2021 Fiscal Year Final Research Report
Development of an automatic estimation method for urban morphology as a basis for systematization of urban warming adaptation measures
| Project/Area Number |
19K22004
|
|---|
| Research Category |
Grant-in-Aid for Challenging Research (Exploratory)
|
| Allocation Type | Multi-year Fund |
|---|
| Review Section |
Medium-sized Section 23:Architecture, building engineering, and related fields
|
|---|
| Research Institution | Tohoku University |
|---|
Principal Investigator |
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
石田 泰之 東北大学, 工学研究科, 助手 (20789515)
|
|---|
| Project Period (FY) |
2019-06-28 – 2022-03-31
|
| Keywords | 市街地形態 / 都市微気候 / 類型化 / 衛星データ / 機械学習 / アジア型市街地 |
|---|
| Outline of Final Research Achievements |
Based on a morphological analysis of the Tokyo Metropolis, this study proposes a classification scheme for detailed categorization of heterogeneous urban morphology and non-uniform land cover, commonly seen in Asian cities. The effectiveness of the proposed scheme and standards was evaluated by the thermal radiation environment which is mainly defined by the urban morphological parameters such as building density and height, and land cover characteristics. Furthermore, a neural network-based method to predict the long-term thermal radiation environment around buildings was developed. For the neural network, a multi-layer neural network optimized by genetic algorithms and backpropagation algorithms was employed to achieve high prediction accuracy. Additionally, the land surface conditions generated by the urban classification method were incorporated into a mesoscale climate model to predict the regional-scale climate with a more detailed consideration of urban influences.
|
| Free Research Field |
建築環境・設備
|
| Academic Significance and Societal Importance of the Research Achievements |
本研究で提案した、都市形態や土地被覆条件が複雑なアジアの都市に適用可能な統一的な市街地形態区分手法の利用を普及させていくことにより、市街地形態とこれにより形成される微気候の関係性に関する研究を加速することが期待される。また、ここで提案した手法は、街区全体のエネルギー消費や水害対策等の他の課題にも利用できるものである。さらに、ここで開発した機械学習による高精度な熱放射環境の予測モデルは、長期間の都市気候予測を高速で実施することを可能とするものであり、本研究で取り組んだように広域気象解析と連携することにより、様々な用途に利用可能である。
|
