi>i</mml:mi>
<mml:mi>s</mml:mi>
<mml:mi>e</mml:mi>
</mml:mrow>
</mml:mtd>
</mml:mtr>
</mml:mtable>
</mml:mrow>
</mml:mrow>
</mml:mrow>
</mml:math>
<label>(14)</label>
</disp-formula>where <inline-formula id="inf28">
<mml:math id="m42">
<mml:mrow>
<mml:msub>
<mml:mi>x</mml:mi>
<mml:mi>i</mml:mi>
</mml:msub>
</mml:mrow>
</mml:math>
</inline-formula> represents the input data, <inline-formula id="inf29">
<mml:math id="m43">
<mml:mrow>
<mml:msub>
<mml:mi>y</mml:mi>
<mml:mi>i</mml:mi>
</mml:msub>
</mml:mrow>
</mml:math>
</inline-formula> is the actual value of the ground truth, <inline-formula id="inf30">
<mml:math id="m44">
<mml:mrow>
<mml:mover accent="true">
<mml:mrow>
<mml:msub>
<mml:mi>y</mml:mi>
<mml:mi>i</mml:mi>
</mml:msub>
</mml:mrow>
<mml:mo stretchy="true">&#x5e;</mml:mo>
</mml:mover>
</mml:mrow>
</mml:math>
</inline-formula> is the predicted mean value, <inline-formula id="inf31">
<mml:math id="m45">
<mml:mrow>
<mml:mrow>
<mml:mover accent="true">
<mml:mi>F</mml:mi>
<mml:mo>&#x5e;</mml:mo>
</mml:mover>
</mml:mrow>
<mml:mrow>
<mml:mo>(</mml:mo>
<mml:msub>
<mml:mi>y</mml:mi>
<mml:mi>i</mml:mi>
</mml:msub>
<mml:mo>)</mml:mo>
</mml:mrow>
</mml:mrow>
</mml:math>
</inline-formula> represents the cumulative density function (CDF) of the <inline-formula id="inf32">
<mml:math id="m46">
<mml:mrow>
<mml:mover accent="true">
<mml:mrow>
<mml:msub>
<mml:mi>y</mml:mi>
<mml:mi>i</mml:mi>
</mml:msub>
</mml:mrow>
<mml:mo stretchy="true">&#x5e;</mml:mo>
</mml:mover>
</mml:mrow>
</mml:math>
</inline-formula>; and <inline-formula id="inf33">
<mml:math id="m47">
<mml:mrow>
<mml:mi>H</mml:mi>
<mml:mrow>
<mml:mo>(</mml:mo>
<mml:mo>)</mml:mo>
</mml:mrow>
</mml:mrow>
</mml:math>
</inline-formula> denotes the binary step function with the observed sample at the step point. We can then compute the CRPS using <xref ref-type="disp-formula" rid="e15">(15)</xref> as follows:<disp-formula id="e15">
<mml:math id="m48">
<mml:mrow>
<mml:mi>C</mml:mi>
<mml:mi>R</mml:mi>
<mml:mi>P</mml:mi>
<mml:mi>S</mml:mi>
<mml:mo>&#x3d;</mml:mo>
<mml:mfrac>
<mml:mn>1</mml:mn>
<mml:mi>N</mml:mi>
</mml:mfrac>
<mml:munderover>
<mml:mstyle displaystyle="true">
<mml:mo>&#x2211;</mml:mo>
</mml:mstyle>
<mml:mrow>
<mml:mi>i</mml:mi>
<mml:mo>&#x3d;</mml:mo>
<mml:mn>1</mml:mn>
</mml:mrow>
<mml:mi>N</mml:mi>
</mml:munderover>
<mml:munderover>
<mml:mstyle displaystyle="true">
<mml:mo>&#x222b;</mml:mo>
</mml:mstyle>
<mml:mrow>
<mml:mo>&#x2212;</mml:mo>
<mml:mi>&#x221e;</mml:mi>
</mml:mrow>
<mml:mrow>
<mml:mo>&#x2b;</mml:mo>
<mml:mi>&#x221e;</mml:mi>
</mml:mrow>
</mml:munderover>
<mml:msup>
<mml:mrow>
<mml:mrow>
<mml:mo>[</mml:mo>
<mml:mrow>
<mml:mrow>
<mml:mover accent="true">
<mml:mi>F</mml:mi>
<mml:mo>&#x5e;</mml:mo>
</mml:mover>
</mml:mrow>
<mml:mrow>
<mml:mo>(</mml:mo>
<mml:mrow>
<mml:msub>
<mml:mi>y</mml:mi>
<mml:mi>i</mml:mi>
</mml:msub>
</mml:mrow>
<mml:mo>)</mml:mo>
</mml:mrow>
<mml:mo>&#x2212;</mml:mo>
<mml:mi>H</mml:mi>
<mml:mrow>
<mml:mo>(</mml:mo>
<mml:mrow>
<mml:msub>
<mml:mi>y</mml:mi>
<mml:mi>i</mml:mi>
</mml:msub>
<mml:mo>&#x2212;</mml:mo>
<mml:mrow>
<mml:mover accent="true">
<mml:mrow>
<mml:msub>
<mml:mi>y</mml:mi>
<mml:mi>i</mml:mi>
</mml:msub>
</mml:mrow>
<mml:mo stretchy="true">&#x5e;</mml:mo>
</mml:mover>
</mml:mrow>
</mml:mrow>
<mml:mo>)</mml:mo>
</mml:mrow>
</mml:mrow>
<mml:mo>]</mml:mo>
</mml:mrow>
</mml:mrow>
<mml:mn>2</mml:mn>
</mml:msup>
<mml:mi>d</mml:mi>
<mml:msub>
<mml:mi>y</mml:mi>
<mml:mi>i</mml:mi>
</mml:msub>
</mml:mrow>
</mml:math>
<label>(15)</label>
</disp-formula>where <inline-formula id="inf34">
<mml:math id="m49">
<mml:mi>N</mml:mi>
</mml:math>
</inline-formula> represents total number of data points in the test dataset.</p>
</sec>
</sec>
<sec id="s3">
<title>3 Dataset Collection</title>
<p>In this study, time-series displacement data were collected from our case study area, in southwest China. The case study area had landslide occurrences with a wide spatial distribution (<xref ref-type="bibr" rid="B4">Cui et al., 2021</xref>). The main material on the case study area slope were enormous deposits of silty clay and fragmented rubble, which are often loose and chaotic. The underlying bedrock of the case study landslide consisted of siltstones and mudstones. The major triggering factors of the landslide were heavy rainfall.</p>
<p>To obtain the displacement data, global positioning system (GPS) technology was used to monitor the landslides surface displacement, which is a useful and straightforward method for landslide evolution analysis. The GPS points recorded the cumulative displacement of the target landslide. In this study, a total of six GPS points were configured on the slide slope since the first reported initiation of slope failure. Continuous monitoring of the cumulative displacement was then conducted using the GPS points. The locations of the GPS points were relatively stable, enabling continuous and reliable acquisition of displacement data in the temporal domain. The six GPS points are shown in <xref ref-type="fig" rid="F1">Figure 1</xref>.</p>
<fig id="F1" position="float">
<label>FIGURE 1</label>
<caption>
<p>Cracks measured by the GPS points on the front part of the slope.</p>
</caption>
<graphic xlink:href="feart-10-944301-g001.tif"/>
</fig>
<p>As shown in <xref ref-type="fig" rid="F1">Figure 1</xref>, the datasets contain multiple GPS time-series data monitoring the landslide deformation process. Within the figure, the label LF stands for the cracks measured by the GPS points. The evolution of the crack is the key indicator for quantify the landslide displacement on-site. The datasets display the cumulative displacement since the activation of slope failure. All data were recorded on a monthly basis, and the unit for the points was millimeters. In total, 6&#xa0;years of data were provided by field experts for training and testing the probabilistic forecasting models.</p>
</sec>
<sec id="s4">
<title>4 Experimental Results</title>
<p>To achieve accurate probabilistic forecasting of landslide displacement, field data from six single GPS points from the study area were utilized in this study. In total, 6-year monthly data from 2014 to 2019 were considered for training and testing the proposed SGP model. All displacement data were transformed from cumulative displacement into instant displacement, which measures the absolute increment between the two-time stamps. For each GPS point, data collected between 2014 and 2018 were used to train the SGP, and the data collected in 2019 were used as the test dataset.</p>
<p>In our experiment, the training epochs for all GPS-collected displacement time series were set to 150. The loss function utilized for training was based on maximum likelihood, as described in <xref ref-type="sec" rid="s2-3">Section 2.3</xref>. The average training time for all GPS points was 20&#xa0;s. The average PI production time was less than 1&#xa0;s. The convergence curves of the loss functions during the training process are shown in <xref ref-type="fig" rid="F2">Figure 2</xref>.</p>
<fig id="F2" position="float">
<label>FIGURE 2</label>
<caption>
<p>Convergence curves of loss functions during the training process.</p>
</caption>
<graphic xlink:href="feart-10-944301-g002.tif"/>
</fig>
<p>As illustrated in <xref ref-type="fig" rid="F2">Figure 2</xref>, the loss curves of all six GPS monitoring points exhibit similar patterns. The loss function is based on the objective function expressed in <xref ref-type="disp-formula" rid="e2">(2)</xref> in <xref ref-type="sec" rid="s2-3">Section 2.3</xref> above. The starting value of the loss function varied depending on the random initialization of the experiment. The loss values converged at approximately 50 epochs on average, and the variance significantly reduced thereafter. This phenomenon confirms the reliability of the SGP in effectively learning patterns from the displacement time series.</p>
<p>Prior to the performance evaluation of the proposed approach, the heterogeneity and sharpness of the test dataset were investigated. The test dataset contained the instant monthly displacement data collected in 2019. All test data per GPS point were rescaled between 0 and 1 <italic>via</italic> min-max scaling, and the histograms for the GPS points are presented in <xref ref-type="fig" rid="F3">Figure 3</xref>. The vertical axis represents the scaled frequency and the horizontal axis denotes the scaled instant displacement between 0 and 1. Evidently, all instant displacements followed a right-skewed distribution, which confirms the field experts&#x2019; opinion that the majority of the displacements were under the mode of slow motion. However, occasional heavy rainfall or over-irrigation could trigger faster seasonal displacements on the slope over a few months, which contributes to occurrences above the median value.</p>
<fig id="F3" position="float">
<label>FIGURE 3</label>
<caption>
<p>Histograms of the scaled test dataset for all GPS points.</p>
</caption>
<graphic xlink:href="feart-10-944301-g003.tif"/>
</fig>
<p>
<xref ref-type="fig" rid="F4">Figure 4</xref> displays the six selected timestamps within the test dataset for each GPS point. The predicted probability density function (PDF) was the probabilistic forecast output generated by the SGP model. The vertical red line denotes the actual scaled value that corresponds to its intersection on the horizontal axis. For GPS points 1, 3, and 6, the selected instant displacement was from the mode of faster seasonal displacement. Correspondingly, the actual value were within the region with a high probability density. For the other three GPS points, the timestamps were selected from the mode of slow displacement. The actual value of the displacement was smaller than the group median value but was still within the region of high probability density. This demonstrates the reliability of SGP in probabilistic forecasting.</p>
<fig id="F4" position="float">
<label>FIGURE 4</label>
<caption>
<p>Constructed PIs and actual target instant displacement of the test dataset.</p>
</caption>
<graphic xlink:href="feart-10-944301-g004.tif"/>
</fig>
<p>For comparative analysis, we merged all test data collected from the six GPS points and transformed the data into a Gaussian distribution that follows <inline-formula id="inf35">
<mml:math id="m50">
<mml:mrow>
<mml:mi mathvariant="script">E</mml:mi>
<mml:mrow>
<mml:mo>(</mml:mo>
<mml:mn>0,1</mml:mn>
<mml:mo>)</mml:mo>
</mml:mrow>
</mml:mrow>
</mml:math>
</inline-formula>. The mean value of the predicted probability distribution per point was considered as the point estimate of the displacement. The mean predicted values generated by all probabilistic prediction algorithms versus the actual measured instant displacement are shown in <xref ref-type="fig" rid="F5">Figure 5</xref>. It is notable that majority of the mean predicted values provided by SGP fall within a narrow band with respect to the diagonal red dashed line, which represents the corresponding actual value. In comparison, more outlier points were generated outside the narrow band provided by the other state-of-the-art algorithms, including, QRGMB, KDE, and KNN. This confirms that the SGP is outstanding in terms of probabilistic forecasting of landslide displacement (see <xref ref-type="fig" rid="F5">Figure 5</xref>).</p>
<fig id="F5" position="float">
<label>FIGURE 5</label>
<caption>
<p>Actual value versus predicted mean value for all algorithms tested.</p>
</caption>
<graphic xlink:href="feart-10-944301-g005.tif"/>
</fig>
<p>For a quantitative performance comparison, CRPS (see <xref ref-type="sec" rid="s2-5">Section 2.5</xref>, <xref ref-type="disp-formula" rid="e15">Eq. 15</xref>) was adopted as the measurement metric to evaluate the quality of the estimated probability density. <xref ref-type="table" rid="T1">Table 1</xref> presents the CRPS computed by all algorithms tested and in terms of all six GPS points. The proposed SGP model had the smallest CRPS score compared to the other state-of-the-art algorithms, which confirms the superiority of the proposed approach.</p>
<table-wrap id="T1" position="float">
<label>TABLE 1</label>
<caption>
<p>Summary of CRPS for all probabilistic algorithms tested.</p>
</caption>
<table>
<thead valign="top">
<tr>
<th rowspan="2" align="left">GPS point</th>
<th colspan="4" align="center">Algorithm</th>
</tr>
<tr>
<th align="center">SGP</th>
<th align="center">QRGBM</th>
<th align="center">KDE</th>
<th align="center">KNN</th>
</tr>
</thead>
<tbody valign="top">
<tr>
<td align="left">1</td>
<td align="char" char=".">
<bold>6.73</bold>
</td>
<td align="char" char=".">9.51</td>
<td align="char" char=".">8.97</td>
<td align="char" char=".">9.04</td>
</tr>
<tr>
<td align="left">2</td>
<td align="char" char=".">
<bold>7.24</bold>
</td>
<td align="char" char=".">8.32</td>
<td align="char" char=".">9.19</td>
<td align="char" char=".">12.06</td>
</tr>
<tr>
<td align="left">3</td>
<td align="char" char=".">
<bold>4.95</bold>
</td>
<td align="char" char=".">5.32</td>
<td align="char" char=".">6.86</td>
<td align="char" char=".">10.87</td>
</tr>
<tr>
<td align="left">4</td>
<td align="char" char=".">
<bold>9.26</bold>
</td>
<td align="char" char=".">9.33</td>
<td align="char" char=".">9.31</td>
<td align="char" char=".">9.79</td>
</tr>
<tr>
<td align="left">5</td>
<td align="char" char=".">
<bold>8.84</bold>
</td>
<td align="char" char=".">8.96</td>
<td align="char" char=".">10.11</td>
<td align="char" char=".">9.57</td>
</tr>
<tr>
<td align="left">6</td>
<td align="char" char=".">
<bold>7.21</bold>
</td>
<td align="char" char=".">7.25</td>
<td align="char" char=".">8.11</td>
<td align="char" char=".">9.34</td>
</tr>
<tr>
<td align="left">Mean</td>
<td align="char" char=".">
<bold>7.37</bold>
</td>
<td align="char" char=".">8.12</td>
<td align="char" char=".">8.76</td>
<td align="char" char=".">10.11</td>
</tr>
<tr>
<td align="left">Standard deviation</td>
<td align="char" char=".">
<bold>1.42</bold>
</td>
<td align="char" char=".">1.46</td>
<td align="char" char=".">1.03</td>
<td align="char" char=".">1.04</td>
</tr>
</tbody>
</table>
</table-wrap>
</sec>
<sec id="s5">
<title>5 Conclusion</title>
<p>In this study, the uncertainties of future landslide displacements were quantified and formulated using Bayesian theory. The sparse Gaussian process was adopted to derive the inducing variable, variational inference, and variational distribution of the future displacement, while significantly reducing the computational cost. Compared with other state-of-the-art probabilistic forecasting models, the proposed SGP approach demonstrated outstanding performance in terms of accuracy, reliability, and computational efficiency. The probabilistic forecasting of future displacement has improved remarkably. The proposed approach can provide practical assistance to field engineering geologists in the hazard estimation of future landslide occurrences.</p>
</sec>
</body>
<back>
<sec id="s6" sec-type ="data-availability">
<title>Data Availability Statement</title>
<p>The raw data supporting the conclusions of this article will be made available by the authors, without undue reservation.</p>
</sec>
<sec id="s7">
<title>Author Contributions</title>
<p>WY and LW contributed to the study methodology and wrote the original draft. WY and YF contributed to the study data curation. contributed to data analysis and investigation. JW contributed to conceptualize the study and writing-original draft. All authors have read and agreed to the published version of the manuscript.</p>
</sec>
<sec sec-type="COI-statement" id="s8">
<title>Conflict of Interest</title>
<p>The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.</p>
</sec>
<sec sec-type="disclaimer" id="s9">
<title>Publisher&#x2019;s Note</title>
<p>All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article, or claim that may be made by its manufacturer, is not guaranteed or endorsed by the publisher.</p>
</sec>
<ref-list>
<title>References</title>
<ref id="B1">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Abu Alfeilat</surname>
<given-names>H. A.</given-names>
</name>
<name>
<surname>Hassanat</surname>
<given-names>A. B. A.</given-names>
</name>
<name>
<surname>Lasassmeh</surname>
<given-names>O.</given-names>
</name>
<name>
<surname>Tarawneh</surname>
<given-names>A. S.</given-names>
</name>
<name>
<surname>Alhasanat</surname>
<given-names>M. B.</given-names>
</name>
<name>
<surname>Eyal Salman</surname>
<given-names>H. S.</given-names>
</name>
<etal/>
</person-group> (<year>2019</year>). <article-title>Effects of Distance Measure Choice on K-Nearest Neighbor Classifier Performance: a Review</article-title>. <source>Big data</source> <volume>7</volume> (<issue>4</issue>), <fpage>221</fpage>&#x2013;<lpage>248</lpage>. <pub-id pub-id-type="doi">10.1089/big.2018.0175</pub-id> </citation>
</ref>
<ref id="B2">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Aggarwal</surname>
<given-names>A.</given-names>
</name>
<name>
<surname>Alshehri</surname>
<given-names>M.</given-names>
</name>
<name>
<surname>Kumar</surname>
<given-names>M.</given-names>
</name>
<name>
<surname>Alfarraj</surname>
<given-names>O.</given-names>
</name>
<name>
<surname>Sharma</surname>
<given-names>P.</given-names>
</name>
<name>
<surname>Pardasani</surname>
<given-names>K. R.</given-names>
</name>
</person-group> (<year>2020</year>). <article-title>Landslide Data Analysis Using Various Time-Series Forecasting Models</article-title>. <source>Comput. Electr. Eng.</source> <volume>88</volume>, <fpage>106858</fpage>. <pub-id pub-id-type="doi">10.1016/j.compeleceng.2020.106858</pub-id> </citation>
</ref>
<ref id="B3">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Botev</surname>
<given-names>Z. I.</given-names>
</name>
<name>
<surname>Grotowski</surname>
<given-names>J. F.</given-names>
</name>
<name>
<surname>Kroese</surname>
<given-names>D. P.</given-names>
</name>
</person-group> (<year>2010</year>). <article-title>Kernel Density Estimation via Diffusion</article-title>. <source>Ann. Statistics</source> <volume>38</volume> (<issue>5</issue>), <fpage>2916</fpage>&#x2013;<lpage>2957</lpage>. <pub-id pub-id-type="doi">10.1214/10-aos799</pub-id> </citation>
</ref>
<ref id="B4">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Cui</surname>
<given-names>S.</given-names>
</name>
<name>
<surname>Pei</surname>
<given-names>X.</given-names>
</name>
<name>
<surname>Jiang</surname>
<given-names>Y.</given-names>
</name>
<name>
<surname>Wang</surname>
<given-names>G.</given-names>
</name>
<name>
<surname>Fan</surname>
<given-names>X.</given-names>
</name>
<name>
<surname>Yang</surname>
<given-names>Q.</given-names>
</name>
<etal/>
</person-group> (<year>2021</year>). <article-title>Liquefaction within a Bedding Fault: Understanding the Initiation and Movement of the Daguangbao Landslide Triggered by the 2008 Wenchuan Earthquake (Ms &#x3d; 8.0)</article-title>. <source>Eng. Geol.</source> <volume>295</volume>, <fpage>106455</fpage>. <pub-id pub-id-type="doi">10.1016/j.enggeo.2021.106455</pub-id> </citation>
</ref>
<ref id="B5">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Deringer</surname>
<given-names>V. L.</given-names>
</name>
<name>
<surname>Bart&#xf3;k</surname>
<given-names>A. P.</given-names>
</name>
<name>
<surname>Bernstein</surname>
<given-names>N.</given-names>
</name>
<name>
<surname>Wilkins</surname>
<given-names>D. M.</given-names>
</name>
<name>
<surname>Ceriotti</surname>
<given-names>M.</given-names>
</name>
<name>
<surname>Cs&#xe1;nyi</surname>
<given-names>G.</given-names>
</name>
</person-group> (<year>2021</year>). <article-title>Gaussian Process Regression for Materials and Molecules</article-title>. <source>Chem. Rev.</source> <volume>121</volume> (<issue>16</issue>), <fpage>10073</fpage>&#x2013;<lpage>10141</lpage>. <pub-id pub-id-type="doi">10.1021/acs.chemrev.1c00022</pub-id> </citation>
</ref>
<ref id="B6">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Fan</surname>
<given-names>Z.</given-names>
</name>
<name>
<surname>Cai</surname>
<given-names>J.</given-names>
</name>
</person-group> (<year>2021</year>). <article-title>Effects of Unidirectional <italic>In Situ</italic> Stress on Crack Propagation of a Jointed Rock Mass Subjected to Stress Wave</article-title>. <source>Shock Vib.</source> <volume>2021</volume>, <fpage>1</fpage>&#x2013;<lpage>13</lpage>. <pub-id pub-id-type="doi">10.1155/2021/5529540</pub-id> </citation>
</ref>
<ref id="B7">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Fan</surname>
<given-names>Z.</given-names>
</name>
<name>
<surname>Zhang</surname>
<given-names>J.</given-names>
</name>
<name>
<surname>Xu</surname>
<given-names>H.</given-names>
</name>
<name>
<surname>Wang</surname>
<given-names>X.</given-names>
</name>
</person-group> (<year>2022</year>). <article-title>Transmission and Application of a P-Wave across Joints Based on a Modified G-&#x3bb; Model</article-title>. <source>Int. J. Rock Mech. Min. Sci.</source> <volume>150</volume>, <fpage>104991</fpage>. <pub-id pub-id-type="doi">10.1016/j.ijrmms.2021.104991</pub-id> </citation>
</ref>
<ref id="B8">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Fuhg</surname>
<given-names>J. N.</given-names>
</name>
<name>
<surname>Marino</surname>
<given-names>M.</given-names>
</name>
<name>
<surname>Bouklas</surname>
<given-names>N.</given-names>
</name>
</person-group> (<year>2022</year>). <article-title>Local Approximate Gaussian Process Regression for Data-Driven Constitutive Models: Development and Comparison with Neural Networks</article-title>. <source>Comput. Methods Appl. Mech. Eng.</source> <volume>388</volume>, <fpage>114217</fpage>. <pub-id pub-id-type="doi">10.1016/j.cma.2021.114217</pub-id> </citation>
</ref>
<ref id="B9">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>He</surname>
<given-names>Y.</given-names>
</name>
<name>
<surname>Kusiak</surname>
<given-names>A.</given-names>
</name>
</person-group> (<year>2018</year>). <article-title>Performance Assessment of Wind Turbines: Data-Derived Quantitative Metrics</article-title>. <source>IEEE Trans. Sustain. Energy</source> <volume>9</volume> (<issue>1</issue>), <fpage>65</fpage>&#x2013;<lpage>73</lpage>. <pub-id pub-id-type="doi">10.1109/TSTE.2017.2715061</pub-id> </citation>
</ref>
<ref id="B10">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Jamei</surname>
<given-names>M.</given-names>
</name>
<name>
<surname>Ahmadianfar</surname>
<given-names>I.</given-names>
</name>
<name>
<surname>Olumegbon</surname>
<given-names>I. A.</given-names>
</name>
<name>
<surname>Karbasi</surname>
<given-names>M.</given-names>
</name>
<name>
<surname>Asadi</surname>
<given-names>A.</given-names>
</name>
</person-group> (<year>2021</year>). <article-title>On the Assessment of Specific Heat Capacity of Nanofluids for Solar Energy Applications: Application of Gaussian Process Regression (GPR) Approach</article-title>. <source>J. Energy Storage</source> <volume>33</volume>, <fpage>102067</fpage>. <pub-id pub-id-type="doi">10.1016/j.est.2020.102067</pub-id> </citation>
</ref>
<ref id="B11">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Jiang</surname>
<given-names>Y.</given-names>
</name>
<name>
<surname>Xu</surname>
<given-names>Q.</given-names>
</name>
<name>
<surname>Lu</surname>
<given-names>Z.</given-names>
</name>
<name>
<surname>Luo</surname>
<given-names>H.</given-names>
</name>
<name>
<surname>Liao</surname>
<given-names>L.</given-names>
</name>
<name>
<surname>Dong</surname>
<given-names>X.</given-names>
</name>
</person-group> (<year>2021</year>). <article-title>Modelling and Predicting Landslide Displacements and Uncertainties by Multiple Machine-Learning Algorithms: Application to Baishuihe Landslide in Three Gorges Reservoir, China</article-title>. <source>Geomatics, Nat. Hazards Risk</source> <volume>12</volume> (<issue>1</issue>), <fpage>741</fpage>&#x2013;<lpage>762</lpage>. <pub-id pub-id-type="doi">10.1080/19475705.2021.1891145</pub-id> </citation>
</ref>
<ref id="B12">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Keller</surname>
<given-names>J. M.</given-names>
</name>
<name>
<surname>Gray</surname>
<given-names>M. R.</given-names>
</name>
<name>
<surname>Givens</surname>
<given-names>J. A.</given-names>
</name>
</person-group> (<year>1985</year>). <article-title>A Fuzzy K-Nearest Neighbor Algorithm</article-title>. <source>IEEE Trans. Syst. Man. Cybern.</source> <volume>SMC-15</volume> (<issue>4</issue>), <fpage>580</fpage>&#x2013;<lpage>585</lpage>. <pub-id pub-id-type="doi">10.1109/tsmc.1985.6313426</pub-id> </citation>
</ref>
<ref id="B13">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Kim</surname>
<given-names>J.</given-names>
</name>
<name>
<surname>Scott</surname>
<given-names>C. D.</given-names>
</name>
</person-group> (<year>2012</year>). <article-title>Robust Kernel Density Estimation</article-title>. <source>J. Mach. Learn. Res.</source> <volume>13</volume> (<issue>1</issue>), <fpage>2529</fpage>&#x2013;<lpage>2565</lpage>. </citation>
</ref>
<ref id="B14">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Landry</surname>
<given-names>M.</given-names>
</name>
<name>
<surname>Erlinger</surname>
<given-names>T. P.</given-names>
</name>
<name>
<surname>Patschke</surname>
<given-names>D.</given-names>
</name>
<name>
<surname>Varrichio</surname>
<given-names>C.</given-names>
</name>
</person-group> (<year>2016</year>). <article-title>Probabilistic Gradient Boosting Machines for GEFCom2014 Wind Forecasting</article-title>. <source>Int. J. Forecast.</source> <volume>32</volume> (<issue>3</issue>), <fpage>1061</fpage>&#x2013;<lpage>1066</lpage>. <pub-id pub-id-type="doi">10.1016/j.ijforecast.2016.02.002</pub-id> </citation>
</ref>
<ref id="B15">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Lewis</surname>
<given-names>R.</given-names>
</name>
<name>
<surname>Reinsel</surname>
<given-names>G. C.</given-names>
</name>
</person-group> (<year>1985</year>). <article-title>Prediction of Multivariate Time Series by Autoregressive Model Fitting</article-title>. <source>J. Multivar. analysis</source> <volume>16</volume> (<issue>3</issue>), <fpage>393</fpage>&#x2013;<lpage>411</lpage>. <pub-id pub-id-type="doi">10.1016/0047-259x(85)90027-2</pub-id> </citation>
</ref>
<ref id="B16">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Li</surname>
<given-names>H.</given-names>
</name>
<name>
<surname>Deng</surname>
<given-names>J.</given-names>
</name>
<name>
<surname>Feng</surname>
<given-names>P.</given-names>
</name>
<name>
<surname>Pu</surname>
<given-names>C.</given-names>
</name>
<name>
<surname>Arachchige</surname>
<given-names>D. D. K.</given-names>
</name>
<name>
<surname>Cheng</surname>
<given-names>Q.</given-names>
</name>
</person-group> (<year>2021b</year>). <article-title>Short-Term Nacelle Orientation Forecasting Using Bilinear Transformation and ICEEMDAN Framework</article-title>. <source>Front. Energy Res.</source> <volume>9</volume>, <fpage>780928</fpage>. <pub-id pub-id-type="doi">10.3389/fenrg.2021.780928</pub-id> </citation>
</ref>
<ref id="B17">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Li</surname>
<given-names>H.</given-names>
</name>
<name>
<surname>Deng</surname>
<given-names>J.</given-names>
</name>
<name>
<surname>Yuan</surname>
<given-names>S.</given-names>
</name>
<name>
<surname>Feng</surname>
<given-names>P.</given-names>
</name>
<name>
<surname>Arachchige</surname>
<given-names>D. D. K.</given-names>
</name>
</person-group> (<year>2021a</year>). <article-title>Monitoring and Identifying Wind Turbine Generator Bearing Faults Using Deep Belief Network and EWMA Control Charts</article-title>. <source>Front. Energy Res.</source> <volume>9</volume>, <fpage>799039</fpage>. <pub-id pub-id-type="doi">10.3389/fenrg.2021.799039</pub-id> </citation>
</ref>
<ref id="B18">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Li</surname>
<given-names>H.</given-names>
</name>
<name>
<surname>He</surname>
<given-names>Y.</given-names>
</name>
<name>
<surname>Xu</surname>
<given-names>Q.</given-names>
</name>
<name>
<surname>Deng</surname>
<given-names>j.</given-names>
</name>
<name>
<surname>Li</surname>
<given-names>W.</given-names>
</name>
<name>
<surname>Wei</surname>
<given-names>Y.</given-names>
</name>
</person-group> (<year>2022</year>). <article-title>Detection and Segmentation of Loess Landslides via Satellite Images: a Two-phase Framework</article-title>. <source>Landslides</source> <volume>19</volume>, <fpage>673</fpage>&#x2013;<lpage>686</lpage>. <pub-id pub-id-type="doi">10.1007/s10346-021-01789-0</pub-id> </citation>
</ref>
<ref id="B19">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Li</surname>
<given-names>H.</given-names>
</name>
</person-group> (<year>2022a</year>). <article-title>SCADA Data Based Wind Power Interval Prediction Using LUBE-Based Deep Residual Networks</article-title>. <source>Front. Energy Res.</source> <volume>10</volume>, <fpage>920837</fpage>. <pub-id pub-id-type="doi">10.3389/fenrg.2022.920837</pub-id> </citation>
</ref>
<ref id="B20">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Li</surname>
<given-names>H.</given-names>
</name>
</person-group> (<year>2022b</year>). <article-title>Short-term Wind Power Prediction via Spatial Temporal Analysis and Deep Residual Networks</article-title>. <source>Front. Energy Res.</source> <volume>10</volume>, <fpage>920407</fpage>. <pub-id pub-id-type="doi">10.3389/fenrg.2022.920407</pub-id> </citation>
</ref>
<ref id="B21">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Li</surname>
<given-names>H.</given-names>
</name>
<name>
<surname>Xu</surname>
<given-names>Q.</given-names>
</name>
<name>
<surname>He</surname>
<given-names>Y.</given-names>
</name>
<name>
<surname>Deng</surname>
<given-names>J.</given-names>
</name>
</person-group> (<year>2018</year>). <article-title>Prediction of Landslide Displacement with an Ensemble-Based Extreme Learning Machine and Copula Models</article-title>. <source>Landslides</source> <volume>15</volume> (<issue>10</issue>), <fpage>2047</fpage>&#x2013;<lpage>2059</lpage>. <pub-id pub-id-type="doi">10.1007/s10346-018-1020-2</pub-id> </citation>
</ref>
<ref id="B22">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Li</surname>
<given-names>H.</given-names>
</name>
<name>
<surname>Xu</surname>
<given-names>Q.</given-names>
</name>
<name>
<surname>He</surname>
<given-names>Y.</given-names>
</name>
<name>
<surname>Fan</surname>
<given-names>X.</given-names>
</name>
<name>
<surname>Li</surname>
<given-names>S.</given-names>
</name>
</person-group> (<year>2020</year>). <article-title>Modeling and Predicting Reservoir Landslide Displacement with Deep Belief Network and EWMA Control Charts: a Case Study in Three Gorges Reservoir</article-title>. <source>Landslides</source> <volume>17</volume> (<issue>3</issue>), <fpage>693</fpage>&#x2013;<lpage>707</lpage>. <pub-id pub-id-type="doi">10.1007/s10346-019-01312-6</pub-id> </citation>
</ref>
<ref id="B23">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Lian</surname>
<given-names>C.</given-names>
</name>
<name>
<surname>Zeng</surname>
<given-names>Z.</given-names>
</name>
<name>
<surname>Yao</surname>
<given-names>W.</given-names>
</name>
<name>
<surname>Tang</surname>
<given-names>H.</given-names>
</name>
</person-group> (<year>2015</year>). <article-title>Multiple Neural Networks Switched Prediction for Landslide Displacement</article-title>. <source>Eng. Geol.</source> <volume>186</volume>, <fpage>91</fpage>&#x2013;<lpage>99</lpage>. <pub-id pub-id-type="doi">10.1016/j.enggeo.2014.11.014</pub-id> </citation>
</ref>
<ref id="B24">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Liu</surname>
<given-names>Z.</given-names>
</name>
<name>
<surname>Xu</surname>
<given-names>W. Y.</given-names>
</name>
<name>
<surname>Shao</surname>
<given-names>J. F.</given-names>
</name>
</person-group> (<year>2012</year>). <article-title>Gauss Process Based Approach for Application on Landslide Displacement Analysis and Prediction</article-title>. <source>Comput. Model. Eng. Sci.</source> <volume>84</volume> (<issue>2</issue>), <fpage>99</fpage>&#x2013;<lpage>122</lpage>. <pub-id pub-id-type="doi">10.3970/cmes.2012.084.099</pub-id> </citation>
</ref>
<ref id="B25">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Lu</surname>
<given-names>P.</given-names>
</name>
<name>
<surname>Rosenbaum</surname>
<given-names>M. S.</given-names>
</name>
</person-group> (<year>2003</year>). <article-title>Artificial Neural Networks and Grey Systems for the Prediction of Slope Stability</article-title>. <source>Nat. Hazards</source> <volume>30</volume> (<issue>3</issue>), <fpage>383</fpage>&#x2013;<lpage>398</lpage>. <pub-id pub-id-type="doi">10.1023/b:nhaz.0000007168.00673.27</pub-id> </citation>
</ref>
<ref id="B26">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Ma</surname>
<given-names>J.</given-names>
</name>
<name>
<surname>Tang</surname>
<given-names>H.</given-names>
</name>
<name>
<surname>Liu</surname>
<given-names>X.</given-names>
</name>
<name>
<surname>Wen</surname>
<given-names>T.</given-names>
</name>
<name>
<surname>Zhang</surname>
<given-names>J.</given-names>
</name>
<name>
<surname>Tan</surname>
<given-names>Q.</given-names>
</name>
<etal/>
</person-group> (<year>2018</year>). <article-title>Probabilistic Forecasting of Landslide Displacement Accounting for Epistemic Uncertainty: a Case Study in the Three Gorges Reservoir Area, China</article-title>. <source>Landslides</source> <volume>15</volume> (<issue>6</issue>), <fpage>1145</fpage>&#x2013;<lpage>1153</lpage>. <pub-id pub-id-type="doi">10.1007/s10346-017-0941-5</pub-id> </citation>
</ref>
<ref id="B27">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Schulz</surname>
<given-names>E.</given-names>
</name>
<name>
<surname>Speekenbrink</surname>
<given-names>M.</given-names>
</name>
<name>
<surname>Krause</surname>
<given-names>A.</given-names>
</name>
</person-group> (<year>2018</year>). <article-title>A Tutorial on Gaussian Process Regression: Modelling, Exploring, and Exploiting Functions</article-title>. <source>J. Math. Psychol.</source> <volume>85</volume>, <fpage>1</fpage>&#x2013;<lpage>16</lpage>. <pub-id pub-id-type="doi">10.1016/j.jmp.2018.03.001</pub-id> </citation>
</ref>
<ref id="B28">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Tamhidi</surname>
<given-names>A.</given-names>
</name>
<name>
<surname>Kuehn</surname>
<given-names>N.</given-names>
</name>
<name>
<surname>Ghahari</surname>
<given-names>S. F.</given-names>
</name>
<name>
<surname>Rodgers</surname>
<given-names>A. J.</given-names>
</name>
<name>
<surname>Kohler</surname>
<given-names>M. D.</given-names>
</name>
<name>
<surname>Taciroglu</surname>
<given-names>E.</given-names>
</name>
<etal/>
</person-group> (<year>2022</year>). <article-title>Conditioned Simulation of Ground-Motion Time Series at Uninstrumented Sites Using Gaussian Process Regression</article-title>. <source>Bull. Seismol. Soc. Am.</source> <volume>112</volume> (<issue>1</issue>), <fpage>331</fpage>&#x2013;<lpage>347</lpage>. <pub-id pub-id-type="doi">10.1785/0120210054</pub-id> </citation>
</ref>
<ref id="B29">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Tang</surname>
<given-names>P.</given-names>
</name>
<name>
<surname>Chen</surname>
<given-names>G.-Q.</given-names>
</name>
<name>
<surname>Huang</surname>
<given-names>R.-Q.</given-names>
</name>
<name>
<surname>Wang</surname>
<given-names>D.</given-names>
</name>
</person-group> (<year>2021</year>). <article-title>Effect of the Number of Coplanar Rock Bridges on the Shear Strength and Stability of Slopes with the Same Discontinuity Persistence</article-title>. <source>Bull. Eng. Geol. Environ.</source> <volume>80</volume> (<issue>5</issue>), <fpage>3675</fpage>&#x2013;<lpage>3691</lpage>. <pub-id pub-id-type="doi">10.1007/s10064-021-02180-y</pub-id> </citation>
</ref>
<ref id="B30">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Tang</surname>
<given-names>P.</given-names>
</name>
<name>
<surname>Chen</surname>
<given-names>G.-Q.</given-names>
</name>
<name>
<surname>Huang</surname>
<given-names>R.-Q.</given-names>
</name>
<name>
<surname>Zhu</surname>
<given-names>J.</given-names>
</name>
</person-group> (<year>2020</year>). <article-title>Brittle Failure of Rockslides Linked to the Rock Bridge Length Effect</article-title>. <source>Landslides</source> <volume>17</volume> (<issue>4</issue>), <fpage>793</fpage>&#x2013;<lpage>803</lpage>. <pub-id pub-id-type="doi">10.1007/s10346-019-01323-3</pub-id> </citation>
</ref>
<ref id="B31">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Ton</surname>
<given-names>J.-F.</given-names>
</name>
<name>
<surname>Flaxman</surname>
<given-names>S.</given-names>
</name>
<name>
<surname>Sejdinovic</surname>
<given-names>D.</given-names>
</name>
<name>
<surname>Bhatt</surname>
<given-names>S.</given-names>
</name>
</person-group> (<year>2018</year>). <article-title>Spatial Mapping with Gaussian Processes and Nonstationary Fourier Features</article-title>. <source>Spat. Stat.</source> <volume>28</volume>, <fpage>59</fpage>&#x2013;<lpage>78</lpage>. <pub-id pub-id-type="doi">10.1016/j.spasta.2018.02.002</pub-id> </citation>
</ref>
<ref id="B32">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Wen</surname>
<given-names>H.</given-names>
</name>
<name>
<surname>Ma</surname>
<given-names>J.</given-names>
</name>
<name>
<surname>Gu</surname>
<given-names>J.</given-names>
</name>
<name>
<surname>Yuan</surname>
<given-names>L.</given-names>
</name>
<name>
<surname>Jin</surname>
<given-names>Z.</given-names>
</name>
</person-group> (<year>2022</year>). <article-title>Sparse Variational Gaussian Process Based Day-Ahead Probabilistic Wind Power Forecasting</article-title>. <source>IEEE Trans. Sustain. Energy</source> <volume>13</volume> (<issue>2</issue>), <fpage>957</fpage>&#x2013;<lpage>970</lpage>. <pub-id pub-id-type="doi">10.1109/tste.2022.3141549</pub-id> </citation>
</ref>
<ref id="B33">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>West</surname>
<given-names>A.</given-names>
</name>
<name>
<surname>Tsitsimpelis</surname>
<given-names>I.</given-names>
</name>
<name>
<surname>Licata</surname>
<given-names>M.</given-names>
</name>
<name>
<surname>Jazbec</surname>
<given-names>A.</given-names>
</name>
<name>
<surname>Snoj</surname>
<given-names>L.</given-names>
</name>
<name>
<surname>Joyce</surname>
<given-names>M. J.</given-names>
</name>
<etal/>
</person-group> (<year>2021</year>). <article-title>Use of Gaussian Process Regression for Radiation Mapping of a Nuclear Reactor with a Mobile Robot</article-title>. <source>Sci. Rep.</source> <volume>11</volume> (<issue>1</issue>), <fpage>1</fpage>&#x2013;<lpage>11</lpage>. <pub-id pub-id-type="doi">10.1038/s41598-021-93474-4</pub-id> </citation>
</ref>
<ref id="B34">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Xing</surname>
<given-names>Y.</given-names>
</name>
<name>
<surname>Yue</surname>
<given-names>J.</given-names>
</name>
<name>
<surname>Chen</surname>
<given-names>C.</given-names>
</name>
</person-group> (<year>2019</year>). <article-title>Interval Estimation of Landslide Displacement Prediction Based on Time Series Decomposition and Long Short-Term Memory Network</article-title>. <source>IEEE Access</source> <volume>8</volume>, <fpage>3187</fpage>&#x2013;<lpage>3196</lpage>. <pub-id pub-id-type="doi">10.1109/ACCESS.2019.2961295</pub-id> </citation>
</ref>
<ref id="B35">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Xu</surname>
<given-names>Q.</given-names>
</name>
<name>
<surname>Li</surname>
<given-names>H.</given-names>
</name>
<name>
<surname>He</surname>
<given-names>Y.</given-names>
</name>
<name>
<surname>Liu</surname>
<given-names>F.</given-names>
</name>
<name>
<surname>Peng</surname>
<given-names>D.</given-names>
</name>
</person-group> (<year>2019</year>). <article-title>Comparison of Data-Driven Models of Loess Landslide Runout Distance Estimation</article-title>. <source>Bull. Eng. Geol. Environ.</source> <volume>78</volume> (<issue>2</issue>), <fpage>1281</fpage>&#x2013;<lpage>1294</lpage>. <pub-id pub-id-type="doi">10.1007/s10064-017-1176-3</pub-id> </citation>
</ref>
<ref id="B36">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Zhou</surname>
<given-names>J.</given-names>
</name>
<name>
<surname>Wei</surname>
<given-names>J.</given-names>
</name>
<name>
<surname>Yang</surname>
<given-names>T.</given-names>
</name>
<name>
<surname>Zhang</surname>
<given-names>P.</given-names>
</name>
<name>
<surname>Liu</surname>
<given-names>F.</given-names>
</name>
<name>
<surname>Chen</surname>
<given-names>J.</given-names>
</name>
</person-group> (<year>2021</year>). <article-title>Seepage Channel Development in the Crown Pillar: Insights from Induced Microseismicity</article-title>. <source>Int. J. Rock Mech. Min. Sci.</source> <volume>145</volume>, <fpage>104851</fpage>. <pub-id pub-id-type="doi">10.1016/j.ijrmms.2021.104851</pub-id> </citation>
</ref>
<ref id="B37">
<citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname>Zhu</surname>
<given-names>X.</given-names>
</name>
<name>
<surname>Xu</surname>
<given-names>Q.</given-names>
</name>
<name>
<surname>Tang</surname>
<given-names>M.</given-names>
</name>
<name>
<surname>Nie</surname>
<given-names>W.</given-names>
</name>
<name>
<surname>Ma</surname>
<given-names>S.</given-names>
</name>
<name>
<surname>Xu</surname>
<given-names>Z.</given-names>
</name>
</person-group> (<year>2017</year>). <article-title>Comparison of Two Optimized Machine Learning Models for Predicting Displacement of Rainfall-Induced Landslide: A Case Study in Sichuan Province, China</article-title>. <source>Eng. Geol.</source> <volume>218</volume>, <fpage>213</fpage>&#x2013;<lpage>222</lpage>. <pub-id pub-id-type="doi">10.1016/j.enggeo.2017.01.022</pub-id> </citation>
</ref>
</ref-list>
</back>
</article>