Anna E. Brower, Bianca G. Corpuz, Balaji Ramesh, B. Zaitchik, J. Gohlke, S. Swarup
{"title":"飓风劳拉期间疏散率预测:天气预报、推特和新冠肺炎","authors":"Anna E. Brower, Bianca G. Corpuz, Balaji Ramesh, B. Zaitchik, J. Gohlke, S. Swarup","doi":"10.1175/wcas-d-22-0006.1","DOIUrl":null,"url":null,"abstract":"\nMachine learning was applied to predict evacuation rates for all Census tracts affected by Hurricane Laura. The evacuation ground truthwas derived from cellphone-based mobility data. Twitter data, Census data, geographical data, COVID-19 case rates, the CDC/ATSDR social vulnerability index, and relevant weather and physical data were used to do the prediction. Random forests were found to perform well, with a MAPE of 4.9% on testing data. Feature importance for prediction was analyzed using Shapley additive explanations and it was found that previous evacuation, rainfall forecasts, COVID-19 case rates, and Twitter data rank highly in terms of importance. Social vulnerability indices were also found to show a very consistent relationship with evacuation rates, such that higher vulnerability consistently implies lower evacuation rates. These findings can help with hurricane evacuation preparedness and planning as well as real-time assessment.","PeriodicalId":48971,"journal":{"name":"Weather Climate and Society","volume":null,"pages":null},"PeriodicalIF":1.9000,"publicationDate":"2022-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":"{\"title\":\"Predictors of Evacuation Rates During Hurricane Laura: Weather Forecasts, Twitter, and COVID-19\",\"authors\":\"Anna E. Brower, Bianca G. Corpuz, Balaji Ramesh, B. Zaitchik, J. Gohlke, S. Swarup\",\"doi\":\"10.1175/wcas-d-22-0006.1\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"\\nMachine learning was applied to predict evacuation rates for all Census tracts affected by Hurricane Laura. The evacuation ground truthwas derived from cellphone-based mobility data. Twitter data, Census data, geographical data, COVID-19 case rates, the CDC/ATSDR social vulnerability index, and relevant weather and physical data were used to do the prediction. Random forests were found to perform well, with a MAPE of 4.9% on testing data. Feature importance for prediction was analyzed using Shapley additive explanations and it was found that previous evacuation, rainfall forecasts, COVID-19 case rates, and Twitter data rank highly in terms of importance. Social vulnerability indices were also found to show a very consistent relationship with evacuation rates, such that higher vulnerability consistently implies lower evacuation rates. These findings can help with hurricane evacuation preparedness and planning as well as real-time assessment.\",\"PeriodicalId\":48971,\"journal\":{\"name\":\"Weather Climate and Society\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":1.9000,\"publicationDate\":\"2022-12-19\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"1\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Weather Climate and Society\",\"FirstCategoryId\":\"89\",\"ListUrlMain\":\"https://doi.org/10.1175/wcas-d-22-0006.1\",\"RegionNum\":4,\"RegionCategory\":\"地球科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"ENVIRONMENTAL STUDIES\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Weather Climate and Society","FirstCategoryId":"89","ListUrlMain":"https://doi.org/10.1175/wcas-d-22-0006.1","RegionNum":4,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"ENVIRONMENTAL STUDIES","Score":null,"Total":0}
Predictors of Evacuation Rates During Hurricane Laura: Weather Forecasts, Twitter, and COVID-19
Machine learning was applied to predict evacuation rates for all Census tracts affected by Hurricane Laura. The evacuation ground truthwas derived from cellphone-based mobility data. Twitter data, Census data, geographical data, COVID-19 case rates, the CDC/ATSDR social vulnerability index, and relevant weather and physical data were used to do the prediction. Random forests were found to perform well, with a MAPE of 4.9% on testing data. Feature importance for prediction was analyzed using Shapley additive explanations and it was found that previous evacuation, rainfall forecasts, COVID-19 case rates, and Twitter data rank highly in terms of importance. Social vulnerability indices were also found to show a very consistent relationship with evacuation rates, such that higher vulnerability consistently implies lower evacuation rates. These findings can help with hurricane evacuation preparedness and planning as well as real-time assessment.
期刊介绍:
Weather, Climate, and Society (WCAS) publishes research that encompasses economics, policy analysis, political science, history, and institutional, social, and behavioral scholarship relating to weather and climate, including climate change. Contributions must include original social science research, evidence-based analysis, and relevance to the interactions of weather and climate with society.