A Computationally Efficient Simulation Framework for Long-Term Temperature in Climate Risk Stress Testing: A Case Study of the Yangtze River Delta Temperature Index.

Against the backdrop of global warming and frequent extreme weather events, temperature risk poses an increasingly prominent threat to economic and financial stability. Existing temperature models suffer from limitations such as high computational demands, slow updates, and difficulties in capturing extreme temperatures, making them inadequate to meet the timeliness requirements of the economic and financial systems for interannual-scale risk quantification and stress testing. This paper proposes a computationally efficient temperature risk stress testing model. By improving the O-U model and incorporating key physical drivers using the LSTM method, the model enhances the characterization of extreme temperatures. Empirical analysis based on the Yangtze River Delta Temperature Index from 2022 to 2024 demonstrates that the model effectively improves long-term prediction accuracy and extreme temperature simulation capabilities while maintaining low computational costs, particularly excelling in spring and summer. This model can serve as a flexible and efficient temperature risk stress testing tool for sectors such as banking, insurance, and energy, supporting daily loss estimation and scenario simulation, with promising application prospects.