The U.S. home insurance market is experiencing growing instability due to rising climate risks, surging premiums, and widespread non-renewals. Despite the urgent need for data-driven insights, publicly available datasets remain limited, making it difficult to assess and mitigate climate-driven insurance risk. This study introduces an AI-driven modeling framework that predicts home insurance premiums and non-renewals at high spatial resolution. By integrating multimodal data—including Google’s Population Dynamics Foundation Model embeddings (leveraging transfer learning), socioeconomic indicators, historical loss records, and physical climate risk—the model first predicts county-level trends before applying embedding-based super-resolution to refine predictions at the zipcode level. Results show strong predictive performance, achieving 93% top-2 accuracy in premium classification and explaining 61% of the variability in non-renewals at the county level. Feature importance analysis highlights climate hazards, such as hurricane and wildfire risk, as key drivers of recent insurance market shifts. By offering fine-scale, data-driven insights, this study not only enhances understanding of how climate change is reshaping the insurance industry but also provides actionable guidance to incentivize resilient building, discourage high-risk development, and inform policies aimed at mitigating climate-related insurance volatility.