Machine learning and SHAP-based susceptibility assessment of storm flood in rapidly urbanizing areas: a case study of Shenzhen, China

References

• Benito G, Lang M, Barriendos M, Llasat MC, Frances F, Ouarda T, Thorndycraft VR, Enzel Y, Bardossy A, Coeur D, et al. 2004. Use of systematic, palaeoflood and historical data for the improvement of flood risk estimation. Review of scientific methods. Nat Hazards. 31(3):623–643. doi: 10.1023/B:NHAZ.0000024895.48463.eb.
   Web of Science ®Google Scholar
• Bergstra J, Bengio Y. 2012. Random search for hyper-parameter optimization. J Mach Learn Res. 13(1):281–305.
   Google Scholar
• Breiman L. 2001. Random forests. Mach Learn. 45(1):5–32.), doi: 10.1023/A:1010933404324.
   Web of Science ®Google Scholar
• Budholiya K, Shrivastava SK, Sharma V. 2022. An optimized xgboost based diagnostic system for effective prediction of heart disease. J King Saud Univ - Comput Inform Sci. 34(7):4514–4523. doi: 10.1016/j.jksuci.2020.10.013.
   Web of Science ®Google Scholar
• Chang I, Park H, Hong E, Lee J, Kwon N. 2022. Predicting effects of built environment on fatal pedestrian accidents at location-specific level: application of xgboost and shap. Accid Anal Prev. 166:106545. doi: 10.1016/j.aap.2021.106545.
   PubMed Web of Science ®Google Scholar
• Chen D, Zhang F, Zhang M, Meng Q, Jim CY, Shi J, Tan ML, Ma X. 2022. Landscape and vegetation traits of urban green space can predict local surface temperature. Sci Total Environ. 825:154006. 10.1016/j.scitotenv.2022.154006.
   PubMed Web of Science ®Google Scholar
• Chen TQ, Guestrin C, Assoc CM. 2016. Xgboost: a scalable tree boosting system. Proceeding of the 22nd acm sigkdd International Conference on Knowledge Discovery and Data Mining, 785 – 794. doi: 10.1145/2939672.2939785.
   Google Scholar
• Chen W, Hong H, Li S, Shahabi H, Wang Y, Wang X, Ahmad BB. 2019. Flood susceptibility modelling using novel hybrid approach of reduced-error pruning trees with bagging and random subspace ensembles. J Hydrol (Amst). 575:864–873. doi: 10.1016/j.jhydrol.2019.05.089.
   Web of Science ®Google Scholar
• Cheng T, Xu Z, Hong S, Song S. 2017. Flood risk zoning by using 2d hydrodynamic modeling: a case study in Jinan City. Math Probl Eng. 2017:1–8. doi: 10.1155/2017/5659197.
   Web of Science ®Google Scholar
• Bisht DS, Chatterjee C, Kalakoti S, Upadhyay P, Sahoo M, Panda A., 2016. Modeling urban floods and drainage using SWMM and MIKE URBAN: a case study. Nat Hazards. 84(2):749–776. doi: 10.1007/s11069-016-2455-1.
   Web of Science ®Google Scholar
• Du S, Van Rompaey A, Shi P, Wang JA. 2015. A dual effect of urban expansion on flood risk in the Pearl River Delta (China) revealed by land-use scenarios and direct runoff simulation. Nat Hazards. 77(1):111–128. doi: 10.1007/s11069-014-1583-8.
   Web of Science ®Google Scholar
• Felder G, Zischg A, Weingartner R. 2017. The effect of coupling hydrologic and hydrodynamic models on probable maximum flood estimation. J Hydrol. 550:157–165. doi: 10.1016/j.jhydrol.2017.04.052.
   Web of Science ®Google Scholar
• Hawker L, Uhe P, Paulo L, Sosa J, Savage J, Sampson C, Neal J. 2022. A 30 m global map of elevation with forests and buildings removed. Environ Res Lett. 17(2):024016. doi: 10.1088/1748-9326/ac4d4f.
   Web of Science ®Google Scholar
• He Q, Shahabi H, Shirzadi A, Li S, Chen W, Wang N, Chai H, Bian H, Ma J, Chen Y, et al. 2019. Landslide spatial modelling using novel bivariate statistical based Naïve Bayes, RBF classifier, and RBF network machine learning algorithms. Sci Total Environ. 663:1–15. doi: 10.1016/j.scitotenv.2019.01.329.
   PubMed Web of Science ®Google Scholar
• Hénonin J, Hongtao M, Zheng-Yu Y, Hartnack J, Havnø K, Gourbesville P, Mark O., 2015. Citywide multi-grid urban flood modelling: the July 2012 flood in Beijing. Urban Water J. 12(1):52–66. doi: 10.1080/1573062X.2013.851710.
   Web of Science ®Google Scholar
• Jaafari A, Zenner EK, Pham BT. 2018. Wildfire spatial pattern analysis in the Zagros mountains, Iran: a comparative study of decision tree based classifiers. Ecol Inform. 43:200–211. doi: 10.1016/j.ecoinf.2017.12.006.
   Web of Science ®Google Scholar
• Jang E, Kim YJ, Im J, Park Y, Sung T. 2022. Global sea surface salinity via the synergistic use of SMAP satellite and HYCOM data based on machine learning. Remote Sens Environ. 273:112980. doi: 10.1016/j.rse.2022.112980.
   Web of Science ®Google Scholar
• Jenson K, Domingue O. 1988. Extracting topographic structure from digital elevation data for geographic system analysis. Pe. & RS. 54(11)
   Web of Science ®Google Scholar
• Jiang W, Deng L, Chen L, Wu J, Li J. 2009. Risk assessment and validation of flood disaster based on fuzzy mathematics. Prog Nat Sci. 19(10):1419–1425. doi: 10.1016/j.pnsc.2008.12.010.
   Web of Science ®Google Scholar
• Li Q, Jiang X, Liu D. 2013. Analysis and modelling of flood risk assessment using information diffusion and artificial neural network. WSA. 39(5):643–648. doi: 10.4314/wsa.v39i5.8.
   Web of Science ®Google Scholar
• Li R, Cui L, Fu H, Meng Y, Li J, Guo J. 2020. Estimating high-resolution PM1 concentration from Himawari-8 combining extreme gradient boosting-geographically and temporally weighted regression (XGBoost-GTWR). Atmos Environ. 229 (1994):117434. doi: 10.1016/j.atmosenv.2020.117434.
   Google Scholar
• Li S, Fan Z. 2022. Evaluation of urban green space landscape planning scheme based on pso-bp neural network model. Alex Eng J. 61(9):7141–7153. doi: 10.1016/j.aej.2021.12.057.
   Web of Science ®Google Scholar
• Liang ZC, Zhao YL, Fu YC. 2017. Optimization of spatial pattern of urban imperviousness based on the integration of scs-cn hydrological model and the ant colony algorithm. J Geo-Inform Sci. 19(10):1315–1326.
   Google Scholar
• Liu X, Zhu X, Zhang Q, Yang T, Pan Y, Sun P. 2020. A remote sensing and artificial neural network-based integrated agricultural drought index: index development and applications. Catena (Amst). 186:104394. doi: 10.1016/j.catena.2019.104394.
   Web of Science ®Google Scholar
• Liu H. 2022. Optimal selection of control parameters for automatic machining based on bp neural network. Energy Rep. 8:7016–7024. doi: 10.1016/j.egyr.2022.05.038.
   Web of Science ®Google Scholar
• Liu WD, Tang ZP, Xia Y, Han MY, Jiang WB. 2019. Identifying the key factors influencing chinese carbon intensity using machine learning, the random forest algorithm, and evolutionary analysis. Acta Geogr Sin. 74(12):2592–2603.
   Google Scholar
• Lu W. 2022. Machine learning formula derivation and code implementation. People’s posts and telecommunications Press, Beijing.
   Google Scholar
• Lundberg SM, Lee SI. 2017. A unified approach to interpreting model predictions . Advances in neural information processing systems 30 (NIPS 2017), Long Beach, CA, USA, Curran Associates Inc. pp . 4768–4777.
   Google Scholar
• Luo K, Zhang X. 2022. Increasing urban flood risk in China over recent 40 years induced by lucc. Landsc Urban Plan. 219:104317. doi: 10.1016/j.landurbplan.2021.104317.
   Web of Science ®Google Scholar
• Ma M, Zhao G, He B, Li Q, Dong H, Wang S, Wang Z. 2021. Xgboost-based method for flash flood risk assessment. J Hydrol (Amst). 598:126382. doi: 10.1016/j.jhydrol.2021.126382.
   Web of Science ®Google Scholar
• Marjanović M, Kovačević M, Bajat B, Voženílek V. 2011. Landslide susceptibility assessment using SVM machine learning algorithm. Eng Geol. 123(3):225–234. doi: 10.1016/j.enggeo.2011.09.006.
   Web of Science ®Google Scholar
• Qian Y, Wang H, Wu J. 2021. Protecting existing urban green space versus cultivating more green infrastructures: strategies choices to alleviate urban waterlogging risks in Shenzhen. Remote Sens (Basel). 13(21):4433. doi: 10.3390/rs13214433.
   Web of Science ®Google Scholar
• Rui XF, Jiang CY, Chen QJ, Ding XY. 2015. Principle analysis and application of storm water management model on stimulating rainfall-runoff. Adv Sci Technol Water Res. 4(35):1–5.
   Google Scholar
• Smith MB. 1993. A GIS‐based distributed parameter hydrologic model for urban areas. Hydrol Process. 7(1):45–61. doi: 10.1002/hyp.3360070106.
   Web of Science ®Google Scholar
• Su BN, Huang H, Zhang N. 2015. Dynamic urban waterlogging risk assessment method based on scenario simulations. J Tsinghua Univ (Sci Technol). 55(06):684–690.
   Google Scholar
• Tang X, Hong H, Shu Y, Tang H, Li J, Liu W. 2019. Urban waterlogging susceptibility assessment based on a pso-svm method using a novel repeatedly random sampling idea to select negative samples. J Hydrol (Amst). 576:583–595. doi: 10.1016/j.jhydrol.2019.06.058.
   Web of Science ®Google Scholar
• Tang X, Shu Y, Lian Y, Zhao Y, Fu Y. 2018. A spatial assessment of urban waterlogging risk based on a weighted Naïve Bayes classifier. Sci Total Environ. 630:264–274. doi: 10.1016/j.scitotenv.2018.02.172.
   PubMed Web of Science ®Google Scholar
• Tan Y, Cheng Q, Lyu F, Liu F, Liu L, Su Y, Yuan S, Xiao W, Liu Z, Chen Y. 2024. Hydrological reduction and control effect evaluation of sponge city construction based on one-way coupling model of SWMM-FVCOM: a case in university campus. J Environ Manage. 349:119599. 10.1016/j.jenvman.2023.119599.
   PubMed Web of Science ®Google Scholar
• Tingsanchali T, Karim F. 2010. Flood-hazard assessment and risk-based zoning of a tropical flood plain: case study of the Yom River, Thailand. Hydrol Sci J/J Des Sci Hydrol. 55(2):145–161. doi: 10.1080/02626660903545987.
   Web of Science ®Google Scholar
• Vega García M, Aznarte JL. 2020. Shapley additive explanations for no2 forecasting. Ecol Inform. 56:101039. doi: 10.1016/j.ecoinf.2019.101039.
   Web of Science ®Google Scholar
• Wang WW, Wang Q, Lin H, Gong JD, Zhang SW. 2015. Summarization and prospection for the studies on China’s urban waterlogging. Urban Problems. (10), :24–28.
   Google Scholar
• Wang Z, Lai C, Chen X, Yang B, Zhao S, Bai X. 2015. Flood hazard risk assessment model based on random forest. J Hydrol (Amst). 527:1130–1141. doi: 10.1016/j.jhydrol.2015.06.008.
   Web of Science ®Google Scholar
• Woznicki SA, Baynes J, Panlasigui S, Mehaffey M, Neale A. 2019. Development of a spatially complete floodplain map of the conterminous United States using random forest. Sci Total Environ. 647:942–953. doi: 10.1016/j.scitotenv.2018.07.353.
   PubMed Web of Science ®Google Scholar
• Wu JS, Zhang PH. 2017. The effect of urban landscape pattern on urban waterlogging. Geogr Sin. 72(03):444–456.
   Google Scholar
• Xiao XW, Shen XY, Ke CQ, Zhou XH. 2020. Comparison of machine learning algorithms based on sentinel-1a data to detect icebergs. Acta Geod Cartogr Sin. 49(04):509–521.
   Google Scholar
• Xu Y, Zhen JN, Jiang XP, Wang JJ. 2021. Mangrove species classification with UAV-based remote sensing data and xgboost. Natl Remote Sen Bull. 25(3):737–752. doi: 10.11834/jrs.20210281.
   Google Scholar
• Yang LY, Chen YB. 2021. Information extraction and analysis on temporal and spatial pattern changes of surfaces impervious to water in Shenzhen City during 1979-2020. Bull Soil Water Conserv. 41(05):198–205.
   Google Scholar
• Yang XL, Ding JH, Hou H. 2013. Application of a triangular fuzzy ahp approach for flood risk evaluation and response measures analysis. Nat Hazards. 68(2):657–674. doi: 10.1007/s11069-013-0642-x.
   Web of Science ®Google Scholar
• Ye C, Xu Z, Lei X, Chen Y, Ding X, Liang Y. 2023. Flood simulation and risk analysis on urban block scale based on swmm and infoworks icm. Water Resources Protection. 39(02):87–94.
   Google Scholar
• Zhang L, Wang LL, Zhang XD, Liu SR, Sun PS, Wang TQ. 2014. The basic principle of random forest and its applications in ecology: a case study of Pinus yunnanensis. Acta Ecol Sin. 34(03):650–659.
   Google Scholar
• Zhang Q, Wu Z, Zhang H, Dalla Fontana G, Tarolli P. 2020. Identifying dominant factors of waterlogging events in metropolitan coastal cities: the case study of guangzhou, china. J Environ Manage. 271:110951. doi: 10.1016/j.jenvman.2020.110951.
   PubMed Web of Science ®Google Scholar
• Zhao G, Pang B, Xu Z, Peng D, Xu L. 2019. Assessment of urban flood susceptibility using semi-supervised machine learning model. Sci Total Environ. 659:940–949. doi: 10.1016/j.scitotenv.2018.12.217.
   PubMed Web of Science ®Google Scholar
• Zou Q, Zhou J, Zhou C, Song L, Guo J. 2013. Comprehensive flood risk assessment based on set pair analysis-variable fuzzy sets model and fuzzy AHP. Stoch Environ Res Risk Assess. 27(2):525–546. doi: 10.1007/s00477-012-0598-5.
   Web of Science ®Google Scholar