India turns to AI in weather forecasts

India is testing artificial intelligence (AI) to build climate models to improve weather forecasting as torrential rains, floods and droughts proliferate across the vast country, according to a Reuters report.

A press release from India’s Press Information Bureau states that Artificial Intelligence (AI) and Machine Learning (ML) techniques are being used to improve the prediction skill of weather, climate, and ocean forecasts at various institutes under the ministry. The Indian Ministry of Earth Sciences (MoES) has established a dedicated AI and ML virtual center tasked with developing and testing various AI and ML techniques and capacity building activities by conducting workshops and conferences. A computing environment and virtual workspace for training and deploying AI models has been established in the India Meteorological Department (IMD).

As the Reuters report points out, weather agencies around the world are focussing on AI, which can bring down cost and improve speed, and which Britain’s Met Office says could “revolutionise”, opens new tab weather forecasting, with a recent Google-funded model found to have outperformed, opens new tab conventional methods. Accurate weather forecasting is particularly crucial in India, a country of 1.4 billion people, many impoverished, and the world’s second-largest producer of rice, wheat and sugar. The IMD provides forecasts based on mathematical models using supercomputers. Using AI with an expanded observation network could help generate higher-quality forecast data at lower cost.

In India, climate scientists have begun experimenting with AI. In December 2023, Kiren Rijiju, a minister at the Ministry of Earth Sciences (MoES), said the department had established a virtual centre dedicated to developing and refining various AI and ML techniques for enhanced weather predictions. Earlier this year, the IMD had highlighted that India’s weather scientists have started harnessing the power of artificial intelligence and machine learning to enhance weather forecasts. The IMD has deployed a network of 39 doppler weather radars that cover 85% of the country’s landmass and enable hourly forecasts for prominent cities. This advanced radar data, with a resolution of 350 meters per pixel, enables the detection and simulation of convective clouds, significantly enhancing forecast accuracy for extreme events like heavy rainfall and cyclones. The IMD has also digitised weather records for the country dating back to 1901 and artificial intelligence could be used to sift through this plentiful information to generate knowledge about weather patterns.

But as an Eco-Business report points out, while there has been considerable excitement around AI-based weather forecasting in India, the problem is lack of credible data. The report adds that amid the surge of extreme weather events globally, billions of dollars are pouring into developing cutting-edge weather forecasting models based on AI and ML. Leading tech giants, such as Google and IBM, are spearheading efforts for more precise and expedited forecasting. Traditional weather forecasting typically relies on computer calculations based on physics to predict the weather. In contrast, AI and deep learning (a subset of ML) use large volumes of raw, unfiltered and processed data to predict weather. When used in combination with traditional physical models and statistical methods, they can enhance the accuracy and reliability of weather forecasts. However, traditional weather models come with a quantifiable margin of error, which allows for the identification and correction of specific errors based on the physics equations on which they are built. AI/ML models often lack such transparency since they are based on past correlations, making it difficult to ascertain the exact reasons behind their inaccuracies.

A British Met press office had earlier reported that AI has the potential to revolutionise weather forecasting. Researchers from The Alan Turing Institute and the Met Office had just then joined forces in a new collaboration. The partnership has the organisations working together to develop AI models that will enable improved forecasting, including for extreme weather events, helping to save lives and protect critical national infrastructure.

As the British Met press office report highlighted, the UK’s national meteorological service has a track record of using advanced technology to help predict the weather. Using information from satellites as well as observational data from weather stations on Earth, they run simulations on a supercomputer that generates forecasts used by millions of people around the world.