Skip to content
Conference Open access

LULC-Based Flood Risk Assessment using Spatial Modeling for Watershed Decision Support

Sep 2026 · International Conference on Communications and Information Technology · pp. 1-7 · 0 citations · 43 references

Abstract

Rapid urbanization in peri-urban watersheds alters hydrological processes and exacerbates downstream flooding by replacing permeable vegetated landscapes with impervious surfaces. Hydrological and hydrodynamic modeling tools often demand extensive calibration datasets that are unavailable in data-limited regions. This study develops a data-driven spatial decision-support framework using multi-temporal Land Use and Land Cover dynamics as a proxy to evaluate flood risk. Using Landsat satellite imagery from 2015, 2020, and 2025 covering the Cikeas and Cileungsi sub-watersheds in West Java, Indonesia, LULC transition dynamics were classified in an open-source geographic information system using a Random Forest algorithm. Supervised classification performance reached an overall accuracy of 89.5% and a Kappa index of 0.86. Spatial overlay analysis demonstrated continuous urban expansion across both sub-watersheds. Between 2015 and 2025, built-up areas expanded from 20.4% to 48.2% in Cikeas and from 18.8% to 49.0% in Cileungsi. Concurrently, vegetation cover dropped from 42.4% to 24.1% in Cikeas and from 43.3% to 24.3% in Cileungsi. These land cover changes increased the Flood Risk Index from 0.26 to 0.93 in Cikeas and from 0.23 to 0.53 in Cileungsi. Urban planners and watershed managers can utilize this spatial proxy framework to identify high-risk flood zones and prioritize land-use zoning without requiring complex hydrodynamic simulations.

Read PDF

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.