WEKO3
アイテム
ソーシャルメディア画像を用いた豪雨時のリアルタイム浸水マッピングツールの開発と現地への適用
https://nied-repo.bosai.go.jp/records/7531
https://nied-repo.bosai.go.jp/records/7531910e49c1-361f-46c3-87da-b4fa029a0c53
| Item type | researchmap(1) | |||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 公開日 | 2026-04-27 | |||||||||||
| タイトル | ||||||||||||
| 言語 | ja | |||||||||||
| タイトル | ソーシャルメディア画像を用いた豪雨時のリアルタイム浸水マッピングツールの開発と現地への適用 | |||||||||||
| タイトル | ||||||||||||
| 言語 | en | |||||||||||
| タイトル | Development and Field Application of a Real-time Flood Mapping Tool Using Social Media Imagery During Severe Storm Events | |||||||||||
| 著者 |
Kohin Hirano
× Kohin Hirano
× Shakti P.c.
× Satoshi Iizuka
|
|||||||||||
| 抄録 | ||||||||||||
| 内容記述タイプ | Other | |||||||||||
| 内容記述 | Severe storm events in recent years have caused extensive flooding in various regions of Japan, creating significant challenges for rapid emergency response and damage assessment. This study presents a real-time flood mapping approach using images and videos from social media, implemented in a browser-based web GIS tool. The system enables users to input reference point and inundation depths to estimate inundation extents based on high-resolution elevation data. We applied this tool during two recent flood events: the July 2023 flood in Akita City and the September 2024 flood in Wajima City. Notably, the latter occurred in areas still recovering from the January 2024 Noto Peninsula Earthquake, amplifying the disaster's impact on vulnerable infrastructure and temporary housing. In both cases, flood conditions were estimated within hours after impact using social media data and the results were publicly available the same day. In Wajima, field surveys were conducted for post-event validation. Although some discrepancies were observed in areas where the terrain had changed due to earthquake-induced subsidence, overall agreement between estimated and observed flood depths was reasonably good. These results indicate that real-time flood mapping using crowd-sourced data is effective for flood disaster response and can supplement existing hazard information system. The study also highlights limitations in spatial accuracy and emphasized the need for automated region segmentation and multisource data fusion to improve scalability and reliability. | |||||||||||
| 言語 | en | |||||||||||
| 書誌情報 |
en : 12th European Conference on Severe Storms 発行日 2025-08-08 |
|||||||||||
| 出版者 | ||||||||||||
| 言語 | en | |||||||||||
| 出版者 | Copernicus GmbH | |||||||||||
| DOI | ||||||||||||
| 関連識別子 | 10.5194/ecss2025-150 | |||||||||||
