AUTHOR=Li Guan , Han Changcheng , Zhang Zizhao , Hu Chenlin , Jin Yujie , Yang Yi , Qi Ming , He Xudong 

TITLE=Multifractal analysis of the heterogeneity of nanopores in tight reservoirs based on boosting machine learning algorithms

JOURNAL=Frontiers in Earth Science

VOLUME=Volume 11 - 2023

YEAR=2023

URL=https://www.frontiersin.org/journals/earth-science/articles/10.3389/feart.2023.1200913

DOI=10.3389/feart.2023.1200913

ISSN=2296-6463

ABSTRACT=Exploring the geological factors that affect fluid flow has always been a hot topic. For tight reservoirs, the pore structure and characteristics of different lithofacies reveal the storage status of fluids in different reservoir environments. The size, connectivity and distribution of fillers in different sedimentary environments have always been difficult to study microscopic heterogeneity. In this paper, six logging curves (gamma-ray (GR), density (DEN), acoustic (AC), compensated neutron (CN), shallow resistivity (RI) and deep resistivity (RT)) in two marker Wells J1 and J2 of Permian Lucogou Formation in Jimsar Basin are tested by four reinforcement learning algorithms: LogitBoost, GBM, XGBoost and KNN. The total percent correct (TPC) of training well J2 is 96%, 96%, 96% and 96%, and the TPC of validation well J1 is 75%, 68%, 72% and 75%, respectively. Based on the lithofacies classification obtained by reinforcement learning algorithm, the micropores, mesopores and macropores are comprehensively described by high-pressure mercury injection (HPMI) and low-pressure nitrogen gas adsorption (LPN2GA) test. The multifractal theory servers for the quantitative characterization of the pore distribution heterogeneity regarding different lithofacies samples. As found, the higher probability measure areas (HPMA) of the generalized fractal spectrum affects the heterogeneity of the local interval of mesopores and macropores of estuary dam. In the micropore and mesopore, the heterogeneity of evaporation lake showed large variation due to the influence of HPMA, and in the mesopore and macropore, the heterogeneity of evaporation lake was controlled by lower probability measure areas (LPMA). According to the correlation analysis, the single-fractal dimension is well related to the multifractal parameters, and the individual fitting degree is up to 99%, which can serve for characterizing the pore size distribution (PSD) uniformity. The combination of Boosting machine learning and Multifractal can help to better characterize the micro-heterogeneity under different sedimentary environments and different pore size distribution ranges, which is helpful to the exploration and development of oil fields.