CNCast: Leveraging 3D Swin Transformer and DiT for Enhanced Regional Weather Forecasting

2025-03-16

AI Summary

Current nowcasting systems suffer from insufficient accuracy for short-term forecasts (1 hour to 5 days) and low-resolution precipitation diagnostics at regional scales. Method: This paper proposes a high-accuracy, hourly regional forecasting framework that integrates physical constraints with generative modeling. We introduce the first coupling of a 3D Swin Transformer with a latent diffusion transformer (DiT) to construct a multi-scale meteorological sequence generator; incorporate numerical weather prediction (NWP) boundary-condition embeddings to enforce physical consistency; and establish a novel 5-km-resolution, hourly precipitation diagnostic paradigm. Results: Experiments demonstrate that our model significantly outperforms the global benchmark Pangu-Weather across multiple key meteorological variables. It achieves substantial improvements in regional forecast accuracy and temporal stability, offering a scalable, physically interpretable technical pathway for high-resolution, short-term forecasting.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Machine Learning: Large Multimodal Models (LMMs)
• Planning, Routing, and Scheduling: Planning with Language Models

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Web Mining and Content Analysis: Large pretrained models with web data
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

This study introduces a cutting-edge regional weather forecasting model based on the SwinTransformer 3D architecture. This model is specifically designed to deliver precise hourly weather predictions ranging from 1 hour to 5 days, significantly improving the reliability and practicality of short-term weather forecasts. Our model has demonstrated generally superior performance when compared to Pangu, a well-established global model. The evaluation indicates that our model excels in predicting most weather variables, highlighting its potential as a more effective alternative in the field of limited area modeling. A noteworthy feature of this model is the integration of enhanced boundary conditions, inspired by traditional numerical weather prediction (NWP) techniques. This integration has substantially improved the model's predictive accuracy. Additionally, the model includes an innovative approach for diagnosing hourly total precipitation at a high spatial resolution of approximately 5 kilometers. This is achieved through a latent diffusion model, offering an alternative method for generating high-resolution precipitation data.

Problem

• Develops a regional weather forecasting model using SwinTransformer 3D.
• Improves short-term weather predictions from 1 hour to 5 days.
• Enhances predictive accuracy with high-resolution precipitation diagnostics.

Innovation

• Uses 3D Swin Transformer for weather forecasting
• Integrates enhanced boundary conditions from NWP
• Employs latent diffusion for high-resolution precipitation