{"title":"通过深度学习利用确定性天气预报进行现场概率温度预测","authors":"David Landry, A. Charantonis, C. Monteleoni","doi":"10.1175/mwr-d-23-0273.1","DOIUrl":null,"url":null,"abstract":"\nWe propose a neural network approach to produce probabilistic weather forecasts from a deterministic numerical weather prediction. Our approach is applied to operational surface temperature outputs from the Global Deterministic Prediction System up to ten-day lead times, targeting METAR observations in Canada and the United States. We show how postprocessing performance is improved by training a single model for multiple lead times. Multiple strategies to condition the network for the lead time are studied, including a supplementary predictor and an embedding. The proposed model is evaluated for accuracy, spread, distribution calibration, and its behavior under extremes. The neural network approach decreases CRPS by 15% and has improved distribution calibration compared to a naive probabilistic model based on past forecast errors. Our approach increases the value of a deterministic forecast by adding information about the uncertainty, without incurring the cost of simulating multiple trajectories. It applies to any gridded forecast including the recent machine learning-based weather prediction models. It requires no information regarding forecast spread and can be trained to generate probabilistic predictions from any deterministic forecast.","PeriodicalId":18824,"journal":{"name":"Monthly Weather Review","volume":null,"pages":null},"PeriodicalIF":2.8000,"publicationDate":"2024-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Leveraging deterministic weather forecasts for in-situ probabilistic temperature predictions via deep learning\",\"authors\":\"David Landry, A. Charantonis, C. Monteleoni\",\"doi\":\"10.1175/mwr-d-23-0273.1\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"\\nWe propose a neural network approach to produce probabilistic weather forecasts from a deterministic numerical weather prediction. Our approach is applied to operational surface temperature outputs from the Global Deterministic Prediction System up to ten-day lead times, targeting METAR observations in Canada and the United States. We show how postprocessing performance is improved by training a single model for multiple lead times. Multiple strategies to condition the network for the lead time are studied, including a supplementary predictor and an embedding. The proposed model is evaluated for accuracy, spread, distribution calibration, and its behavior under extremes. The neural network approach decreases CRPS by 15% and has improved distribution calibration compared to a naive probabilistic model based on past forecast errors. Our approach increases the value of a deterministic forecast by adding information about the uncertainty, without incurring the cost of simulating multiple trajectories. It applies to any gridded forecast including the recent machine learning-based weather prediction models. It requires no information regarding forecast spread and can be trained to generate probabilistic predictions from any deterministic forecast.\",\"PeriodicalId\":18824,\"journal\":{\"name\":\"Monthly Weather Review\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":2.8000,\"publicationDate\":\"2024-06-04\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Monthly Weather Review\",\"FirstCategoryId\":\"89\",\"ListUrlMain\":\"https://doi.org/10.1175/mwr-d-23-0273.1\",\"RegionNum\":3,\"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":"Monthly Weather Review","FirstCategoryId":"89","ListUrlMain":"https://doi.org/10.1175/mwr-d-23-0273.1","RegionNum":3,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"METEOROLOGY & ATMOSPHERIC SCIENCES","Score":null,"Total":0}
Leveraging deterministic weather forecasts for in-situ probabilistic temperature predictions via deep learning
We propose a neural network approach to produce probabilistic weather forecasts from a deterministic numerical weather prediction. Our approach is applied to operational surface temperature outputs from the Global Deterministic Prediction System up to ten-day lead times, targeting METAR observations in Canada and the United States. We show how postprocessing performance is improved by training a single model for multiple lead times. Multiple strategies to condition the network for the lead time are studied, including a supplementary predictor and an embedding. The proposed model is evaluated for accuracy, spread, distribution calibration, and its behavior under extremes. The neural network approach decreases CRPS by 15% and has improved distribution calibration compared to a naive probabilistic model based on past forecast errors. Our approach increases the value of a deterministic forecast by adding information about the uncertainty, without incurring the cost of simulating multiple trajectories. It applies to any gridded forecast including the recent machine learning-based weather prediction models. It requires no information regarding forecast spread and can be trained to generate probabilistic predictions from any deterministic forecast.
期刊介绍:
Monthly Weather Review (MWR) (ISSN: 0027-0644; eISSN: 1520-0493) publishes research relevant to the analysis and prediction of observed atmospheric circulations and physics, including technique development, data assimilation, model validation, and relevant case studies. This research includes numerical and data assimilation techniques that apply to the atmosphere and/or ocean environments. MWR also addresses phenomena having seasonal and subseasonal time scales.