Assessment of urban flood susceptibility using semi-supervised machine learning model

Gang Zhao; Bo Pang; Zongxue Xu; Dingzhi Peng; Liyang Xu

doi:10.1016/j.scitotenv.2018.12.217

Assessment of urban flood susceptibility using semi-supervised machine learning model

Sci Total Environ. 2019 Apr 1:659:940-949. doi: 10.1016/j.scitotenv.2018.12.217. Epub 2018 Dec 15.

Authors

Gang Zhao¹, Bo Pang², Zongxue Xu³, Dingzhi Peng³, Liyang Xu⁴

Affiliations

¹ College of Water Sciences, Beijing Normal University; Beijing 100875, China; Beijing Key Laboratory of Urban Hydrological Cycle and Sponge City Technology, Beijing 100875, China; School of Geographical Science, University of Bristol, Bristol BS8 1SS, UK.
² College of Water Sciences, Beijing Normal University; Beijing 100875, China; Beijing Key Laboratory of Urban Hydrological Cycle and Sponge City Technology, Beijing 100875, China. Electronic address: pb@bnu.edu.cn.
³ College of Water Sciences, Beijing Normal University; Beijing 100875, China; Beijing Key Laboratory of Urban Hydrological Cycle and Sponge City Technology, Beijing 100875, China.
⁴ School of Aeronautics, Northwestern Polytechnical University, Xi'an 710072, China.

PMID: 31096424
DOI: 10.1016/j.scitotenv.2018.12.217

Abstract

In order to identify flood-prone areas with limited flood inventories, a semi-supervised machine learning model-the weakly labeled support vector machine (WELLSVM)-is used to assess urban flood susceptibility in this study. A spatial database is collected from metropolitan areas in Beijing, including flood inventories from 2004 to 2014 and nine metrological, geographical, and anthropogenic explanatory factors. Urban flood susceptibility is mapped and compared using logistic regression, artificial neural networks, and a support vector machine. Model performances are evaluated using four evaluation indices (accuracy, precision, recall, and F-score) as well as the receiver operating characteristic curve. The results show that WELLSVM can better utilize the spatial information (unlabeled data), and it outperforms all comparison models. The high-quality WELLSVM flood susceptibility map is thus applicable to efficient urban flood management.

Keywords: Beijing; Flood susceptibility; Semi-supervised machine learning model; Urban area; Weakly labeled support vector machine.