India Seeks to Harness AI for Anticipating Significant Weather Changes Amid Worries about Climate Change

MUMBAI: India is testing artificial intelligence (AI) to build climate models to improve weather forecasts as heavy rains, floods and droughts increase across the vast country, a top weather official said.

Global warming has caused stronger weather system collisions in India in recent years and increased extreme weather events, which the independent Center for Science and Environment estimates have killed nearly 3,000 people this year.

Weather agencies around the world are focusing on artificial intelligence that can cut costs and improve speed, and which the UK Met Office says could “revolutionise” weather forecasting, after a Google-funded model was found to outperform traditional methods.

Accurate weather forecasts are especially important in India, home to 1.4 billion people, many of whom are poor, and the world’s second largest producer of rice, wheat and sugar.

The India Meteorological Department (IMD) provides forecasts based on mathematical models using supercomputers. Using artificial intelligence with an extended observational network can help generate higher quality predictions at lower cost.

The department expects the AI-based climate models and advice it has developed to help improve forecasts, K.S. Hosalikar, director of climate research and services at IMD, told Reuters.

The weather bureau has used artificial intelligence to generate public alerts about heat waves and diseases such as malaria, Hosalikar said. He plans to increase weather observation points by providing data down to the village level, potentially providing higher-resolution data for forecasts, he said.

The government announced Thursday that it wants to create weather and climate forecasts by incorporating artificial intelligence into traditional models, and has set up a center to test the idea through workshops and conferences.

“The AI model doesn’t require the high costs of running a supercomputer — you can even run it from a high-end desktop,” said Saurabh Rathore, an assistant professor at the Indian Institute of Technology in Delhi.

According to experts, better data is also needed to get the most out of artificial intelligence.

“Without high-resolution data in space and time, no AI model for location-specific upscaling of existing model predictions is possible,” said Parthasarathi Mukhopadhyay, a climate scientist at the Indian Institute of Tropical Meteorology.