The India Meteorological Department (IMD) is exploring ways to use artificial intelligence (AI) in weather forecasting, especially for issuing nowcasts. The AI intervention is said to improve the prediction of extreme weather events by 3-6 hours, said Mrutunjay Mohapatra, the IMD Director-General on Sunday.

Since the use of AI and machine learning is not prevalent in the weather forecasting industry, at least in India, the IMD has invited various research groups to study AI integration into improving weather forecasting. Plans for collaborative studies on this topic are also in the pipelines. The Ministry of Earth Sciences is evaluating their proposals, Mohapatra shared.

Currently, IMD uses technologies such as radars and satellite imagery to issue nowcasts. Nowcasts are extreme weather predictions that can occur in the next 3-6 hours.

Extreme weather events such as thunderstorms and dust storms are more difficult to predict than cyclones because these situations develop and dissipate in short periods of time, however, cause much damage to life and property with the heavy rains and winds and lightning. In the month on July, more than 160 people perished by lighting in Uttar Pradesh and Bihar, alone.

IMD's move comes at an opportune moment as its counterparts across the world too set out to explore the extent of AI and machine learning technology in weather forecasting. The National Oceanic and Atmospheric Administration of the U.S. announced new strategies this year to expand the agency's application of four emerging science and technology focus areas — NOAA Unmanned Systems, artificial intelligence, Omics, and the cloud — to guide transformative advancements in the quality and timeliness of NOAA science, products and services.