{"title":"深度学习和网络分析:地质灾害报告的分类和可视化","authors":"Wenjia Li, Liang Wu, Xinde Xu, Zhong Xie, Qinjun Qiu, Hao Liu, Zhen Huang, Jianguo Chen","doi":"10.1007/s12583-021-1589-6","DOIUrl":null,"url":null,"abstract":"<p>If progress is to be made toward improving geohazard management and emergency decision-making, then lessons need to be learned from past geohazard information. A geologic hazard report provides a useful and reliable source of information about the occurrence of an event, along with detailed information about the condition or factors of the geohazard. Analyzing such reports, however, can be a challenging process because these texts are often presented in unstructured long text formats, and contain rich specialized and detailed information. Automatically text classification is commonly used to mine disaster text data in open domains (e.g., news and microblogs). But it has limitations to performing contextual long-distance dependencies and is insensitive to discourse order. These deficiencies are most obviously exposed in long text fields. Therefore, this paper uses the bidirectional encoder representations from Transformers (BERT), to model long text. Then, utilizing a softmax layer to automatically extract text features and classify geohazards without manual features. The latent Dirichlet allocation (LDA) model is used to examine the interdependencies that exist between causal variables to visualize geohazards. The proposed method is useful in enabling the machine-assisted interpretation of text-based geohazards. Moreover, it can help users visualize causes, processes, and other geohazards and assist decision-makers in emergency responses.</p>","PeriodicalId":15607,"journal":{"name":"Journal of Earth Science","volume":"9 1","pages":""},"PeriodicalIF":4.1000,"publicationDate":"2024-08-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Deep Learning and Network Analysis: Classifying and Visualizing Geologic Hazard Reports\",\"authors\":\"Wenjia Li, Liang Wu, Xinde Xu, Zhong Xie, Qinjun Qiu, Hao Liu, Zhen Huang, Jianguo Chen\",\"doi\":\"10.1007/s12583-021-1589-6\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p>If progress is to be made toward improving geohazard management and emergency decision-making, then lessons need to be learned from past geohazard information. A geologic hazard report provides a useful and reliable source of information about the occurrence of an event, along with detailed information about the condition or factors of the geohazard. Analyzing such reports, however, can be a challenging process because these texts are often presented in unstructured long text formats, and contain rich specialized and detailed information. Automatically text classification is commonly used to mine disaster text data in open domains (e.g., news and microblogs). But it has limitations to performing contextual long-distance dependencies and is insensitive to discourse order. These deficiencies are most obviously exposed in long text fields. Therefore, this paper uses the bidirectional encoder representations from Transformers (BERT), to model long text. Then, utilizing a softmax layer to automatically extract text features and classify geohazards without manual features. The latent Dirichlet allocation (LDA) model is used to examine the interdependencies that exist between causal variables to visualize geohazards. The proposed method is useful in enabling the machine-assisted interpretation of text-based geohazards. Moreover, it can help users visualize causes, processes, and other geohazards and assist decision-makers in emergency responses.</p>\",\"PeriodicalId\":15607,\"journal\":{\"name\":\"Journal of Earth Science\",\"volume\":\"9 1\",\"pages\":\"\"},\"PeriodicalIF\":4.1000,\"publicationDate\":\"2024-08-14\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of Earth Science\",\"FirstCategoryId\":\"89\",\"ListUrlMain\":\"https://doi.org/10.1007/s12583-021-1589-6\",\"RegionNum\":2,\"RegionCategory\":\"地球科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"GEOSCIENCES, MULTIDISCIPLINARY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Earth Science","FirstCategoryId":"89","ListUrlMain":"https://doi.org/10.1007/s12583-021-1589-6","RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"GEOSCIENCES, MULTIDISCIPLINARY","Score":null,"Total":0}
Deep Learning and Network Analysis: Classifying and Visualizing Geologic Hazard Reports
If progress is to be made toward improving geohazard management and emergency decision-making, then lessons need to be learned from past geohazard information. A geologic hazard report provides a useful and reliable source of information about the occurrence of an event, along with detailed information about the condition or factors of the geohazard. Analyzing such reports, however, can be a challenging process because these texts are often presented in unstructured long text formats, and contain rich specialized and detailed information. Automatically text classification is commonly used to mine disaster text data in open domains (e.g., news and microblogs). But it has limitations to performing contextual long-distance dependencies and is insensitive to discourse order. These deficiencies are most obviously exposed in long text fields. Therefore, this paper uses the bidirectional encoder representations from Transformers (BERT), to model long text. Then, utilizing a softmax layer to automatically extract text features and classify geohazards without manual features. The latent Dirichlet allocation (LDA) model is used to examine the interdependencies that exist between causal variables to visualize geohazards. The proposed method is useful in enabling the machine-assisted interpretation of text-based geohazards. Moreover, it can help users visualize causes, processes, and other geohazards and assist decision-makers in emergency responses.
期刊介绍:
Journal of Earth Science (previously known as Journal of China University of Geosciences), issued bimonthly through China University of Geosciences, covers all branches of geology and related technology in the exploration and utilization of earth resources. Founded in 1990 as the Journal of China University of Geosciences, this publication is expanding its breadth of coverage to an international scope. Coverage includes such topics as geology, petrology, mineralogy, ore deposit geology, tectonics, paleontology, stratigraphy, sedimentology, geochemistry, geophysics and environmental sciences.
Articles published in recent issues include Tectonics in the Northwestern West Philippine Basin; Creep Damage Characteristics of Soft Rock under Disturbance Loads; Simplicial Indicator Kriging; Tephra Discovered in High Resolution Peat Sediment and Its Indication to Climatic Event.
The journal offers discussion of new theories, methods and discoveries; reports on recent achievements in the geosciences; and timely reviews of selected subjects.