Enhancing Demand-Oriented Regionalization with Agentic AI and Local Heterogeneous Data for Adaptation Planning
Seyedeh Mobina Noorani, Shangde Gao, Changjie Chen, Karla Saldana Ochoa
TL;DR
The paper addresses the misalignment between traditional planning boundaries and local disaster risk by proposing an agentic AI-based planning support system that generates demand-oriented planning regions. It combines RepSC-SOM, a data-driven regionalization framework with Embedding-Clustering-Refining, and an interactive, human-in-the-loop workflow to produce spatially coherent regions using local socioeconomic and environmental data. A Jacksonville, Florida flood-risk case study demonstrates feature-driven, interactive regionalization and iterative refinement to reflect local priorities. The approach enables targeted resource allocation and adaptive governance by bridging data-driven rigor with user-driven decision making. This work advances hazard-aware regionalization by delivering interpretable, flexible planning units suitable for dynamic climate adaptation and disaster response.
Abstract
Conventional planning units or urban regions, such as census tracts, zip codes, or neighborhoods, often do not capture the specific demands of local communities and lack the flexibility to implement effective strategies for hazard prevention or response. To support the creation of dynamic planning units, we introduce a planning support system with agentic AI that enables users to generate demand-oriented regions for disaster planning, integrating the human-in-the-loop principle for transparency and adaptability. The platform is built on a representative initialized spatially constrained self-organizing map (RepSC-SOM), extending traditional SOM with adaptive geographic filtering and region-growing refinement, while AI agents can reason, plan, and act to guide the process by suggesting input features, guiding spatial constraints, and supporting interactive exploration. We demonstrate the capabilities of the platform through a case study on the flooding-related risk in Jacksonville, Florida, showing how it allows users to explore, generate, and evaluate regionalization interactively, combining computational rigor with user-driven decision making.