| Title: |
When Vulnerability Drives Action: Designing Forward-Looking Frameworks for Disaster Preparedness. |
| Authors: |
Roderick, Thomas1 (AUTHOR) Tom@flamelit.tech; Tremblay, Monica Chiarini2 (AUTHOR) monica.tremblay@mason.wm.edu; Kohli, Rajiv2 (AUTHOR) rajiv.kohli@mason.wm.edu; Castellanos, Arturo2 (AUTHOR) arturo.castellanos@mason.wm.edu; Pengetnze, Yolande3 (AUTHOR) yolande.pengetnze@pccinnovation.org |
| Source: |
Information Systems Research (INFORMS). Apr2026, p1. 21p. |
| Abstract: |
The increasing frequency and severity of disasters underscore the limits of commonly used vulnerability indices (the Social Vulnerability Index (SoVI), the Centers for Disease Control and Prevention’s (CDC’s) Social Vulnerability Index (SVI), the Area Deprivation Index (ADI), and the Federal Emergency Management Agency’s (FEMA’s) National Risk Index (NRI)) that rely on static demographic proxies. As disaster impacts differ according to community composition, these limitations risk embedding structural bias and obscuring how specific hazards translate into distinct community needs. For example, some populations require medical support when power outages disrupt treatment, whereas others face heightened risks of housing loss or food insecurity. Anticipatory frameworks must therefore capture hazard-specific vulnerabilities and predict resource needs directly. We develop the Local Impact Vulnerability Assessment (LIVA), a computational design science framework that predicts disaster- and need-specific vulnerability rather than producing generic scores. LIVA integrates demographic, housing, socioeconomic, and health indicators with hazard exposure and FEMA-recorded outcomes, using Random Forest and XGBoost models validated via nested cross-validation, out-of-sample tests, and out-of-time evaluation on federally declared disasters from 2018–2025. In out-of-time and holdout evaluations, LIVA attains substantially higher correlations with observed FEMA needs across hazards and community need categories than existing indices. We further illustrate these results by applying LIVA to the 2024 Hurricane Beryl. Feature attribution and ablation analyses highlight the role of health and preventive care access alongside structural indicators. By linking hazards to resource need-specific outcomes, LIVA provides interpretable, actionable guidance for equitable allocation of scarce resources in preparedness and response.History: Ahmed Abbasi, Senior Editor; Heng Xu, Associate Editor.Supplemental Material: The online appendix is available at https://doi.org/10.1287/isre.2024.1683. [ABSTRACT FROM AUTHOR] |
| : |
Copyright of Information Systems Research (INFORMS) is the property of INFORMS: Institute for Operations Research & the Management Sciences and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) |
| Database: |
Business Source Premier |