| 注册
首页|期刊导航|特种油气藏|基于RIME-XGBoost的泥页岩油产量预测方法

基于RIME-XGBoost的泥页岩油产量预测方法

杨二龙 殷世潭 王宇 王贤君 董驰

特种油气藏2026,Vol.33Issue(3):62-71,10.
✕
特种油气藏2026,Vol.33Issue(3):62-71,10.DOI:10.3969/j.issn.1006-6535.2026.03.007

基于RIME-XGBoost的泥页岩油产量预测方法

A production prediction method for shale oil in mud shale formations based on RIME-XGBoost

杨二龙 1殷世潭 1王宇 2王贤君 2董驰1

作者信息

  • 1. 东北石油大学陆相页岩油气成藏及高效开发教育部重点实验室,黑龙江 大庆 163318
  • 2. 中国石油大庆油田有限责任公司采油工艺研究院,黑龙江 大庆 163453
  • 折叠

摘要

Abstract

Accurate production prediction remains difficult for hydraulically fractured horizontal wells in mud shale oil reservoirs because numerous geological and engineering factors jointly affect well performance.To solve this prob-lem,a big-data preprocessing method for shale oil production prediction was proposed by combining retrieval-aug-mented generation(RAG)technology with the DeepSeek large language model,increasing data collection efficiency by six times.A RIME-XGBoost model suitable for production prediction in mud shale reservoirs was constructed to achieve intelligent prediction of cumulative oil production from hydraulically fractured horizontal wells,and SHAP-based interpretability analysis was used to identify the key factors controlling production.The results show that the main controlling factors of mud shale oil production are vitrinite reflectance(Ro),compensated neutron,proppant in-tensity,sand-fluid ratio,logging-derived effective porosity,maximum horizontal principal stress,and total hydrocar-bon from gas logging.The RIME-XGBoost model yields a coefficient of determination(R2)of 0.936 and a predic-tion accuracy of 91.04%,demonstrating both high accuracy and strong interpretability.This study effectively addres-ses problems such as low efficiency in data preprocessing and poor model interpretability in traditional production prediction,and provides a data-driven solution for accurate productivity prediction and fracturing parameter optimi-zation in mud shale oil development,which is of great significance for the efficient development of mud shale oil.

关键词

泥页岩油/机器学习/产量预测/智能压裂/地质工程一体化

Key words

mud shale oil/machine learning/production prediction/intelligent fracturing/geology-engineering inte-gration

分类

能源科技

引用本文复制引用

杨二龙,殷世潭,王宇,王贤君,董驰..基于RIME-XGBoost的泥页岩油产量预测方法[J].特种油气藏,2026,33(3):62-71,10.

基金项目

国家自然科学基金"高应力差致密油藏微观孔隙结构应力变形下原油动用机制研究"(52274037) (52274037)

特种油气藏

1006-6535

访问量0
|
下载量0
段落导航相关论文