古地理学报2025，Vol.27Issue(4)：937-949,13.DOI:10.7605/gdlxb.2025.083
基于BSMOTE-SVM的细粒沉积岩岩相智能预测:以松辽盆地青山口组一段为例
Intelligent prediction of fine-grained sedimentary lithofacies based on BSMOTE-SVM:a case study of the Member 1 of Qingshankou Formation in Songliao Basin
摘要
Abstract
The spatial distribution of lithofacies of fine-grained sedimentary rocks is a critical re-search focus in shale oil exploration.Due to the high cost and scarcity of core wells,which constrain direct lithofacies analysis,logging-based prediction has become increasingly essential.Taking the First Member of the Qingshankou Formation in the Songliao Basin as a case study,this research establishes a lithofacies classification scheme integrating lithology,mineral composition,total organic carbon(TOC),and sedi-mentary structures,resulting in the identification of seven distinct lithofacies types.A lithofacies-well log dataset was constructed for Well X8 using six conventional logging curves.Three machine learning algo-rithms—Random Forest(RF),eXtreme Gradient Boosting(XGBoost),and Support Vector Machine(SVM)—were employed to evaluate classification performance,with SVM identified as the optimal mo-del.To address class imbalance in the training data,the BSMOTE(Borderline Synthetic Minority Over-sampling Technique)algorithm was applied.The balanced dataset was then used to develop a hybrid litho-facies prediction model:BSMOTE-SVM.The BSMOTE-SVM model demonstrated the best predictive per-formance,achieving an accuracy of 86.49％,precision of 86.60％,recall of 86.49％,and F1-score of 86.31％.This integrated model enables rapid and accurate lithofacies prediction across multiple wells and delineates the lithofacies distribution in Member 1 of the Qingshankou Formation in the Changling sag,of-fering a robust foundation for selecting favorable shale oil enrichment zones in future exploration.关键词
细粒沉积岩/岩相/测井预测/BSMOTE-SVM/青山口组/松辽盆地Key words
fine-grained sedimentary rocks/lithofacies/logging prediction/BSMOTE-SVM/Qingshankou Formation/Songliao Basin分类
天文与地球科学引用本文复制引用
唐佰强,孟庆涛,杨亮,胡菲,谭悦,邢济麟,刘招君,张恩威,董秦玮..基于BSMOTE-SVM的细粒沉积岩岩相智能预测:以松辽盆地青山口组一段为例[J].古地理学报,2025,27(4):937-949,13.基金项目
吉林省自然科学基金项目(编号:20230101081JC)和中国石油吉林油田分公司项目(编号:JS2022-W-13-JZ-78-92)联合资助.[Co-funded by the Project of Natural Science Foundation Jilin Province(No.20230101081JC)and the Project of CNPC Jilin Oilfield Branch Company(No.JS2022-W-13-JZ-78-92)] （编号:20230101081JC）
