Chinese researchers at Fudan University's Shanghai Institute of Artificial Intelligence Sciences (SAIS) have announced the creation of a new artificial intelligence (AI) model to predict weather conditions.
This artificial intelligence model is tailored for sub-seasonal forecasting and shows high forecast accuracy within a two-week window. The model, called FuXI-Subseasonal, can make longer weather forecasts, with lead researcher Qi Yuan noting that it is adept at making predictions as far out as 30 days.
Qi revealed that the motivation for continuing to use generative AI weather forecasting models is to detect climate disaster warnings as early as possible. Researchers say that using the model, Chinese authorities will be able to identify climate crises in advance and take necessary measures to mitigate the damage.
“Here we introduce FuXi Subseasonal-to-Seasonal (FuXi-S2S), a machine learning-based subseasonal forecast model that provides global daily average forecasts up to 42 days covering 13 pressure levels and 11 surface variables of five upper-altitude atmospheric variables,” one paper reads.
Compared to traditional numerical weather forecasting that relies on supercomputers, FuXI-Subseasonal outperforms across multiple metrics and is able to produce accurate forecasts based on limited data.
“Climate disaster warning is another important value of the Fuxi-Subseasonal model,” Qi said in an interview with the Global Times.
The machine learning model, developed in collaboration with China's National Climate Center, is much faster than traditional weather forecast models, with the report saying it runs “thousands of times faster.” Longer forecasting horizons and greater accuracy may lead Chinese authorities to rely on local AI models to prevent climate disasters rather than products from North America and Europe.
Locally designed artificial intelligence models have shown promise in predicting climate disaster patterns in mainland China. In mid-2023, Chinese authorities confirmed that an early artificial intelligence model developed by SAIS accurately predicted the movement and intensity of Typhoon Doksurik, providing sufficient data for aid and disaster relief efforts.
The rise of weather forecasting systems based on artificial intelligence
While generative AI has found new use cases in multiple fields, the field of meteorology is still growing in usefulness, with several companies launching their products and merging them with other emerging technologies.
NASA and IBM (NASDAQ: IBM) have launched base models specifically for severe weather patterns, while Johns Hopkins University has partnered with the National Oceanic and Atmospheric Administration (NOAA) to launch their smart weather forecast model.
Google (NASDAQ: GOOGL ) has commercially released several weather forecast systems since mid-2023, but among other countries, India appears to be the biggest adopter of the technology as it attempts to mitigate a A series of environmental disasters.
For artificial intelligence (AI) to function within the law and thrive in the face of growing challenges, it needs to integrate an enterprise blockchain system that ensures data input quality and ownership, allowing it to keep data secure while Guaranteed immutability of data. Check out CoinGeek’s coverage Learn more about this emerging technology Why enterprise blockchain will become the backbone of artificial intelligence.
Watch: Transformative AI applications are coming
New to blockchain? Check out CoinGeek’s Blockchain for Beginners section, the ultimate resource guide for learning more about blockchain technology.
