Abstract
To evaluate the performances of regression models applied in the urban flash flood risk assessment, the historical urban flash flood occurrences points were used to build the Voronoi polygon networks for calculating Ripley’s K values which can be adopted to be the risk value and the predictands in regression. The first level risk indicators of hazard, vulnerability, sensitivity and exposure risk factors in the risk assessment, as well as the sensitivity subordinate indicators of imperviousness and terrain factor, were listed to be the predictors in the regression model. Subsequently, methods of the linear regression equation (LRE), nonlinear regression power-form function (PF) and a simplified power-form function (SPF), as well as support vector machine (SVM) model and random forests (RF) model, were all nominated for the performance evaluation and comparison of the fitness of their regression relationships between the predictors and the predictands. With the support of samples, the benchmarking firstly demonstrated the SPF is the best of the regression equation; but the full PF equation cannot be figured out on account of the sample data deficiency. The SVM model behaves better than the regression equations of SPE and LRE, while the SVM of nonlinear polynomial kernel function is slightly better than that of the nonlinear Gaussian kernel function. Above all, the RF model performed perfectly in the regression fitting, which the relative bias index is − 0.009 and the relative mean squared error is 0.0773. Meanwhile, it mostly resolves the problems of overfitting, outliers and noise in regression. The variable importance (VI) evaluated by the RF model indicated that the top four important risk factors are the imperviousness, terrain factor, vulnerability, and exposure factor, which the VI index value is 0.38, 0.16, 0.11 and 0.1, respectively. Unexpectedly, the hazard factor appears to be the least important factor with a VI value of 0.04. The homogeneity of invariable hazard being preserved in regional climate background makes the hazard a minor role in risk contribution. The model performance evaluation demonstrated the artificial intelligence RF model should be recommended to be the common-use model for aftermath meteorology-related risk assessment. On the other hand, the VI analysis tools of RF were also recognized to be a welcome toolbox items for the risk analysis.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Braud I, Ayral P-A, Bouvier C, Branger F, Delrieu G (2014) Multi-scale hydrometeorological observation and modelling for flash flood understanding. Hydrol Earth Syst Sci 18:3733–3761. https://doi.org/10.5194/hess-18-3733-2014
Breiman L (2001) Random Forests. Machine Learn 45:5-32
Breiman L, Cutler A (2022) Random Forests, available at: https://www.stat.berkeley.edu/~breiman/RandomForests/cc_home.htm, last access: September 2022
Chen X, Ishwaran H (2012) Random forests for genomic data analysis. Genomics 99(6):323–329. https://doi.org/10.1016/j.ygeno.2012.04.003
Chen J, Chen J, Liao A, Cao X, Chen L, Chen X, He C, Han G, Peng S, Lu M, Zhang W, Tong X, Mills J (2014) Global land cover mapping at 30 resolution: a POK-based operational approach. ISPRS J Photogramm Remote Sens 103:7–27
Cloke HL, Pappenberger F (2009) Ensemble flood forecasting: a review. J Hydrol 375:613–626. https://doi.org/10.1016/j.jhydrol.2009.06.005
Corral C, Berenguer M, Sempere-Torres D, Poletti L, Silvestro F, Rebora N (2019) Comparison of two early warning systems for regional flash flood hazard forecasting. J Hydrol 572:603–619. https://doi.org/10.1016/j.jhydrol.2019.03.026
CRED and UNISDR: the human cost of weather related disasters –1995–2015, United Nations Office for Disaster Risk Reduction (UNISDR) and Centre for Research on the Epidemiology of Disasters (CRED), 2015
Desai S, Ouarda TB (2021) Regional hydrological frequency analysis at ungauged sites with random forest regression. J Hydrol 594:125861. https://doi.org/10.1016/j.jhydrol.2020.125861
Fan RE, Chen PH, Lin CJ (2006) A study on SMO-type decomposition methods for support vector machines. IEEE Trans Neural Netw 17:893–908
Fernández DS, Lutz MA (2010) Urban flood hazard zoning in Tucumán Province, Argentina, using GIS and multicriteria decision analysis. Eng Geol 111(1–4):90–98
Fernández-Montblanc T, Vousdoukas MI, Ciavola P, Voukouvalas E, Mentaschi L, Breyiannis G, Feyen L, Salamon P (2019) Towards robust pan-European storm surge forecasting. Ocean Model 133:129–144. https://doi.org/10.1016/j.ocemod.2018.12.001
Garmdareh ES, Vafakhah M, Eslamian SS (2018) Regional flood frequency analysis using support vector regression in arid and semi-arid regions of Iran. Hydrolog Sci J 63:426–440. https://doi.org/10.1080/02626667.2018.1432056
Gong Z, Forrest JY-L (2014) Special issue on meteorological disaster risk analysis and assessment: on basis of grey systems theory. Nat Hazards 71(2):995–1000. https://doi.org/10.1007/s11069-013-0864-y
Hapuarachchi HAP, Wang QJ, Pagano TC (2011) A review of advances in flash flood forecasting. Hydrol Process 25:2771–2784. https://doi.org/10.1002/hyp.8040
Henonin J, Russo B, Mark O, Gourbesville P (2013) Real-time urban flood forecasting and modelling—a state of the art. J Hydroinform 15:717–736. https://doi.org/10.2166/hydro.2013.132
Hu HB (2016) Rainstorm flash flood risk assessment using genetic programming: a case study of risk zoning in Beijing[J]. Natural Hazards: J Int Soc Prevent Mitigation Nat Hazards 83(1):485–500
Hu HB, Xuan C, Zhu L (2013) The pre-event risk assessment of Beijing urban flood. J Appl Meteor Sci 24(1):99–108
Hu Z, Zhang X, Cui J et al (2021) A survey-based analysis of the public’s willingness for disaster relief in China. Nat Hazards 107:2205–2225. https://doi.org/10.1007/s11069-021-04538-7
IPCC (2007) Climate change 2007: synthesis report. Contribution of working groups I, II and III to the fourth assessment report of the intergovernmental panel on climate change. In: Pachauri RK and Reisinger A (eds.) Geneva, Switzerland. p 104
Jain SK, Mani P, Jain SK, Prakash P, Singh VP, Tullos D, Kumar S, Agarwal SP, Dimri AP (2018) A brief review of flood forecasting techniques and their applications. Int J River Basin Manage 16:329–344. https://doi.org/10.1080/15715124.2017.1411920
Kohno N, Dube SK, Entel M, Fakhruddin S, Greenslade D, Leroux M-D, Rhome J, Thuy NB (2018) Recent progress in storm surge forecasting. Tropical Cyclone Res Rev 7:128–139. https://doi.org/10.6057/2018TCRR02.04
Láng-Ritter J, Berenguer M, Dottori F et al (2021) Compound flood impact forecasting: integrating fluvial and flash flood impact assessments into a unified system. Hydrol Earth Syst Sci 26:689–709. https://doi.org/10.5194/hess-26-689-2022
Maqsood I, Huang GH (2012) A dual two-stage stochastic model for flood management with inexact-integer analysis under multiple uncertainties. Stoch Env Res Risk Assess 27(3):643–657. https://doi.org/10.1007/s00477-012-0629-2
McGovern A, Lagerquist R, Gagne DJ, Jergensen GE, Elmore KL, Homeyer CR, Smith T (2019) Making the black box more transparent: Understanding the physical implications of machine learning. Bull Amer Meteor Soc 100, 2175–2199. https://doi.org/10.1175/BAMS-D-18-0195.1
Meyer V, Scheuer S, Haase D (2009) A multicriteria approach for flood risk mapping exemplified at the Mulde River. Germany Natural Hazards 48(1):17–39
Munich Re: Flood risk: underestimated natural hazards, available at: https://www.munichre.com/en/risks/natural-disasters-losses-are-trending-upwards/ floods-and-flash-floods-underestimated-natural-hazards.html (last access: 2 February 2022), 2020.
Ni JR, Xue A (2003) Application of artificial neural network to the rapid feedback of potential ecological risk in flood diversion zone. Eng Appl Artif Intell 16(2):105–119
Ogden FL, Sharif HO, Senarath SUS, Smith JA, Baeck ML, Richardson JR (2000) Hydrometeorological analysis of the Fort Collins, Colorado, flash flood of 1997. J Hydrol 228:82–100. https://doi.org/10.1016/S0022-1694(00)00146-3
Rucinska D (2015) Spatial distribution of flood risk and quality of spatial management: case study in Odra Valley, Poland. Risk Anal 35:241–251. https://doi.org/10.1111/risa.12295
Schumacher RS, Hill AJ, Klein M, Nelson JA, Erickson MJ, Tronjniak SM, Herman GR (2021) From Random Forests to Flood Forecasts: A Research to Operations Success Story. Abstr Bullet Amer Meteorol Soc 102(9) E1742-E1755. https://doi.org/10.1175/BAMS-D-20-0186.1
Shepherd M, Mote T, Dowd J, Roden M, Knox P, McCutcheon SC, Nelson SE (2011) An overview of synoptic and mesoscale factors contributing to the disastrous Atlanta Flood of 2009. Bull Amer Meteor Soc 92(7):861–870. https://doi.org/10.1175/2010BAMS3003.1
Shi P, Wang M, Fang W (2023) comprehensive natural hazards and disaster risk survey achievements supporting spatial land planning. China Journal of Disaster Reduction 9:14–15 ((in Chinese))
Smith K (1996) Environmental hazards: assessing risk and reducing disaster. Routledge, New York
Smith JA, Baeck ML, Morrison JE et al (2002) The regional hydrology of extreme floods in an urbanizing drainage basin. J Hydrometeorol 3(3):267–282
Smith JA, Miller AJ, Baeck ML et al (2005) Extraordinary flood response of a small urban watershed to short- duration convective rainfall. J Hydrometeorol 6(5):599–617
Smith A, Sampson C, Bates P (2015) Regional flood frequency analysis at the global scale, Water Resour. Res 51:539–553. https://doi.org/10.1002/2014wr015814
Stefanidis S, Stathis D (2013) Assessment of flood hazard based on natural and anthropogenic factors using analytic hierarchy process (AHP). Nat Hazards 68:569–585
Stevens MR, Song Y, Berke PR (2010) New Urbanist developments in flood-prone areas: safe development, or safe development paradox? Nat Hazards 53:605–629. https://doi.org/10.1007/s11069-009-9450-8
Su Y, Zhao F, Tan L (2015) Whether a large disaster could change public concern and risk perception: a case study of the 7/21 extraordinary rainstorm disaster in Beijing in 2012. Nat Hazards 78:555–567. https://doi.org/10.1007/s11069-015-1730-x
Trigg MA, Birch CE, Neal JC, Bates PD, Smith A, Sampson CC, Yamazaki D, Hirabayashi Y, Pappenberger F, Dutra E, Ward PJ, Winsemius HC, Salamon P, Dot-tori F, Rudari R, Kappes MS, Simpson AL, Hadzilacos G, Fewtrell TJ (2016) The credibility challenge for global fluvial flood risk analysis. Environ Res Lett 11:094014. https://doi.org/10.1088/1748-9326/11/9/094014
Wang J, Liang Z, Hu Y, Wang D (2015a) Modified weighted function method with the incorporation of historical floods into systematic sample for parameter estimation of Pearson type three distribution. J Hydrol 527:958–966
Wang Z, Lai C, Chen X, Yang B, Zhao S, Bai X (2015b) Flood hazard risk assessment model based on random forest. J Hydrol 527:1130–1141. https://doi.org/10.1016/j.jhydrol.2015.06.008
Wang X, Lu Z, Wang L, Jiang W, Ma G (2016) Simplified assessment method and application research of rainstorm disaster risk and impact—Using Jing Jin Ji “7.21” Heavy rain as an example. Meteor Mon 42(2):213–220
Yang XL, Ding JH, Hou H (2013) Application of a triangular fuzzy AHP approach for flood risk evaluation and response measures analysis. Nat Hazards 68:657–674
Yeh CC, Chi DJ, Lin YR (2014) Going-concern prediction using hybrid random forests and rough set approach. Inf Sci 254:98–110
Zanchetta AD, Coulibaly P (2020) Recent advances in real-time pluvial flash flood forecasting. Water 12:570. https://doi.org/10.3390/w12020570
Zhao G, Bates P, Neal J, Pang B (2021) Design flood estimation for global river networks based. Hydrol Earth Syst Sci 25:5981–5999. https://doi.org/10.5194/hess-25-5981-2021
Zhou Q, Teng S, Situ Z, Liao X, Feng J, Chen G, Zhang J, Lu Z (2023) A deep-learning-technique-based data-driven model for accurate and rapid flood predictions in temporal and spatial dimensions. Hydrol Earth Syst Sci 27: 1791-1808. https://doi.org/10.5194/hess-27-1791-2023
Acknowledgements
This study has been supported by the Open Grants of the State Key Laboratory of Severe Weather (2021LASW-A18) and Natural Science Foundation of Beijing Municipality (8222018).
Funding
This work of survey was supported and funded by the Open Grants of the State Key Laboratory of Severe Weather (2021LASW-A18) and Natural Science Foundation of Beijing Municipality (8222018).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors have not disclosed any competing interests.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Hu, H., Yu, M., Zhang, X. et al. Performance benchmarking on several regression models applied in urban flash flood risk assessment. Nat Hazards 120, 3487–3504 (2024). https://doi.org/10.1007/s11069-023-06341-y
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11069-023-06341-y