New Delhi: To mitigate the impact of climate change and erratic weather phenomena, ‘Arka’ and ‘Arunika’, a High-Performance computing (HPC) system was launched on Thursday.
Prime Minister inaugurated a High-Performance Computing (HPC) system tailored for “weather and climate research” and marked the day a huge achievement in science and technology.
He noted that India’s capacity for weather forecasting will increase allowing for hyper-local and more accurate predictions with the advent of High-Performance Computing (HPC) Systems and supercomputers.
The Prime Minister further explained that weather and soil analysis by supercomputers in remote villages is not merely a scientific achievement but a “transformative change for thousands of lives.
Role of High-Performance Computing:
The High-Performance Computing (HPC) system tailored to track, analyze, simulate and predict the behaviour of weather systems, climate patterns and other atmospheric phenomena.
This project represents an investment of Rs. 850 crore, marking a significant leap in India’s computational capabilities for Meteorological applications.
Located at two key sites, the Indian Institute of Tropical Meteorology (IITM) in Pune and the National Center for Medium Range Weather Forecast (NCMRWF) in Noida, this HPC system has extraordinary computing power.
The new HPC systems are named ‘Arka’ and ‘Arunika,’ reflecting their connection to the Sun. These high-resolution models will significantly enhance the accuracy and lead time of predictions related to tropical cyclones, heavy precipitation, thunderstorms, hailstorms, heat waves, droughts, and other critical weather phenomena.
How Tech giants working on AI-based weather forecasting:
Recently, the United States allocated $100 million fund, which will harness artificial intelligence and machine learning capabilities to tackle advanced climate and weather research.
Google DeepMind, Google’s AI research laboratory, developed a machine learning model that it says can accurately predict and outperforms 90% of the targets used by the world’s best weather prediction systems.
As per the Science publisher, Google DeepMind’s AI weather forecasting model has been trained on almost 40 years of historical weather data to improve its accuracy, explains the publisher, Science.
But the algorithm this produced can predict weather up to 10 days away in less than one minute on a single desktop computer.
The Google DeepMind, also called GraphCast, the accuracy significantly beats current weather systems on 90% of 1,380 metrics, explain the Science journal.
