気象用二重偏波フェーズドアレイレーダとCNNおよびLSTMを用いた豪雨検知手法

カテゴリ: 論文誌(論文単位)

グループ名: 【A】基礎・材料・共通部門

発行日: 2024/04/01

タイトル(英語): A Consideration of Heavy Rainfall Detection Method Using Multi-Parameter Phased Array Radar, Convolutional Neural Network, and Long Short-Term Memory Network

著者名: 後藤　翼（電気通信大学大学院情報理工学研究科），菊池　博史（電気通信大学宇宙・電磁環境研究センター），芳原　容英（電気通信大学大学院情報理工学研究科／電気通信大学宇宙・電磁環境研究センター），牛尾　知雄（大阪大学大学院工学研究科）

著者名(英語): Tsubasa Goto (Graduate School of Informatics and Engineering, The University of Electro-Communications), Hiroshi Kikuchi (Center for Space Science and Radio Engineering, The University of Electro-Communications), Yasuhide Hobara (Graduate School of Informatics and Engineering, The University of Electro-Communications/Center for Space Science and Radio Engineering, The University of Electro-Communications), Tomoo Ushio (Graduate School of Engineering, Osaka University)

キーワード: 二重偏波フェーズドアレイ気象レーダ，畳み込みニューラルネットワーク，長・短期記憶ネットワーク　　multi-parameter phased array weather radar，convolutional neural network，long short-term memory network

要約(英語): In order to mitigate weather disasters caused by heavy precipitations, it is important to observe 3-dimensional precipitation structure in a storm with high temporal resolution. In recent years, the development of phased array weather radar is being promoted for high-speed precipitation observations. We propose an algorithm for predicting heavy rainfall using machine learning for the novel phased array weather radar (Multi-Parameter Phased Array Weather Radar: MP-PAWR) observation data. The algorithm predicts localized convective rainfall by extracting the vertical structure of storms observed by MP-PAWR for each precipitation cell. The proposed method with the combination of convolutional neural networks and long short-term memory networks were applied to various observation data from MP-PAWR with high spatial and temporal resolution to predict heavy rainfalls a few minutes later. The results showed that the use of specific differential phase data gave particularly accurate predictions for heavy rainfall compared to radar reflectivity factor and differential reflectivity data.

本誌: 電気学会論文誌A（基礎・材料・共通部門誌） Vol.144 No.4 （2024） 特集：2023年基礎・材料・共通部門大会

本誌掲載ページ: 132-138 p

原稿種別: 論文／日本語

電子版へのリンク: https://www.jstage.jst.go.jp/article/ieejfms/144/4/144_132/_article/-char/ja/