A Positive-Unlabeled Learning Algorithm for Urban Flood Susceptibility Modeling
Flood susceptibility modeling helps understand the relationship between influencing factors and occurrence of urban flooding and further provides spatial distribution of flood risk, which is critical for flood-risk reduction. Machine learning methods have been widely applied in flood susceptibility...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-11-01
|
| Series: | Land |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-445X/11/11/1971 |
| _version_ | 1797467612849897472 |
|---|---|
| author | Wenkai Li Yuanchi Liu Ziyue Liu Zhen Gao Huabing Huang Weijun Huang |
| author_facet | Wenkai Li Yuanchi Liu Ziyue Liu Zhen Gao Huabing Huang Weijun Huang |
| author_sort | Wenkai Li |
| collection | DOAJ |
| description | Flood susceptibility modeling helps understand the relationship between influencing factors and occurrence of urban flooding and further provides spatial distribution of flood risk, which is critical for flood-risk reduction. Machine learning methods have been widely applied in flood susceptibility modeling, but traditional supervised learning requires both positive (flood) and negative (non-flood) samples in model training. Historical flood inventory data usually contain positive-only data, whereas negative data selected from areas without flood records are prone to be contaminated by positive data, which is referred to as case-control sampling with contaminated controls. In order to address this problem, we propose to apply a novel positive-unlabeled learning algorithm, namely positive and background learning with constraints (PBLC), in flood susceptibility modeling. PBLC trains a binary classifier from case-control positive and unlabeled samples without requiring truly labeled negative data. With historical records of flood locations and environmental covariates, including elevation, slope, aspect, plan curvature, profile curvature, slope length factor, stream power index, topographic position index, topographic wetness index, distance to rivers, distance to roads, land use, normalized difference vegetation index, and precipitation, we compared the performances of the traditional artificial neural network (ANN) and the novel PBLC in flood susceptibility modeling in the city of Guangzhou, China. Experimental results show that PBLC can produce more calibrated probabilistic prediction, more accurate binary prediction, and more reliable susceptibility mapping of urban flooding than traditional ANN, indicating that PBLC is effective in addressing the problem of case-control sampling with contaminated controls and it can be successfully applied in urban flood susceptibility mapping. |
| first_indexed | 2024-03-09T18:56:09Z |
| format | Article |
| id | doaj.art-d027fc3ed4124d95a7e3882989ffb26c |
| institution | Directory Open Access Journal |
| issn | 2073-445X |
| language | English |
| last_indexed | 2024-03-09T18:56:09Z |
| publishDate | 2022-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Land |
| spelling | doaj.art-d027fc3ed4124d95a7e3882989ffb26c2023-11-24T05:28:27ZengMDPI AGLand2073-445X2022-11-011111197110.3390/land11111971A Positive-Unlabeled Learning Algorithm for Urban Flood Susceptibility ModelingWenkai Li0Yuanchi Liu1Ziyue Liu2Zhen Gao3Huabing Huang4Weijun Huang5School of Geography and Planning, Sun Yat-Sen University, Guangzhou 510006, ChinaSchool of Geography and Planning, Sun Yat-Sen University, Guangzhou 510006, ChinaSchool of Geography and Planning, Sun Yat-Sen University, Guangzhou 510006, ChinaGuangzhou Institute of Geography, Guangdong Academy of Sciences, Guangzhou 510070, ChinaSchool of Geography and Planning, Sun Yat-Sen University, Guangzhou 510006, ChinaSchool of Geography and Planning, Sun Yat-Sen University, Guangzhou 510006, ChinaFlood susceptibility modeling helps understand the relationship between influencing factors and occurrence of urban flooding and further provides spatial distribution of flood risk, which is critical for flood-risk reduction. Machine learning methods have been widely applied in flood susceptibility modeling, but traditional supervised learning requires both positive (flood) and negative (non-flood) samples in model training. Historical flood inventory data usually contain positive-only data, whereas negative data selected from areas without flood records are prone to be contaminated by positive data, which is referred to as case-control sampling with contaminated controls. In order to address this problem, we propose to apply a novel positive-unlabeled learning algorithm, namely positive and background learning with constraints (PBLC), in flood susceptibility modeling. PBLC trains a binary classifier from case-control positive and unlabeled samples without requiring truly labeled negative data. With historical records of flood locations and environmental covariates, including elevation, slope, aspect, plan curvature, profile curvature, slope length factor, stream power index, topographic position index, topographic wetness index, distance to rivers, distance to roads, land use, normalized difference vegetation index, and precipitation, we compared the performances of the traditional artificial neural network (ANN) and the novel PBLC in flood susceptibility modeling in the city of Guangzhou, China. Experimental results show that PBLC can produce more calibrated probabilistic prediction, more accurate binary prediction, and more reliable susceptibility mapping of urban flooding than traditional ANN, indicating that PBLC is effective in addressing the problem of case-control sampling with contaminated controls and it can be successfully applied in urban flood susceptibility mapping.https://www.mdpi.com/2073-445X/11/11/1971urban floodingsusceptibilitymachine learningpositive dataunlabeled data |
| spellingShingle | Wenkai Li Yuanchi Liu Ziyue Liu Zhen Gao Huabing Huang Weijun Huang A Positive-Unlabeled Learning Algorithm for Urban Flood Susceptibility Modeling Land urban flooding susceptibility machine learning positive data unlabeled data |
| title | A Positive-Unlabeled Learning Algorithm for Urban Flood Susceptibility Modeling |
| title_full | A Positive-Unlabeled Learning Algorithm for Urban Flood Susceptibility Modeling |
| title_fullStr | A Positive-Unlabeled Learning Algorithm for Urban Flood Susceptibility Modeling |
| title_full_unstemmed | A Positive-Unlabeled Learning Algorithm for Urban Flood Susceptibility Modeling |
| title_short | A Positive-Unlabeled Learning Algorithm for Urban Flood Susceptibility Modeling |
| title_sort | positive unlabeled learning algorithm for urban flood susceptibility modeling |
| topic | urban flooding susceptibility machine learning positive data unlabeled data |
| url | https://www.mdpi.com/2073-445X/11/11/1971 |
| work_keys_str_mv | AT wenkaili apositiveunlabeledlearningalgorithmforurbanfloodsusceptibilitymodeling AT yuanchiliu apositiveunlabeledlearningalgorithmforurbanfloodsusceptibilitymodeling AT ziyueliu apositiveunlabeledlearningalgorithmforurbanfloodsusceptibilitymodeling AT zhengao apositiveunlabeledlearningalgorithmforurbanfloodsusceptibilitymodeling AT huabinghuang apositiveunlabeledlearningalgorithmforurbanfloodsusceptibilitymodeling AT weijunhuang apositiveunlabeledlearningalgorithmforurbanfloodsusceptibilitymodeling AT wenkaili positiveunlabeledlearningalgorithmforurbanfloodsusceptibilitymodeling AT yuanchiliu positiveunlabeledlearningalgorithmforurbanfloodsusceptibilitymodeling AT ziyueliu positiveunlabeledlearningalgorithmforurbanfloodsusceptibilitymodeling AT zhengao positiveunlabeledlearningalgorithmforurbanfloodsusceptibilitymodeling AT huabinghuang positiveunlabeledlearningalgorithmforurbanfloodsusceptibilitymodeling AT weijunhuang positiveunlabeledlearningalgorithmforurbanfloodsusceptibilitymodeling |