Surface air temperature anomaly prediction over Japan using artificial neural networks

Venkata Ratnam Jayanthi

講演情報

[E] 口頭発表

セッション記号 A (大気水圏科学) » A-AS 大気科学・気象学・大気環境

[A-AS04] Machine Learning Techniques in Weather, Climate, Hydrology and Disease Predictions

2021年6月4日(金) 15:30 〜 17:00 Ch.10 (Zoom会場10)

コンビーナ:Jayanthi Venkata Ratnam(Application Laboratory, JAMSTEC)、Rajib Maity(Indian Institute of Technology Kharagpur)、Behera Swadhin(Climate Variation Predictability and Applicability Research Group, Application Laboratory, JAMSTEC, 3173-25 Showa-machi, Yokohama 236-0001)、土井威志(JAMSTEC)、座長:Pascal Oettli(独立行政法人海洋研究開発機構)、Venkata Ratnam Jayanthi(Application Laboratory, JAMSTEC)、土井威志(JAMSTEC)、Swadhin Behera(Climate Variation Predictability and Applicability Research Group, Application Laboratory, JAMSTEC, 3173-25 Showa-machi, Yokohama 236-0001)

16:45 〜 17:00

[AAS04-12] Surface air temperature anomaly prediction over Japan using artificial neural networks

*Venkata Ratnam Jayanthi¹、Masami Nonaka¹、Swadhin Behera¹ (1.Application Laboratory, JAMSTEC)

キーワード：Artificial Neural Network, NMME

Prediction of surface air temperature anomalies over Japan using the well-known technique of artificial neural networks (ANN) is carried out for the winter season (December, January and February). The period of study is from 1949/50 to 2019/20. The input attributes to the ANN model are derived using lag correlation analysis. The ANN predictions are compared with the predictions of the North American Multi-Model Ensemble (NMME) models. The results indicate the ANN to outperform the NMME predictions. The ANN predictions have higher anomaly correlation skill score along with higher hit rate and lower false alarm rates. The results indicate the ANN to be a promising tool to predict the winter temperature anomalies over Japan.