AUTHOR=Nie Leichao , Qu Keying , Cui Lijuan , Zhai Xiajie , Zhao Xinsheng , Lei Yinru , Li Jing , Wang Jinzhi , Wang Rumiao , Li Wei 

TITLE=Inversion of soil carbon, nitrogen, and phosphorus in the Yellow River Wetland of Shaanxi Province using field in situ hyperspectroscopy

JOURNAL=Frontiers in Soil Science

VOLUME=Volume 4 - 2024

YEAR=2024

URL=https://www.frontiersin.org/journals/soil-science/articles/10.3389/fsoil.2024.1364426

DOI=10.3389/fsoil.2024.1364426

ISSN=2673-8619

ABSTRACT=Soil nitrogen and phosphorus are directly related to soil quality and vegetation growth and are, therefore, a common research topic in studies on target for studying global climate change, material cycling, and information exchange in terrestrial ecosystems. However, collecting soil hyperspectral data under in situ conditions in the field and predicting soil properties, which can effectively save time, manpower, material resources, and financial costs, has have been generally undervalued. Recent optimization techniques have, however, addressed severalmany of the limitations previously restrictingplaguing this technique. Therefore, Iin this study, hyperspectral data were taken from surface soils under different vegetation types in the wetlands in of the Shaanxi Yellow River Wetland Provincial Nature Reserve. Through in situ original spectral data and first-order differential transformation spectral data, three prediction models for soil carbon, nitrogen, and phosphorus contents were established: the partial least squares (PLSR), random forest (RF), and Gaussian process regression (GPR) models. The 𝑅 2 and RMSR of the constructed models were then compared to select the optimal model for evaluatingevaluation of soil content. We found that the The soil organic carbon, total nitrogen, and total phosphorus content models established based on the first-order differential had a higher accuracy when modeling and during model validation, than those of other models, . Moreover,and that the PLSRpartial least squares model based on the original spectrum and the Gaussian process regression model had a superior better inversion performance. These results provide solid theoretical and technical support for developing the optimal model for the quantitative inversion of wetland surface soil carbon, nitrogen, and phosphorus based on in situ hyperspectral technology in the field.