I-Corps: Translation Potential of Precise, Location-Specific Weather Risk Assessments

This I-Corps project focuses on the development of a risk assessment modeling tool designed to deliver highly localized, seasonal evaluations of environmental hazards. The solution addresses a pressing national need to improve community resilience and economic preparedness in the face of increasing weather-related threats. Currently available tools often offer limited precision, presenting data at broader geographic scales and failing to account for the seasonal variability of hazards. This limitation makes it difficult for decision-makers in real estate, infrastructure planning, and insurance to accurately assess risk and plan mitigation strategies. The technology enables users to input a specific location and receive detailed hazard indices that reflect current vulnerabilities and also change over time and across seasons. Outputs are presented through intuitive visualizations, such as maps and charts, to facilitate use by both experts and non-experts. By making environmental risk data more accessible and tailored to specific parcels of land, this project enables better decision-making, supports safer urban development, and reduces long-term costs. The technology advances scientific understanding, strengthens economic resilience, and helps communities prepare for and respond to weather-related disasters.

This I-Corps project utilizes experiential learning coupled with a first-hand investigation of the industry ecosystem to assess the translation potential of the technology. This solution is based on the development of a geospatial modeling platform that applies advanced algorithms to assess compound and seasonal natural hazards at high spatial resolution. The platform processes a range of public environmental datasets to evaluate hazard exposure, vulnerability, and preparedness metrics, integrating them into a composite hazard index. Unlike traditional tools that use static or low-resolution data, this technology supports dynamic, time-sensitive risk assessments tailored to the location and season. The platform incorporates advanced statistical normalization techniques, machine learning-based pattern recognition, and customizable timeframes for historical analysis. Risk factors are quantified and converted into user-friendly outputs including heatmaps, graphs, and summary tables. Early-stage validation studies have shown that the system can accurately predict risk-related outcomes when compared against observed hazard data. These results are evaluated using statistical metrics such as percent bias and correlation coefficients to ensure scientific rigor. The technology holds promise for transforming how professionals in planning, engineering, and environmental management access and apply risk information to make timely, location-specific decisions.

This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

Award Number: 2513039
Principal Investigator: Dalya Ismael
Funds Obligated: $50,000
State: VA