This study develops an innovative insurance rate modelling framework that integrates climate projection data into actuarial pricing mechanisms to mitigate escalating risks posed by extreme weather events. Characterizing weather variability as a compound Poisson stochastic process with jump-diffusion components, it quantifies catastrophe intensity and duration patterns using a 2000–2023 historical meteorological dataset, and integrates expected shortfall (ES) with value-at-risk (VaR) methodologies to construct dynamic risk indices. Premium calibration is achieved via 10,000 Monte Carlo climate scenario simulations, complemented by sensitivity tests on temperature thresholds (Δ2–5°C), rainfall variability (±30%) and catastrophe recurrence cycles (5–20 years). Empirical validation with agricultural insurance cases demonstrates 92.3% predictive accuracy for typhoon-related losses and an 18.7% improvement in flood risk mitigation through adaptive deductibles. The model optimizes underwriting strategies via machine learning-enhanced climate pattern recognition and supports public disaster resilience planning, enabling insurers to develop climate-adaptive products, optimize capital allocation and enhance market sustainability amid environmental uncertainties.

Wenze Wang. Research on Insurance Operation under Extreme Weather Conditions. Academic Journal of Computing & Information Science (2026), Vol. 9, Issue 2: 77-85. https://doi.org/10.25236/AJCIS.2026.090211.

[1] Zheng Xue, Li Wenle. Exploration of the Application Value and Practice of Probability and Statistics in Economic Analysis [J]. Investment and Entrepreneurship, 2021, 32 (09): 82-84.

[2] Li Li Wu, Shimei, Chen Zhenzhu. Extreme weather risks and macroeconomic fluctuations - based on the dual perspectives of network correlation and spatial spillovers [J]. Financial Research, 2023, (9): 58-75.

[3] China Meteorological Administration, Ministry of Finance, et al. Guidance on Strengthening Synergistic Cooperation between Financial and Meteorological Sectors to Serve High-Quality Economic and Social Development [R]. December 2024:1-18.

[4] Otto F E L, Boyd E, Jones R, et al. The role of meteorological data and event attribution in climate risk insurance pricing[J]. Climate Risk Management, 2023, 40: 100512.

[5] Eling M, Schmeiser H, Schmit J T. Insurance and the risk of climate change: A comprehensive review of the academic and industry literature[J]. Journal of Risk and Insurance, 2024, 91(1): 3-38.

[6] Born P, Klimaszewski-Blettner B. Extreme weather events and property insurance pricing: Evidence from the U.S. market[J]. Journal of Financial Services Research, 2023, 63(2): 189-216.

[7] Gan Yu Li. Reflections on insurance companies' response to catastrophe risk in extreme climate [J]. Shanghai Insurance, 2024 (11): 12-18.

[8] Carter M R, de Janvry A, Sadoulet E, et al. Index-based weather insurance for developing countries: A review of evidence and a new way forward[J]. World Development, 2022, 156: 105918.

[9] QYResearch Co., Ltd. Global Climate Risk Insurance Market Size and Trend Analysis (2025 Edition) [R]. 2025:46-89.

[10] Kunreuther, H., & Michel-Kerjan, E. The role of insurance in reducing losses from extreme events: The need for better data and analytics[J]. Geneva Papers on Risk and Insurance-Issues and Practice, 2020, 45(3): 373-386.

[11] Beijing Academy of Emergency Management Science and Technology. Normalization of extreme weather: How can megacities build a disaster prevention safety net?[R]. Beijing: Beijing Academy of Emergency Management Science and Technology, 2025-03: 1-22.

[12] Gatzert N, Kosub T. Climate change and the insurance industry: Market dynamics, strategic responses, and future outlook[J]. The Geneva Papers on Risk and Insurance-Issues and Practice, 2024, 49(2): 345-372.