Logo image
An equity-informed decision-making framework utilizing multi-group constrained system optimization: towards large-scale emergency evacuations
Journal article   Open access   Peer reviewed

An equity-informed decision-making framework utilizing multi-group constrained system optimization: towards large-scale emergency evacuations

Yang Liu, Zhenzhen Li, Benjamin Lev and Lu Gan
Geomatics, natural hazards and risk, v 16(1), 2601822
31 Dec 2025
url
https://doi.org/10.1080/19475705.2025.2601822View
Published, Version of Record (VoR) Open

Abstract

disaster management evacuation planning natural language processing optimization theory Vulnerability risk assessment
Climate change exacerbates geospatial vulnerability, rendering populations more susceptible to environmental disasters. Vulnerable groups face heightened disaster risks, necessitating targeted strategies. This study proposes a multi-group constrained system optimization (MGCSO) framework with equity as its objective, integrating vulnerability assessment with evacuation planning. Firstly, based on online comment analysis, it employs natural language processing (NLP) techniques to extract public perceptions and assess vulnerability disparities among different groups. Subsequently, an enhanced MGCSO algorithm, integrated with GIS, generates customised evacuation plans based on each group's 'tolerance.' To validate the framework's efficacy, a case study was conducted in Yucheng District, Yaan City, China. Compared to conventional methods, this framework significantly improves evacuation efficiency for vulnerable groups, reducing total evacuation time by 23%. This study provides governments with an evidence-based vulnerability assessment methodology and decision support. It not only enhances disaster resilience but also specifically supports the effective assistance of vulnerable groups during flood emergencies.

Metrics

10 Record Views

Details

UN Sustainable Development Goals (SDGs)

This publication has contributed to the advancement of the following goals:

#11 Sustainable Cities and Communities

InCites Highlights

Data related to this publication, from InCites Benchmarking & Analytics tool:

Collaboration types
Domestic collaboration
International collaboration
Web of Science research areas
Geosciences, Multidisciplinary
Meteorology & Atmospheric Sciences
Remote Sensing
Water Resources
Logo image