K. Danilovskiy, A. Petrov, A. Leonenko, K. Sukhorukova
{"title":"基于卷积神经网络算法求解电阻率测井任务的能力","authors":"K. Danilovskiy, A. Petrov, A. Leonenko, K. Sukhorukova","doi":"10.3997/2214-4609.202156039","DOIUrl":null,"url":null,"abstract":"Summary Russian unfocused lateral logs (BKZ) are infamously known for their complexity. However, the BKZ was widely used in the Soviet Union, therefore, a large amount of data was measured at various oilfields. Reinterpretation of these logs using modern processing techniques is an urgent task. In this study, we propose a new approach to Russian resistivity logs modeling and processing, based on fully convolutional networks (FCN). FCN architecture allows taking into account signal-forming media domain for every measurement point. Training datasets are created individually for the task from real and numerically simulated data. The results of the proposed approach applying are demonstrated on the algorithm for transforming BKZ signals into focused lateral log. Application of the algorithm to real data makes it possible to check data conditionality, perform accurate depth matching, and also facilitates cross-well correlation with an incomplete set of logs.","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\":\"Capabilities of Convolutional Neural Networks Based Algorithms for Solving Resistivity Logging Tasks\",\"authors\":\"K. Danilovskiy, A. Petrov, A. Leonenko, K. Sukhorukova\",\"doi\":\"10.3997/2214-4609.202156039\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Summary Russian unfocused lateral logs (BKZ) are infamously known for their complexity. However, the BKZ was widely used in the Soviet Union, therefore, a large amount of data was measured at various oilfields. Reinterpretation of these logs using modern processing techniques is an urgent task. In this study, we propose a new approach to Russian resistivity logs modeling and processing, based on fully convolutional networks (FCN). FCN architecture allows taking into account signal-forming media domain for every measurement point. Training datasets are created individually for the task from real and numerically simulated data. The results of the proposed approach applying are demonstrated on the algorithm for transforming BKZ signals into focused lateral log. Application of the algorithm to real data makes it possible to check data conditionality, perform accurate depth matching, and also facilitates cross-well correlation with an incomplete set of logs.\",\"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/10.3997/2214-4609.202156039\",\"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/10.3997/2214-4609.202156039","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Capabilities of Convolutional Neural Networks Based Algorithms for Solving Resistivity Logging Tasks
Summary Russian unfocused lateral logs (BKZ) are infamously known for their complexity. However, the BKZ was widely used in the Soviet Union, therefore, a large amount of data was measured at various oilfields. Reinterpretation of these logs using modern processing techniques is an urgent task. In this study, we propose a new approach to Russian resistivity logs modeling and processing, based on fully convolutional networks (FCN). FCN architecture allows taking into account signal-forming media domain for every measurement point. Training datasets are created individually for the task from real and numerically simulated data. The results of the proposed approach applying are demonstrated on the algorithm for transforming BKZ signals into focused lateral log. Application of the algorithm to real data makes it possible to check data conditionality, perform accurate depth matching, and also facilitates cross-well correlation with an incomplete set of logs.