Qingkai Kong, Andrea Chiang, Ana C. Aguiar, M. Giselle Fernández-Godino, Stephen C. Myers, Donald D. Lucas
{"title":"深度卷积自编码器在地震学应用中的通用特征提取","authors":"Qingkai Kong, Andrea Chiang, Ana C. Aguiar, M. Giselle Fernández-Godino, Stephen C. Myers, Donald D. Lucas","doi":"10.1016/j.aiig.2021.12.002","DOIUrl":null,"url":null,"abstract":"<div><p>The idea of using a deep autoencoder to encode seismic waveform features and then use them in different seismological applications is appealing. In this paper, we designed tests to evaluate this idea of using autoencoders as feature extractors for different seismological applications, such as event discrimination (i.e., earthquake vs. noise waveforms, earthquake vs. explosion waveforms), and phase picking. These tests involve training an autoencoder, either undercomplete or overcomplete, on a large amount of earthquake waveforms, and then using the trained encoder as a feature extractor with subsequent application layers (either a fully connected layer, or a convolutional layer plus a fully connected layer) to make the decision. By comparing the performance of these newly designed models against the baseline models trained from scratch, we conclude that the autoencoder feature extractor approach may only outperform the baseline under certain conditions, such as when the target problems require features that are similar to the autoencoder encoded features, when a relatively small amount of training data is available, and when certain model structures and training strategies are utilized. The model structure that works best in all these tests is an overcomplete autoencoder with a convolutional layer and a fully connected layer to make the estimation.</p></div>","PeriodicalId":100124,"journal":{"name":"Artificial Intelligence in Geosciences","volume":"2 ","pages":"Pages 96-106"},"PeriodicalIF":0.0000,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2666544121000319/pdfft?md5=3ddd75c252100a7aacae62b9a5d25c95&pid=1-s2.0-S2666544121000319-main.pdf","citationCount":"8","resultStr":"{\"title\":\"Deep convolutional autoencoders as generic feature extractors in seismological applications\",\"authors\":\"Qingkai Kong, Andrea Chiang, Ana C. Aguiar, M. Giselle Fernández-Godino, Stephen C. Myers, Donald D. Lucas\",\"doi\":\"10.1016/j.aiig.2021.12.002\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><p>The idea of using a deep autoencoder to encode seismic waveform features and then use them in different seismological applications is appealing. In this paper, we designed tests to evaluate this idea of using autoencoders as feature extractors for different seismological applications, such as event discrimination (i.e., earthquake vs. noise waveforms, earthquake vs. explosion waveforms), and phase picking. These tests involve training an autoencoder, either undercomplete or overcomplete, on a large amount of earthquake waveforms, and then using the trained encoder as a feature extractor with subsequent application layers (either a fully connected layer, or a convolutional layer plus a fully connected layer) to make the decision. By comparing the performance of these newly designed models against the baseline models trained from scratch, we conclude that the autoencoder feature extractor approach may only outperform the baseline under certain conditions, such as when the target problems require features that are similar to the autoencoder encoded features, when a relatively small amount of training data is available, and when certain model structures and training strategies are utilized. The model structure that works best in all these tests is an overcomplete autoencoder with a convolutional layer and a fully connected layer to make the estimation.</p></div>\",\"PeriodicalId\":100124,\"journal\":{\"name\":\"Artificial Intelligence in Geosciences\",\"volume\":\"2 \",\"pages\":\"Pages 96-106\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2021-12-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.sciencedirect.com/science/article/pii/S2666544121000319/pdfft?md5=3ddd75c252100a7aacae62b9a5d25c95&pid=1-s2.0-S2666544121000319-main.pdf\",\"citationCount\":\"8\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Artificial Intelligence in Geosciences\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S2666544121000319\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Artificial Intelligence in Geosciences","FirstCategoryId":"1085","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2666544121000319","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Deep convolutional autoencoders as generic feature extractors in seismological applications
The idea of using a deep autoencoder to encode seismic waveform features and then use them in different seismological applications is appealing. In this paper, we designed tests to evaluate this idea of using autoencoders as feature extractors for different seismological applications, such as event discrimination (i.e., earthquake vs. noise waveforms, earthquake vs. explosion waveforms), and phase picking. These tests involve training an autoencoder, either undercomplete or overcomplete, on a large amount of earthquake waveforms, and then using the trained encoder as a feature extractor with subsequent application layers (either a fully connected layer, or a convolutional layer plus a fully connected layer) to make the decision. By comparing the performance of these newly designed models against the baseline models trained from scratch, we conclude that the autoencoder feature extractor approach may only outperform the baseline under certain conditions, such as when the target problems require features that are similar to the autoencoder encoded features, when a relatively small amount of training data is available, and when certain model structures and training strategies are utilized. The model structure that works best in all these tests is an overcomplete autoencoder with a convolutional layer and a fully connected layer to make the estimation.