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

[AAS04-07] Climate predictability for societal applications including AI/ML

*Swadhin Behera¹, Jayanthi Venkata Ratnam¹, Manali Pal², Rajib Maiti³, Takeshi Doi¹ (1.Application Laboratory, VAiG, JAMSTEC, 3173-25 Showa-machi, Yokohama 236-0001, 2.National Institute of Technology, Warangal, India, 3.Indian Institute of Technology, Kharagpur, India)

Keywords:El Nino Modoki, Indian Ocean Dipole, AI/ML

The tropical Indo-Pacific domain is important for global climate and its predictability. The Indian Ocean variability is dominated by the Indian Ocean Dipole (IOD) and the Tropical Pacific Ocean has the El Niño/Southern Oscillation (ENSO) phenomenon as the dominant mode. In the recent decades a variant of the ENSO, the ENSO Modoki with warming (cooling) in the Central Pacific and cooing in the east and west tropical Pacific is found to be occurring more frequently. Coupled models like SINTEX-F has been predicting the ENSO Modokis and IOD quite well. Here an attempt is made to compare those predictabilities using predictions from an AI/ML based statistical approach.