| Project/Area Number |
18K13843
|
|---|
| Research Category |
Grant-in-Aid for Early-Career Scientists
|
| Allocation Type | Multi-year Fund |
|---|
| Review Section |
Basic Section 22040:Hydroengineering-related
|
|---|
| Research Institution | Research and Development Center, Nippon Koei Co., Ltd. |
|---|
Principal Investigator |
HITOKOTO Masayuki 日本工営株式会社中央研究所, 先端研究センター, 課長 (40463559)
|
|---|
| Project Period (FY) |
2018-04-01 – 2024-03-31
|
| Project Status |
Completed (Fiscal Year 2023)
|
| Budget Amount *help |
¥4,030,000 (Direct Cost: ¥3,100,000、Indirect Cost: ¥930,000)
Fiscal Year 2020: ¥1,040,000 (Direct Cost: ¥800,000、Indirect Cost: ¥240,000)
Fiscal Year 2019: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000)
Fiscal Year 2018: ¥1,560,000 (Direct Cost: ¥1,200,000、Indirect Cost: ¥360,000)
|
|---|
| Keywords | 洪水予測 / 河川水位予測 / ダム流入量予測 / 都市河川 / 機械学習 / 深層学習 / 人工知能 / 氾濫予測 / ニューラルネットワーク / XRAIN |
|---|
| Outline of Final Research Achievements |
Using high-resolution rainfall data and deep learning, we constructed a rapid and accurate river water level prediction model for small and medium-sized urban rivers, which had been considered difficult to predict, and demonstrated it in the Tsurumi River. We also constructed a model that can directly read high-resolution rainfall radar data using a convolutional neural network (CNN), and demonstrated it in several river basins. In addition, we have improved the model by hybridizing it with physical models, applying explainable AI (XAI), and improving its applicability to inexperienced events through data augmentation. In the final year of the project, a review paper on runoff analysis using deep learning was published. In addition, as a development from the main theme of this research, we conducted a basic study of inundation area prediction technology for inundation by river water using artificial intelligence.
|
| Academic Significance and Societal Importance of the Research Achievements |
学術的意義は次の通りである。①都市河川における人工知能を用いたリアルタイム洪水予測手法の適用性の提示。②CNNの適用によるレーダ雨量の活用、データ拡張による大規模洪水への適用性の向上、不定流モデルとのハイブリッドによる縦断的な水位予測、深層学習に対するXAIの適用による説明性の向上など、新しい手法の開発。③レビュー論文の投稿による学術コミュニティへの知見の共有。
社会的意義は、気候変動による水害リスク増大への適応策に資する技術的貢献として、次の通りである。①洪水予測やダム運用の高度化に直結する技術開発・実証。②開発した水位予測と連携した、将来的なリアルタイム氾濫予測に向けた基礎技術の開発。
|
