Improvement of disastrous extreme precipitation forecasting in North China by Pangu-weather AI-driven regional WRF model

Abstract

In the realm of weather forecasting, the implementation of Artificial Intelligence (AI) represents a transformative approach. However, AI weather forecasting method still faces challenges in accurately predicting meso- and smaller-scale processes and failing to directly capture extreme precipitation due to regression algorithm's nature, coarse resolution, and limitations in key variables like precipitation. Therefore, we propose a state-of-the-art technology which integrates the strengths of the Pangu-Weather AI weather forecasting with the traditional regional weather model, focusing specifically on enhancing the prediction of extreme precipitation events, as mainly exemplified by an unprecedented precipitation in North China from 29 July to 1 August 2023, and an additional extraordinary precipitation event as a supplementary validation to further ensure the accuracy of this technology. The results show that the AI-driven approach exhibits superior performance in capturing the spatial and temporal dynamics of extreme precipitation events. Remarkably, with a threshold of 400 mm, the AI-driven model secures a Threat Score (TS) of 0.1 for forecast lead time reaching up to 8.5 days. This performance notably surpasses the performance of traditional GFS-Driven models, which achieve a similar TS only within a limited 3-day forecast lead time. This considerable enhancement in forecast accuracy, especially over extended lead times illustrates the AI-driven model’s potential to advance in long-term forecasts of extreme precipitation, previously considered challenging, emphasizing the potential of AI in augmenting and refining traditional weather prediction.

Exploring the Integration of a Global AI Model with Traditional Data Assimilation in Weather Forecasting

“…Despite the efficacy demonstrated by the Pangu AI model with the GSI DA system, accurately forecasting extreme precipitation events using current AI models remains a formidable challenge owing to limitations in resolution and the smooth nature of deep learning schemes. Recognizing these difficulties, Xu et al (2024) proposed an approach that integrates the Pangu weather forecasting model with the regional WRF model. This hybrid strategy capitalizes on the large-scale forecasting strengths of the AI model and the detailed resolution capabilities of the regional model, specifically addressing the deficiencies of AI models in predicting extreme precipitation.…”

“…These experiments were differentiated by their driving data sources: one used output from the CTRL experiment, termed WRF_CTRL, and the other utilized outputs from the GSI-Pangu experiments, termed WRF_GSI-Pangu. Except for the driving fields, all WRF model settings were consistent with those described in Xu et al (2024); for detailed specifications, please refer to this study. The aim was not only to evaluate their ability to simulate extreme weather events but also to investigate the effectiveness of integrating traditional DA systems with AI-based forecasting models.…”

“…These models have demonstrated unprecedented ability to surpass the accuracy of the European Centre for Medium-range Weather Forecasts (ECMWF) Integrated Forecasting System, traditionally recognized as the global benchmark in numerical forecasting (Ben-Bouallegue et al, 2023). The consistent reliability of these AI-driven models heralds a notable paradigm shift in predictive meteorology, signaling profound changes in both the methodologies and applications of weather forecasting (Xu et al, 2024).…”