{"title":"虚拟流量计量任务中流量预测精度置信度的评估方法","authors":"E.V. Kupryashin, I.V. Vrabie, D. Syresin","doi":"10.3997/2214-4609.202156032","DOIUrl":null,"url":null,"abstract":"Summary The paper is devoted to computation of the prediction interval and evaluation of regression accuracy, applied for flowrate computation with virtual flowmeters. Our approach is based on ensembles of neural networks known as Mixture Density Networks and minimizing of the negative-log likelihood function. We investigated the advantages of the applied method to calculate the oil rates and prediction interval using synthetic dataset consisting of 180 wells. The approach has demonstrated to be robust and sensitive the presence of signals variability and noise impact, and to the error caused by the model's uncertainty caused by statistical difference between training and testing datasets.","PeriodicalId":266953,"journal":{"name":"Data Science in Oil and Gas 2021","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2021-08-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"The Approach to Evaluate The Confidence of Flow Rate Prediction Accuracy in The Tasks of Virtual Flow Metering\",\"authors\":\"E.V. Kupryashin, I.V. Vrabie, D. Syresin\",\"doi\":\"10.3997/2214-4609.202156032\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Summary The paper is devoted to computation of the prediction interval and evaluation of regression accuracy, applied for flowrate computation with virtual flowmeters. Our approach is based on ensembles of neural networks known as Mixture Density Networks and minimizing of the negative-log likelihood function. We investigated the advantages of the applied method to calculate the oil rates and prediction interval using synthetic dataset consisting of 180 wells. The approach has demonstrated to be robust and sensitive the presence of signals variability and noise impact, and to the error caused by the model's uncertainty caused by statistical difference between training and testing datasets.\",\"PeriodicalId\":266953,\"journal\":{\"name\":\"Data Science in Oil and Gas 2021\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2021-08-04\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Data Science in Oil and Gas 2021\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.3997/2214-4609.202156032\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Data Science in Oil and Gas 2021","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.3997/2214-4609.202156032","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
The Approach to Evaluate The Confidence of Flow Rate Prediction Accuracy in The Tasks of Virtual Flow Metering
Summary The paper is devoted to computation of the prediction interval and evaluation of regression accuracy, applied for flowrate computation with virtual flowmeters. Our approach is based on ensembles of neural networks known as Mixture Density Networks and minimizing of the negative-log likelihood function. We investigated the advantages of the applied method to calculate the oil rates and prediction interval using synthetic dataset consisting of 180 wells. The approach has demonstrated to be robust and sensitive the presence of signals variability and noise impact, and to the error caused by the model's uncertainty caused by statistical difference between training and testing datasets.