Lishan Ji, Bing Han, Qiang Jing, Yunjiang Rao, Huijuan Wu
{"title":"Noise suppression of DAS seismic data with cross-shape multi-head self-attention mechanism","authors":"Lishan Ji, Bing Han, Qiang Jing, Yunjiang Rao, Huijuan Wu","doi":"10.1364/ofs.2022.w4.47","DOIUrl":null,"url":null,"abstract":"Self-attention mechanism can help neural networks pay more attention to noise. By using cross-shaped multi-head self-attention mechanism, we construct a neural network to improve the quality of distributed acoustic sensing signals in oil/gas exploration effectively.","PeriodicalId":265406,"journal":{"name":"27th International Conference on Optical Fiber Sensors","volume":"44 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"27th International Conference on Optical Fiber Sensors","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1364/ofs.2022.w4.47","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
Self-attention mechanism can help neural networks pay more attention to noise. By using cross-shaped multi-head self-attention mechanism, we construct a neural network to improve the quality of distributed acoustic sensing signals in oil/gas exploration effectively.