Deciphering Urban Flood Drivers: An Explainable Machine Learning Approach to Vulnerability Assessment in Indonesian Catchments
インドネシアの流域における都市洪水要因の解読：説明可能な機械学習アプローチによる脆弱性評価 (AI 翻訳)
Ahyahudin Sodri, G. B. Imasuly, Nuraeni Nuraeni, Annisa Layyina Ihsani
🤖 gxceed AI 要約
日本語
本研究は、インドネシアの都市洪水脆弱性を評価するため、XGBoostとSHAPを用いた説明可能な機械学習フレームワークを開発した。衛星データと地理情報システムを統合し、全国514地区で洪水脆弱性指数（FVI）を算出。モデルは高い予測精度（R2=0.89）を達成し、特にバンダアチェなどの地域で高脆弱性を特定した。スケーラブルで透明性のあるアプローチは気候変動適応策を支援する。
English
This study develops an explainable machine learning framework using XGBoost and SHAP to assess urban flood vulnerability across Indonesia. Integrating satellite and geospatial data, it computes a Flood Vulnerability Index (FVI) for 514 districts, achieving high accuracy (R2=0.89). Key drivers include flood depth, population density, and elevation. The scalable framework supports data-driven climate adaptation planning.
Unofficial AI-generated summary based on the public title and abstract. Not an official translation.
📝 gxceed 編集解説 — Why this matters
日本のGX文脈において
インドネシアを対象とするが、本手法は日本の都市洪水脆弱性評価にも適用可能。特に説明可能AI（SHAP）の活用は、日本の自治体や企業の気候リスク開示（TCFD/SSBJ）において災害リスクの定量化に寄与する可能性がある。
In the global GX context
This paper demonstrates the application of explainable AI (XAI) to flood vulnerability assessment, relevant to global climate risk disclosure frameworks (TCFD, ISSB). The scalable methodology using open geospatial data can inform adaptation planning in data-scarce regions, aligning with the UN's Sendai Framework for Disaster Risk Reduction.
👥 読者別の含意
🔬研究者:Demonstrates how XGBoost and SHAP can be applied to flood vulnerability assessment, providing a replicable framework for other regions.
🏢実務担当者:The methodology can be used by urban planners and disaster management agencies to identify high-vulnerability areas and prioritize adaptation investments.
🏛政策担当者:Highlights the importance of data-driven vulnerability mapping for national climate adaptation strategies and reporting under frameworks like TCFD.
📄 Abstract（原文）
Flooding is one of the most frequent and damaging natural disasters, accounting for nearly half of global disasters and posing a major challenge in Indonesia, where floods represent approximately 77% of all nationally recorded disaster events. Rapid urbanisation, land-use change, and climate-induced extreme rainfall have intensified flood risks nationwide. However, existing vulnerability assessments remain fragmented and localised, limiting their relevance for national-scale adaptation planning. This study develops a measurable and explainable framework for assessing urban flood vulnerability across Indonesia using cloud-based geospatial data and interpretable machine learning. The approach integrates CEMS-GLOFAS (flood hazard), WorldPop (population exposure), SRTM (topography), and ESA WorldCover (land cover) datasets within Google Earth Engine (GEE). Flood vulnerability is quantified through a modified Flood Vulnerability Index (FVI) combining hazard, exposure, and physical vulnerability components. The Extreme Gradient Boosting (XGBoost) model predicts FVI values, while SHapley Additive exPlanations (SHAP) and Partial Dependence Plots (PDPs) enhance model transparency and identify the influence of key variables such as flood depth, population density, and elevation. The model achieved high predictive accuracy (R2 = 0.89; RMSE = 0.04728 FVI units, dimensionless) and revealed substantial spatial heterogeneity across 514 districts, with the highest FVI (0.75–0.85) in Banda Aceh, Mojokerto, Pasuruan, Samarinda, and Merauke. The integration of GEE and explainable AI offers a transparent, scalable framework to support data-driven flood risk mitigation and urban climate resilience in Indonesia.
🔗 Provenance — このレコードを発見したソース
- semanticscholar https://doi.org/10.3390/hydrology13070184first seen 2026-07-16 05:58:11
🔔 こうした論文の新着を逃したくない方は キーワードアラート に登録（無料・3キーワードまで）。
gxceed は公開メタデータに基づく研究支援データセットです。要約・翻訳・解説は AI 支援で生成されています。 最終的な解釈・検証は利用者が原典資料に基づいて行うことを前提とします。