AI helps improve predictability of Indian summer monsoons

A newly developed artificial intelligence-powered algorithm can help increase the predictability of the Indian Summer Monsoons (ISMR) 18 months ahead of the season. According to the Ministry of Science and Technology, the predictor discovery algorithm (PDA) developed using a single ocean-related variable could allow for accurate forecasting of the ISMR in time to make effective agricultural and other economic plans for the country.

Scientists from the Institute of Advanced Study in Science and Technology (IASST), Guwahati, an autonomous institute of the Department of Science and Technology (DST), and their collaborators discovered that the widely used sea surface temperature (SST) is insufficient for long-term prediction of ISMR. This was due to the fact that the potential skill of ISMR estimated by the predictor discovery algorithm (PDA) using SST-based predictors was low at all lead months, they discovered.

The team, which included IASST, the Indian Institute of Tropical Meteorology (IITM) in Pune, and Cotton University in Guwahati, developed a predictor discovery algorithm (PDA) that generates predictors at any lead month by projecting the ocean thermocline depth (D20) over the entire tropical belt between 1871 and 2010 onto a correlation map between ISMR and D20 over the same time period.

According to the ministry’s statement, the model’s success was based on AI’s ability to learn the relationship between ISMR and tropical thermocline patterns from 150 years of simulations by 45 physical climate models and then apply that learning to actual observations between 1871 and 1974. Given that the potential skill of ISMR at an 18-month lead is 0.87, there is still significant room for improvement in the model.