Researchers at Northwestern Polytechnical University in China have proposed a novel deep learning-based framework that they say improves the accuracy of regional forecasts, even when data is limited. The study has been published in Atmospheric and Oceanic Science Letters.
Developing the AI model
The method integrates three major systems: the use of semantic segmentation models originally designed for medical image analysis; a learnable Gaussian noise mechanism that improves the model’s robustness; and a cascade prediction strategy that breaks the forecasting task into manageable stages.
“Our goal was to make regional forecasting smarter, faster and more reliable, even in data-limited scenarios,” said associate professor Congqi Cao, corresponding author of the study. “This is especially valuable for areas where a dense network of meteorological observations is not available.”
The method was tested on the East China Regional AI Medium Range Weather Forecasting Competition dataset, which includes 10 years of reanalysis data from ERA5. The task involved using past atmospheric variables to predict five key surface weather indicators – including temperature, wind and precipitation – every six hours for the next five days.
Research results
According to the researchers, the model achieved significant improvements in prediction performance, outperforming many mainstream global AI forecasting models. Specifically, the method reduced temperature forecast errors by 9.3%, improved the precipitation F1-score by 6.8% and lowered wind speed errors by 12.5%.
“This is the first time semantic segmentation and learnable noise mechanisms have been used together for regional weather forecasting,” explained Prof. Cao. “It opens up new possibilities for accurate forecasting in other data-scarce regions.”
Looking ahead, the team plans to extend its method to real-time systems and apply it to more regions across China. They state that they hope their work will eventually serve public safety, agriculture and disaster prevention needs – delivering smarter, faster and more local forecasts when they matter most.
In related news, a team of scientists from the IBS Center for Climate Physics (ICCP), Pusan National University in South Korea and the Alfred Wegener Institute, Helmholtz Centre for Polar and Marine Research (AWI) recently created a high-resolution climate model. According to the research, published in the open-access journal Earth System Dynamics, the model provides unprecedented insights into Earth’s future climate and its variability. Read the full story here