{"title":"预测热带气旋快速增强的深度学习集成方法","authors":"Buo-Fu Chen, Yu-Te Kuo, Treng-Shi Huang","doi":"10.1002/asl.1151","DOIUrl":null,"url":null,"abstract":"<p>Predicting rapid intensification (RI) of tropical cyclones (TCs) is critical in operational forecasting. Statistical schemes rely on human-driven feature extraction and predictor correlation to predict TC intensities. Deep learning provides an opportunity to further improve the prediction if data, including satellite images of TC convection and conventional environmental predictors, can be properly integrated by deep neural networks. This study shows that deep learning yields enhanced intensity and RI prediction performance by simultaneously handling the human-defined environmental/TC-related parameters and information extracted from satellite images. From operational and practical perspectives, we use an ensemble of 20 deep-learning models with different neural network designs and input combinations to predict intensity distributions at +24 h. With the intensity distribution based on the ensemble forecast, forecasters can easily predict a deterministic intensity value demanded in operations and be aware of the chance of RI and the prediction uncertainty. Compared with the operational forecasts provided for western Pacific TCs, the results of the deep learning ensemble achieve higher RI detection probabilities and lower false-alarm rates.</p>","PeriodicalId":50734,"journal":{"name":"Atmospheric Science Letters","volume":null,"pages":null},"PeriodicalIF":2.0000,"publicationDate":"2023-01-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/asl.1151","citationCount":"7","resultStr":"{\"title\":\"A deep learning ensemble approach for predicting tropical cyclone rapid intensification\",\"authors\":\"Buo-Fu Chen, Yu-Te Kuo, Treng-Shi Huang\",\"doi\":\"10.1002/asl.1151\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p>Predicting rapid intensification (RI) of tropical cyclones (TCs) is critical in operational forecasting. Statistical schemes rely on human-driven feature extraction and predictor correlation to predict TC intensities. Deep learning provides an opportunity to further improve the prediction if data, including satellite images of TC convection and conventional environmental predictors, can be properly integrated by deep neural networks. This study shows that deep learning yields enhanced intensity and RI prediction performance by simultaneously handling the human-defined environmental/TC-related parameters and information extracted from satellite images. From operational and practical perspectives, we use an ensemble of 20 deep-learning models with different neural network designs and input combinations to predict intensity distributions at +24 h. With the intensity distribution based on the ensemble forecast, forecasters can easily predict a deterministic intensity value demanded in operations and be aware of the chance of RI and the prediction uncertainty. Compared with the operational forecasts provided for western Pacific TCs, the results of the deep learning ensemble achieve higher RI detection probabilities and lower false-alarm rates.</p>\",\"PeriodicalId\":50734,\"journal\":{\"name\":\"Atmospheric Science Letters\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":2.0000,\"publicationDate\":\"2023-01-11\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://onlinelibrary.wiley.com/doi/epdf/10.1002/asl.1151\",\"citationCount\":\"7\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Atmospheric Science Letters\",\"FirstCategoryId\":\"89\",\"ListUrlMain\":\"https://onlinelibrary.wiley.com/doi/10.1002/asl.1151\",\"RegionNum\":4,\"RegionCategory\":\"地球科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"METEOROLOGY & ATMOSPHERIC SCIENCES\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Atmospheric Science Letters","FirstCategoryId":"89","ListUrlMain":"https://onlinelibrary.wiley.com/doi/10.1002/asl.1151","RegionNum":4,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"METEOROLOGY & ATMOSPHERIC SCIENCES","Score":null,"Total":0}
A deep learning ensemble approach for predicting tropical cyclone rapid intensification
Predicting rapid intensification (RI) of tropical cyclones (TCs) is critical in operational forecasting. Statistical schemes rely on human-driven feature extraction and predictor correlation to predict TC intensities. Deep learning provides an opportunity to further improve the prediction if data, including satellite images of TC convection and conventional environmental predictors, can be properly integrated by deep neural networks. This study shows that deep learning yields enhanced intensity and RI prediction performance by simultaneously handling the human-defined environmental/TC-related parameters and information extracted from satellite images. From operational and practical perspectives, we use an ensemble of 20 deep-learning models with different neural network designs and input combinations to predict intensity distributions at +24 h. With the intensity distribution based on the ensemble forecast, forecasters can easily predict a deterministic intensity value demanded in operations and be aware of the chance of RI and the prediction uncertainty. Compared with the operational forecasts provided for western Pacific TCs, the results of the deep learning ensemble achieve higher RI detection probabilities and lower false-alarm rates.
期刊介绍:
Atmospheric Science Letters (ASL) is a wholly Open Access electronic journal. Its aim is to provide a fully peer reviewed publication route for new shorter contributions in the field of atmospheric and closely related sciences. Through its ability to publish shorter contributions more rapidly than conventional journals, ASL offers a framework that promotes new understanding and creates scientific debate - providing a platform for discussing scientific issues and techniques.
We encourage the presentation of multi-disciplinary work and contributions that utilise ideas and techniques from parallel areas. We particularly welcome contributions that maximise the visualisation capabilities offered by a purely on-line journal. ASL welcomes papers in the fields of: Dynamical meteorology; Ocean-atmosphere systems; Climate change, variability and impacts; New or improved observations from instrumentation; Hydrometeorology; Numerical weather prediction; Data assimilation and ensemble forecasting; Physical processes of the atmosphere; Land surface-atmosphere systems.