基于机器学习的储层渗透率预测方法

Machine learning to predict reservoir permeability

目前在渗透率评价中存在一定困难,主要原因是储层的纵横向非均质性和储层的孔隙结构的巨大差异导致在相同孔隙度条件下,渗透率跨度可能达到一个数量级以上,传统的测井渗透率计算方法难以达到储层精细评价的要求。本文在充分调研渗透率影响因素的前提下,优选了机器学习算法预测渗透率,提高了渗透率的预测精度。

At present,there are some difficulties in permeability evaluation. The main reason is that the permeability span may reach more than one order of magnitude under the same porosity condition due to the heterogeneity of the vertical and horizontal direction of the reservoir and the huge difference in the pore structure of the reservoir. The traditional logging permeability calculation method is difficult to meet the requirements of the fine evaluation of the reservoir. On the premise of fully investigating the influencing factors of permeability,this paper selects the machine learning algorithm to predict permeability and improves the prediction accuracy of permeability.