Data for Filtration Properties Estimation of Host Rocks

To train the machine learning model, a dataset was generated containing data for «Budennovskoye» field, part of which is shown in title figure. (AR and SP are given for 90 centimeter intervals, for which, in turn, the actual values K_fpo. obtained by pumping out (pump out) was determined. As a result, the input variable set consisted of 19 values, including the rock code (AR, SP). The target column isK_f_pump_out .The regression model is based on an ANN with one hidden layer consisting of 31 neurons. K_f_regression values were also calculated for all intervals of the specified dataset using the currently used procedure, K_f_calculation.K_f_regression K_f_calculation values are not to be included to the input values list.The delails of the metod see in "Ravil I. Mukhamediev,, Yan Kuchin etc. Estimation of Filtration Properties of Host Rocks in Sandstone-type Uranium Deposits Us-ing Machine Learning Methods."

为训练该机器学习模型，我们构建了一份包含布登诺夫斯科耶（Budennovskoye）油田相关数据的数据集，部分数据如题图所示。针对90厘米级井段，我们提供了视电阻率（AR）与自然电位（SP，Self-Potential）数据；针对上述井段，同时测定了通过抽提实验得到的实际渗透率值K_f_pump_out（K_fpo）。最终，输入变量集共包含19个特征，其中包括岩石编码（AR、SP）。模型的目标列设为K_f_pump_out。本次回归模型基于单隐藏层人工神经网络（ANN，Artificial Neural Network）搭建，隐藏层包含31个神经元。研究人员还采用现行计算流程K_f_calculation，为该数据集的全部井段计算得到了K_f_regression值；K_f_regression与K_f_calculation值均不应纳入输入变量集。该方法的详细细节可参见文献：Ravil I. Mukhamediev、Yan Kuchin 等. 基于机器学习方法估算砂岩型铀矿床围岩渗流特性（Estimation of Filtration Properties of Host Rocks in Sandstone-type Uranium Deposits Using Machine Learning Methods）。