プロジェクト情報（概要） / Project information (abstract)
基本情報 / Basic Informations
- 研究題目
Research Title 複数地域におけるAIベースの洪水予測の比較：洪水発生時の道路損傷被害の評価
Comparative AI-based flood prediction across multiple regions: assessing road damage during flood
- 状態
Status -
実施中
Started
- 研究番号
Research Number - 1527
- 研究代表者
PI - シャリフィアユーブ / 広島大学
- 事務担当者
Secretary - シャリフィアユーブ / 広島大学
- 受入CSIS教員
CSIS reception staff 中居 楓子
Fuko NAKAI
- 研究内容
Abstract With recent advances in computer science, Artificial Intelligence (AI) has been increasingly adopted across various disciplines to enhance predictive capabilities, with flood risk management emerging as one of its most prominent application areas. Accurate and timely flood forecasting is essential for effective mitigation planning and for minimizing damage to human life, infrastructure, and property. Despite extensive research on AI-based flood prediction, limited attention has been paid to road damage prediction during floods. This study presents a systematic comparison of three widely adopted AI-based models (ConvLSTM, Transformer, and PredRNN++) for flood risk prediction, with a specific focus on flood damage to road infrastructure. First, rainfall forecasting will be performed using three flood-prediction AI models applied to three case study areas characterized by different road network densities and configurations. This multi-regional approach enables the identification of (1) the most suitable model for flood risk prediction when road systems are explicitly incorporated, and (2) the most effective model for real-time flood prediction and road damage applications. Model performance is evaluated using five statistical metrics alongside established flood indicators and road configurations, enabling a robust and comprehensive comparison. The results highlight how road network characteristics influence flood prediction accuracy and demonstrate that model suitability varies across regions and operational requirements. The findings provide valuable insights for selecting appropriate AI models for flood risk management and real-time decision support, thereby contributing to more resilient, infrastructure-aware flood mitigation strategies.
- 研究期間
Research Period - 2026-02-10 - 2027-03-31
変更申請
変更のために新しい申請を保存します。
This will save a new application on the system for a modification.
研究者 / Researchers
申請中の研究者は表示されません。 / Pending researchers are not shown.
アリレザ・ニクナム・カージェパシャ / 広島大学大学院スマート社会創造研究科
シャリフィアユーブ / 広島大学
研究成果 / Achievement
年次報告一覧 / Annual reports 必須
年次報告の内容はメンバーのみ表示されます。