[1F4-GS-10c] AI応用：環境モニタリング

[1F4-GS-10c-04] Improvement in Wind Gust Detection System using CNN

〇Naoki Ishitsu^1,3, Kenichi Kusunoki¹, Toru Adachi¹, Hanako Inoue¹, Chusei Fujiwara², Ken-ichiro Arai^1,3, Hiroto Suzuki² (1. Meteorological Research Institute, 2. East Japan Railway Company, 3. Alpha-denshi Co., Ltd. )

Keywords:Meteorology, Convolutional neural network, Doppler radar, Tornado, Disaster prevention

We are developing a gust detection system using meteorological Doppler radar. When a gust such as a tornado occurs, a vortical airflow is generated in the lower level of the cumulonimbus cloud, and observation by a Doppler radar shows a pair of maximum and minimum Doppler velocities. So far, we have developed a mathematical model of this pattern, fitted it to observed data, and determined whether it is a vortex or not based on the calculated physical quantities. The problem with this method, however, is that it often results in many false detections and misses. In this study, we tried to distinguish vortices by using CNN and found that the performances were greatly improved by applying the CNN-based vortex determination.