基于机器学习的CO2封存致密砂岩储层孔隙度预测
Machine learning-based prediction of porosity in tight sandstone reservoirs for CO2 geological sequestration
路萍 1郭京哲 2高春云 3赵军辉 4张亚芹 5南右泽 6谭富荣 7杨桂林 8钟高润 9李阳阳 10巨浩波 10焦尊生11
作者信息
- 1. 陕西省能源化工研究院,西安 710127;怀柔实验室,北京 101499
- 2. 西北大学,西安 710127
- 3. 陕西榆能集团能源化工研究院有限公司,榆林 719000
- 4. 长庆油田第八采油厂,西安 710018
- 5. 西安阿伯塔资环分析测试技术有限公司,西安 710018
- 6. 上海优也信息科技有限公司,上海 201799
- 7. 陕西省矿产地质调查中心,西安 710069
- 8. 榆林大学,榆林 719053
- 9. 延安大学,延安 716000
- 10. 陕西省能源化工研究院,西安 710127
- 11. 怀俄明大学,拉勒米82071
- 折叠
摘要
CO2地质封存技术被认为是降低大气CO2浓度的有效措施,是我国实现"双碳"目标的关键技术之一.孔隙度是评价储层储集性能的关键参数,对其高精度预测是CO2封存潜力评估的一项重要内容.对于CO2封存致密砂岩储层而言,由于孔隙类型多样,非均质性较强,在以往储层物性评价工作中,利用已有模型和测井解释方法,预测结果与实际测试结果往往偏差很大,实际应用效果不佳.如何利用前沿的数学算法充分挖掘测井数据中隐含的物性信息,建立预测精度较高泛化性能较强的孔隙度模型是致密砂岩储层精细勘探高效开发的关键,更是二氧化碳地质封存潜力评估的关键.本文基于机器学习主成分回归(PCR)、高斯过程回归法(GPR)、随机森林(RF)、支持向量机(SVM)、BP神经网络(BP-ANN)以及极致提升算法(XGBoost)构建致密砂岩储层孔隙度预测模型,经综合对比发现,基于XGBoost的孔隙度预测模型预测精度最高、泛化性能最强,该方法为CO2地质封存致密砂岩储层孔隙度预测模型的构建提供新的思路.
Abstract
CO2 geological storage technology is a crucial measure in reducing atmospheric CO2 concentration and is considered as one of the key technologies for achieving China's"dual carbon"goals.Porosity,as a key parameter for evaluating the reservoir storage performance,plays a vital role in CO2 storage potential evaluation.However,in the case of CO2 storage in tight sandstone reservoirs,due to the diverse pore types and strong heterogeneity,the predicted results using existing models and logging interpretation methods often deviate greatly from the actual test results,resulting in poor actual application effects.Therefore,the establishment of a porosity model with high prediction accuracy and strong generalization performance by using cutting-edge mathematical algorithms to fully explore the porosity information hidden in logging data is crucial for the fine exploration and efficient development of tight sandstone reservoirs,as well as the evaluation of CO2 geological storage potential.This paper presents a porosity prediction model for tight sandstone reservoirs based on machine learning techniques,including Principal Component Regression(PCR),Gaussian Process Regression(GPR),Random Forest(RF),Support Vector Machine(SVM),BP Neural Network(BP-ANN),and Extreme Gradient Boosting Algorithm(XGBoost).Through comprehensive comparison,the XGBoost-based porosity prediction model is found to have the highest prediction accuracy and strongest generalization performance,providing new ideas for the construction of porosity prediction models for tight sandstone reservoirs.
关键词
CO2地质封存/致密砂岩储层/孔隙度模型/机器学习/XGBoostKey words
CO2 geological storage/Tight sandstone reservoir/Porosity model/Machine learning/XGBoost引用本文复制引用
基金项目
陕西省自然科学基础研究计划项目(2022JQ-231)
中国博士后科学基金-面上项目(2023M741321)
北京市博士后科学基金(2023-ZZ-64)
出版年
2024
NETL
NSTL
万方数据