Flood resilience assessment of region based on TOPSIS-BOA-RF integrated model
Global climate change and rapid urbanization have increased the risk of flood disasters in regions. Flood resilience assessment is the foundation for building regional resilience. Addressing issues of efficiency and accuracy in high-dimensional, small-sample context found in existing assessment mode...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2024-12-01
|
| Series: | Ecological Indicators |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1470160X2401358X |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1846121313888894976 |
|---|---|
| author | Guofeng Wen Fayan Ji |
| author_facet | Guofeng Wen Fayan Ji |
| author_sort | Guofeng Wen |
| collection | DOAJ |
| description | Global climate change and rapid urbanization have increased the risk of flood disasters in regions. Flood resilience assessment is the foundation for building regional resilience. Addressing issues of efficiency and accuracy in high-dimensional, small-sample context found in existing assessment models, this study proposes a regional flood resilience assessment integrated model. Firstly, an indicator system is established through the process of “data collection-indicator extraction -opinion solicitation-indicator confirmation”, focusing on dimensions of robustness, redundancy, resourcefulness, and rapidity. Secondly, the combined indicator weights are determined using quadratic programming combined with the EWM-Delphi method. Finally, based on the obtained weights, learning samples are generated using piecewise linear interpolation and the TOPSIS. Training samples are then input into the Butterfly Optimization Algorithm(BOA) to optimize the key parameters in the Random Forest(RF). The performance of optimized RF is evaluated using test samples. Therefore, the TOPSIS-BOA-RF integrated model is constructed. Taking the Shandong Peninsula Urban Agglomeration as an example, the integrated model is used to analyze the flood resilience in 16 cities under the jurisdiction of the region from 2003 to 2022. The results indicate that as of 2022, Jinan, Qingdao, and Zibo have reached a high resilience, while Yantai, Weihai, Weifang, Rizhao, Dongying, and Binzhou are rated higher. In contrast, Zaozhuang, Taian, Dezhou, Jining, Linyi, Liaocheng, and Heze exhibit moderate resilience, which is lower than that of other cities. From 2003 to 2022, the Shandong Peninsula Urban Agglomeration has significantly improved in flood resilience, showing a decreasing trend from northeast to southwest. Comparative analysis shows that results of the constructed model are consistent with reality and perform better than other models. Suggestions for enhancing regional resilience, such as construction of regional rescue centers and improvement of economic circle resilience, are proposed. |
| format | Article |
| id | doaj-art-4f0d4b200baf495e9e5696b97f46348a |
| institution | Kabale University |
| issn | 1470-160X |
| language | English |
| publishDate | 2024-12-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Ecological Indicators |
| spelling | doaj-art-4f0d4b200baf495e9e5696b97f46348a2024-12-16T05:35:26ZengElsevierEcological Indicators1470-160X2024-12-01169112901Flood resilience assessment of region based on TOPSIS-BOA-RF integrated modelGuofeng Wen0Fayan Ji1School of Management Science and Engineering, Shandong Technology and Business University, No. 191, Binhai Middle Road, Laishan District, Yantai, 264005, Shandong, ChinaCorresponding author.; School of Management Science and Engineering, Shandong Technology and Business University, No. 191, Binhai Middle Road, Laishan District, Yantai, 264005, Shandong, ChinaGlobal climate change and rapid urbanization have increased the risk of flood disasters in regions. Flood resilience assessment is the foundation for building regional resilience. Addressing issues of efficiency and accuracy in high-dimensional, small-sample context found in existing assessment models, this study proposes a regional flood resilience assessment integrated model. Firstly, an indicator system is established through the process of “data collection-indicator extraction -opinion solicitation-indicator confirmation”, focusing on dimensions of robustness, redundancy, resourcefulness, and rapidity. Secondly, the combined indicator weights are determined using quadratic programming combined with the EWM-Delphi method. Finally, based on the obtained weights, learning samples are generated using piecewise linear interpolation and the TOPSIS. Training samples are then input into the Butterfly Optimization Algorithm(BOA) to optimize the key parameters in the Random Forest(RF). The performance of optimized RF is evaluated using test samples. Therefore, the TOPSIS-BOA-RF integrated model is constructed. Taking the Shandong Peninsula Urban Agglomeration as an example, the integrated model is used to analyze the flood resilience in 16 cities under the jurisdiction of the region from 2003 to 2022. The results indicate that as of 2022, Jinan, Qingdao, and Zibo have reached a high resilience, while Yantai, Weihai, Weifang, Rizhao, Dongying, and Binzhou are rated higher. In contrast, Zaozhuang, Taian, Dezhou, Jining, Linyi, Liaocheng, and Heze exhibit moderate resilience, which is lower than that of other cities. From 2003 to 2022, the Shandong Peninsula Urban Agglomeration has significantly improved in flood resilience, showing a decreasing trend from northeast to southwest. Comparative analysis shows that results of the constructed model are consistent with reality and perform better than other models. Suggestions for enhancing regional resilience, such as construction of regional rescue centers and improvement of economic circle resilience, are proposed.http://www.sciencedirect.com/science/article/pii/S1470160X2401358XRegionFlood resilienceIntegrated modelTOPSIS-BOA-RF |
| spellingShingle | Guofeng Wen Fayan Ji Flood resilience assessment of region based on TOPSIS-BOA-RF integrated model Ecological Indicators Region Flood resilience Integrated model TOPSIS-BOA-RF |
| title | Flood resilience assessment of region based on TOPSIS-BOA-RF integrated model |
| title_full | Flood resilience assessment of region based on TOPSIS-BOA-RF integrated model |
| title_fullStr | Flood resilience assessment of region based on TOPSIS-BOA-RF integrated model |
| title_full_unstemmed | Flood resilience assessment of region based on TOPSIS-BOA-RF integrated model |
| title_short | Flood resilience assessment of region based on TOPSIS-BOA-RF integrated model |
| title_sort | flood resilience assessment of region based on topsis boa rf integrated model |
| topic | Region Flood resilience Integrated model TOPSIS-BOA-RF |
| url | http://www.sciencedirect.com/science/article/pii/S1470160X2401358X |
| work_keys_str_mv | AT guofengwen floodresilienceassessmentofregionbasedontopsisboarfintegratedmodel AT fayanji floodresilienceassessmentofregionbasedontopsisboarfintegratedmodel |