石油地球物理勘探2026，Vol.61Issue(2)：283-293,11.DOI:10.13810/j.cnki.issn.1000-7210.20250354
基于多尺度随机森林融合地质、测井和地震资料的煤层含气量预测
The prediction of coalbed methane content based on multi-scale random forest integrating geological,logging,and seismic data
摘要
Abstract
Accurate estimation of coalbed methane(CBM)content plays a crucial role in assessing and effi-ciently exploiting CBM resources.Deep CBM is influenced by multiple controlling factors and complex genetic mechanisms.Currently,machine-learning approaches for CBM content prediction typically rely on either seis-mic or logging data.As a result,the complex geological conditions of deep coal seam are not fully accounted for.This study proposes an intelligent prediction method for CBM content,which achieves multi-source data fusion through a multi-scale modeling and deep integration strategy.The approach first extracts multi-scale sensitive at-tributes or features relevant to CBM content from geological,logging,and seismic sources.For each dataset of the same scale,adaptive modeling is performed using a Bayesian hyperparameter-optimized random forest(RF)algorithm,which enhances model robustness and prevents overfitting.The prediction results from individual scales are subsequently integrated through the least squares method to construct a multi-scale RF composite model.The proposed method is validated using a field dataset and compare its performance with that of conven-tional approaches,including single-scale RF and linear regression.The results show that,compared with these baseline methods,the proposed method reduces the mean relative error of CBM content prediction on test wells by 3.01%and 4.94%,respectively.This demonstrates that the proposed approach achieves higher accu-racy and stronger generalization capability,enabling precise characterization of the spatial distribution of CBM content.关键词
煤层气/随机森林/多尺度数据/鄂尔多斯盆地Key words
coalbed methane/random forest/multi-scale data/Ordos Basin分类
天文与地球科学引用本文复制引用
刘浪,袁三一,于越,李明轩..基于多尺度随机森林融合地质、测井和地震资料的煤层含气量预测[J].石油地球物理勘探,2026,61(2):283-293,11.基金项目
本项研究受国家自然科学基金项目"模型和数据联合驱动的叠前时间偏移速度建模流程智能化研究"(42174152)、"五维叠前地震信息驱动的深度学习致密砂岩储层表征机制及含气性预测"(41974140)和中国海油石油有限公司"黄甫庙沟门区非常规天然气甜点地震预测"(CCL2024RCPS0022ESN)联合资助. （42174152）
