地质通报2025，Vol.44Issue(5)：792-800,9.DOI:10.12097/gbc.2024.03.037
基于测井参数的延川南气田煤层含气量预测模型
Logging prediction model of coal seam gas content in Southern Yanchuan gas field
摘要
Abstract
[Objective]The coal seam gas content is a core parameter for resource assessment and development,but current gas content prediction models generally suffer from issues such as insufficient accuracy and weak generalization ability,which hinder the exploration and development of coalbed methane.[Methods]Based on the logging response characteristics of coal seam gas content in Southern Yanchuan gas field,the MIV(Mean Impact Value)method was utilized to optimize the logging parameters.The BP neural network and random forest algorithm were introduced to establish a high-precision coal seam gas content prediction model.[Results]Compared to the traditional multiple linear regression model,both the BP neural network and random forest models achieved notably higher prediction accuracy,with the random forest model performing even better.[Conclusions]The Random Forest model is more suitable for predicting the coalbed methane content in the study area.Based on the model's prediction,the distribution range of gas content in the gas field is 4.84～21.83 m3/t,with an average of 11.63 m3/t.Spatially,the gas content of coal seam increases gradually from southeast to northwest,and its variation law is generally consistent with the buried depth pattern of coal seam.Vertically,with the increase of buried depth,the gas content of coal seam increases gradually,but the dispersion degree of gas content distribution increases.关键词
含气量/测井参数/MIV/BP神经网络/随机森林Key words
gas content/logging parameters/MIV/BP neural network/random forest分类
天文与地球科学引用本文复制引用
刘晓,陈贞龙,杨松,李松,常闯..基于测井参数的延川南气田煤层含气量预测模型[J].地质通报,2025,44(5):792-800,9.基金项目
国家自然科学基金面上项目《深部煤层气赋存态调整分配及释放产出机制》(批准号:42272195),中国石油化工股份有限公司科技项目《华东探区深部煤层气富集规律与有效开发技术》(编号:P23205)、《深层煤炭地下气化关键技术研究》(编号:P22186) （批准号:42272195）
