著者
KUDO Atsushi
出版者
Meteorological Society of Japan
雑誌
気象集誌. 第2輯 (ISSN:00261165)
巻号頁・発行日
pp.2022-011, (Released:2021-11-02)
被引用文献数
2

The Japan Meteorological Agency (JMA) operates gridded temperature guidance to predict two-dimensional (2D) snowfall amounts and precipitation types e.g., rain and snow because surface temperature is one of the key elements to predict them. Operational temperature guidance is based on the Kalman filter, which uses temperature observation and numerical weather prediction (NWP) outputs only around observation sites. Correcting a temperature field when NWP models incorrectly predict a front's location or when observed temperatures are extremely cold or hot has been challenging.  In this study, an encoder–decoder-based convolutional neural network (CNN) has been proposed to predict gridded temperatures at the surface around the Kanto region in Japan. Verification results showed that the proposed model greatly improves the operational guidance and can correct NWP model biases, such as a positional error of fronts and extreme temperatures.

言及状況

外部データベース (DOI)

Twitter (4 users, 5 posts, 23 favorites)

New Online Release of JMSJ Vol. 100, No.1 (February 2022)! Kudo, A., 2022: Statistical post-processing for gridded temperature prediction using encoder–decoder-based deep convolutional neural networks. J. Meteor. Soc. Japan, 100, 219-232. https://t.co/Wc8U4whCbp https://t.co/HFbizbkgUv
New Graphical Abstract now available online! https://t.co/mJnVGtWd1L Kudo, A., 2022: Statistical post-processing for gridded temperature prediction using encoder–decoder-based deep convolutional neural networks. J. Meteor. Soc. Japan, 100, https://t.co/Wc8U4vZsXh. https://t.co/BTrbiLjvNq
数値予報課工藤さんのJMSJ論文。深層畳み込みニューラルネットワークによる面的気温ガイダンスは、現行の(地点別カルマンフィルタに基づく)よりも沿岸前線の位置ずれや極端気温の表現を通じて平均成績を大幅に改善する由 https://t.co/r42xCCEZom

収集済み URL リスト