摘要
一位新闻记者兼机器人与机器学习的新闻编辑每日新闻-在一份新的报告中讨论了人工智能的研究结果。根据NewsRx记者在英国Sylhet的新闻报道，研究表明：“渗透率是确定流体如何通过岩石的最重要的岩石物理特征。本研究旨在开发和评估预测渗透率的智能计算机模型。”我们的新闻记者从沙贾拉尔科技大学的研究中获得了一句话：“这项研究的重点是三种新的模型-决策树、套袋树和额外树-同时也研究了以前应用的技术，如随机森林、支持向量回归器(SVR)、主要数据集由Jeanne D’Arc盆地非均质油藏197个数据点组成，包括实验室演讲导出的渗透率(K)、含油饱和度(SO)、含水饱和度(SW)、地层密度(RGR)、孔隙度(PH)和深度。如行列式系数(2)、均方误差(MSE)、均方误差(MAE)、均方根误差(RMSE)、均方误差(MAPE)、最大误差(maxE)和最小误差(minE)等,根据岩心特征在渗透率建模中的重要性对岩心特征进行排序,提出了一种有效的渗透率预测方法。研究结果表明，MVR不适合于概率预测，所有已开发的模型都优于MVR，Extra Trees是最准确的模型，Extra Trees为0.976，Random Forest和Bagging Tree的Extra Trees为0.961，Bagging Tree略低，Extra Trees为0.964.套袋树、随机森林、SVR、决策树和MVR。LSO研究详细分析了输入参数的影响，强调孔隙度(pH)和含水饱和度(SW)是最有影响的，而颗粒密度(RGR)、含油饱和度(SO)和深度被认为不太重要。
Abstract
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – Research findings on artificial intell igence are discussed in a new report. According to news reporting from Sylhet, B angladesh, by NewsRx journalists, research stated, “Permeability is the most imp ortant petrophysical characteristic for determining how fluids pass through rese rvoir rocks. This study aims to develop and assess intelligent computer-based mo dels for predicting permeability.” Our news correspondents obtained a quote from the research from Shahjalal Univer sity of Science and Technology: “The research focuses on three novel models-Deci sion Tree, Bagging Tree, and Extra Trees-while also investigating previously app lied techniques such as random forest, support vector regressor (SVR), and multi ple variable regression (MVR). The primary dataset consists of 197 data points f rom a heterogeneous petroleum reservoir in the Jeanne d’Arc Basin, including lab oratory-derived permeability (K), oil saturation (SO), water saturation (SW), gr ain density (rgr), porosity (ph), and depth. The most effective machine learning models are identified by a thorough analysis that makes use of a variety of sta tistical metrics, such as the coefficient of the determinant (R2), mean squared error (MSE), mean absolute error (MAE), root mean square error (RMSE), mean abso lute percentage error (MAPE), maximum error (maxE), and minimum error (minE). Ad ditionally, core features are ranked based on their importance in permeability m odeling. This study deviates from conventional approaches by proposing an effici ent means of forecasting permeability, reducing reliance on labor-intensive and time-consuming laboratory work. The findings reveal that MVR is unsuitable for p ermeability prediction, with all developed models outperforming it. Extra Trees emerges as the most accurate model, with an R2 of 0.976, while random forest and bagging tree exhibit slightly lower R2 values of 0.961 and 0.964, respectively. The ranking of these algorithms based on performance criteria is as follows: ex tra trees, bagging tree, random forest, SVR, decision tree, and MVR. The study a lso presents a detailed analysis of the impact of input parameters, highlighting porosity (ph) and water saturation (SW) as the most influential, while grain de nsity (rgr), oil saturation (SO), and depth are considered less important.”
NETL
NSTL