Hurricanes pose a significant threat to population and critical infrastructure in the U.S. coastal regions annually, making it important to characterize the risk associated with them and understand how that may evolve in a changing climate. While the reliable observed record is not long enough to robustly quantify storm behavior, direct simulation of hurricanes using high resolution numerical models is computationally expensive. To overcome these challenges, a Risk Analysis Framework for Tropical Cyclones (RAFT) is being developed at PNNL. RAFT is a hybrid modeling approach that combines physics-based models with statistics and machine learning to model not only the physical behavior of hurricanes but also the human-systems impacts associated with them. Here we apply the RAFT framework to climate model output to understand how the US coastal hurricane risk may evolve under climate change. To this end, RAFT is applied to largescale environmental conditions derived from climate simulations belonging to the Coupled Model Intercomparison Project phase 6 (CMIP6). First, climate model output from the historical period is applied to RAFT and a comparison of model-simulated storms with observations is performed to benchmark model skill. Next, model projections of future climate under the ‘SSP585’ emissions scenario with unchecked anthropogenic greenhouse gas emissions, is applied to RAFT to quantify the potential future change in U.S. hurricane risk.