首页|Research from Petroleum University of Technology Broadens Understanding of Machi ne Learning (Predicting scale deposition in oil reservoirs using machine learnin g optimization algorithms)
Research from Petroleum University of Technology Broadens Understanding of Machi ne Learning (Predicting scale deposition in oil reservoirs using machine learnin g optimization algorithms)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News – Fresh data on artificial intelligence are present ed in a new report. According to news originating from Ahvaz, Iran, by NewsRx co rrespondents, research stated, “Scale deposition, a form of formation damage, no t only affects the reservoir but also damages the well and equipment. This pheno menon occurs due to changes in temperature, pressure, and the injection of incom patible salt water, leading to ionic reactions.” Our news journalists obtained a quote from the research from Petroleum Universit y of Technology: “This study investigated permeability reduction due to scale de position and examined how parameters such as temperature, pressure drop, and ion concentration affect the prediction accuracy. The scale deposits investigated i n this study include CaSO4, BaSO4, and SrSO4. This paper uses Python to employ d ifferent machine-learning algorithms to predict the results. Each machine learni ng model has certain hyper-parameters that need adjustment. Failure to do so wil l result in reduced accuracy and incomplete interpretation of input data. The ac curacy of the support vector regression (SVR) algorithm was significantly affect ed by the variation of the epsilon parameter in the dataset used. Therefore, bef ore hyperparameter optimization, SVR had the lowest accuracy at 0.575. After adj usting the hyperparameters, our findings show that SVR had the highest increase in R-squared value, which was 0.900, and the most minor growth in KNN, which we nt from 0.995 to 0.996.”
Petroleum University of TechnologyAhva zIranAsiaAlgorithmsCyborgsEmerging TechnologiesMachine LearningOpt imization Algorithms
NETL
NSTL
