成都理工大学学报（自然科学版）2025，Vol.52Issue(5)：966-985,20.DOI:10.12474/cdlgzrkx.2025010503
基于NRBO-CNN-LSTM模型的陆相浅水湖盆总有机碳测井预测优选及应用
Logging prediction optimization and the application of total organic carbon in continental shallow lake basins based on the Newton-Raphson optimization convolutional neural network combined with the long short-term memory neural network
摘要
Abstract
Total organic carbon content(TOC)is the main parameter for evaluating the hydrocarbon generation potential of source rocks.Commonly used TOC logging models are greatly affected by differing geological conditions in practical applications,and their stability is not high,which restricts their ability to produce comprehensive evaluation results.In this paper,the second member of the Lianggaoshan Formation in northern Sichuan Basin is selected as the research object.Based on TOC coring data and conventional logging data,the random forest algorithm is used to evaluate the importance of selected logging curves;eliminate the influence of measurement error and redundant data between logging curves;and select four types of logging curves as model input parameters.The resulting convolutional neural network(CNN),which has high accuracy and strong stability,is combined with the long short-term memory(LSTM)and Newton-Raphson optimization(NRBO)algorithms to optimize the resulting neural network,termed NRBO-CNN-LSTM,and determine the optimal hyperparameters relevant for TOC prediction.The model predictions show that the determination coefficient of NRBO-CNN-LSTM is as high as 0.976 3,the mean square error and mean absolute error of the prediction results are 0.107 0 and 0.240 3,respectively,and the overall error is 0.0521.In sedimentary environments where sand and mud are frequently interbedded,and the logging curves fluctuate greatly with lithology changes,NRBO-CNN-LSTM makes up for the shortcomings of conventional neural network prediction algorithms and effectively improves the accuracy of TOC prediction.关键词
有机碳含量预测/机器学习/陆相页岩/四川盆地/凉高山组Key words
total organic carbon(TOC)/machine learning/terrestrial shale/Sichuan Basin/Lianggaoshan Formation分类
能源科技引用本文复制引用
陈瑞杰,路俊刚,李勇,肖正录,朱星丞,张洋洋,周翔,蒋奇君,石雯心..基于NRBO-CNN-LSTM模型的陆相浅水湖盆总有机碳测井预测优选及应用[J].成都理工大学学报（自然科学版）,2025,52(5):966-985,20.基金项目
四川省自然科学基金(2025ZNSFSC0309) （2025ZNSFSC0309）
中国石油-西南石油大学创新联合体科技合作项目(2020CX030000,2020CX050000). （2020CX030000,2020CX050000）
