Predicting Road Flooding Risk with Machine Learning Approaches Using Crowdsourced Reports and Fine-grained Traffic Data

The objective of this study is to predict road flooding risks based on topographic, hydrologic, and temporal precipitation features using machine learning models. Predictive flood monitoring of road network flooding status plays an essential role in community hazard mitigation, preparedness, and response activities. Existing studies related to the estimation of road inundations either lack observed road inundation data for model validations or focus mainly on road inundation exposure assessment based on flood maps. This study addresses this limitation by using crowdsourced and fine-grained traffic data as an indicator of road inundation, and topographic, hydrologic, and temporal precipitation features as predictor variables. Two tree-based machine learning models (random forest and AdaBoost) were then tested and trained for predicting road inundations in the contexts of 2017 Hurricane Harvey and 2019 Tropical Storm Imelda in Harris County, Texas. The findings from Hurricane Harvey indicate that precipitation is the most important feature for predicting road inundation susceptibility, and that topographic features are more essential than hydrologic features for predicting road inundations in both storm cases. The random forest and AdaBoost models had relatively high AUC scores (0.860 and 0.810 for Harvey respectively and 0.790 and 0.720 for Imelda respectively) with the random forest model performing better in both cases. The random forest model showed stable performance for Harvey, while varying significantly for Imelda. This study advances the emerging field of smart flood resilience in terms of predictive flood risk mapping at the road level. For example, such models could help impacted communities and emergency management agencies develop better preparedness and response strategies with improved situational awareness of road inundation likelihood as an extreme weather event unfolds. ar X iv :2 10 8. 13 26 5v 1 [ ph ys ic s. so cph ] 3 0 A ug 2 02 1

[1]  H. Rodda,et al.  The Development and Application of a Flood Risk Model for the Czech Republic , 2005 .

[2]  B. Pradhan,et al.  Urban flood risk mapping using the GARP and QUEST models: A comparative study of machine learning techniques , 2019, Journal of Hydrology.

[3]  Nasir G. Gharaibeh,et al.  Automating the evaluation of urban roadside drainage systems using mobile lidar data , 2020, Comput. Environ. Urban Syst..

[4]  Samuel D. Brody,et al.  Characterizing urbanization impacts on floodplain through integrated land use, hydrologic, and hydraulic modeling , 2019, Journal of Hydrology.

[5]  Paul D. Bates,et al.  Evaluation of a coastal flood inundation model using hard and soft data , 2012, Environ. Model. Softw..

[6]  U. Naeem,et al.  Performance evaluation of 1-D numerical model HEC-RAS towards modeling sediment depositions and sediment flushing operations for the reservoirs , 2018, Environmental Monitoring and Assessment.

[7]  Hichem Sahli,et al.  Flood Inundation Mapping from Optical Satellite Images Using Spatiotemporal Context Learning and Modest AdaBoost , 2017, Remote. Sens..

[8]  Min Liu,et al.  Validating city-scale surface water flood modelling using crowd-sourced data , 2016 .

[9]  Jun Wang,et al.  Modeling the influence of urbanization on urban pluvial flooding: a scenario-based case study in Shanghai, China , 2017, Natural Hazards.

[10]  Kai Liu,et al.  Developing an effective 2-D urban flood inundation model for city emergency management based on cellular automata , 2014 .

[11]  Daniel G. Anderson.  Effects of urban development on floods in northern Virginia , 1970 .

[12]  V. Merwade,et al.  Effect of topographic data, geometric configuration and modeling approach on flood inundation mapping , 2009 .

[13]  L. Mao,et al.  Internet of people enabled framework for evaluating performance loss and resilience of urban critical infrastructures , 2021 .

[14]  Guoru Huang,et al.  Urban inundation response to rainstorm patterns with a coupled hydrodynamic model: A case study in Haidian Island, China , 2018, Journal of Hydrology.

[15]  Eve Gruntfest,et al.  Risk factors for driving into flooded roads , 2007 .

[16]  H. Thomas,et al.  An assessment of the impact of floodplain woodland on flood flows , 2007 .

[17]  Ana Deletic,et al.  A Cellular Automata Fast Flood Evaluation (CA‐ffé) Model , 2019, Water Resources Research.

[18]  Dragan Savic,et al.  The urban inundation model with bidirectional flow interaction between 2D overland surface and 1D se , 2007 .

[19]  Cheng Zhang,et al.  Disaster City Digital Twin: A vision for integrating artificial and human intelligence for disaster management , 2021, Int. J. Inf. Manag..

[20]  Lalit Kumar,et al.  A novel GIS-based ensemble technique for flood susceptibility mapping using evidential belief function and support vector machine: Brisbane, Australia , 2019, PeerJ.

[21]  J. Hou,et al.  Rapid forecasting of urban flood inundation using multiple machine learning models , 2021, Natural Hazards.

[22]  H. Pourghasemi,et al.  Identification of Critical Flood Prone Areas in Data-Scarce and Ungauged Regions: A Comparison of Three Data Mining Models , 2017, Water Resources Management.

[23]  Andy Liaw,et al.  Classification and Regression by randomForest , 2007 .

[24]  S. Brody,et al.  Estimating flood extent during Hurricane Harvey using maximum entropy to build a hazard distribution model , 2019, Journal of Flood Risk Management.

[25]  T. McPherson,et al.  Effect of land use-based surface roughness on hydrologic model output , 2010 .

[26]  Eric S. Blake,et al.  National Hurricane Center Tropical Cyclone Report: Hurricane Harvey (17 August - 1 September 2017) , 2018 .

[27]  Amir Mosavi,et al.  Integrated machine learning methods with resampling algorithms for flood susceptibility prediction. , 2019, The Science of the total environment.

[28]  Ali Mostafavi,et al.  Integrated infrastructure-plan analysis for resilience enhancement of post-hazards access to critical facilities , 2021 .

[29]  Amir Mosavi,et al.  Flash-flood hazard assessment using ensembles and Bayesian-based machine learning models: Application of the simulated annealing feature selection method. , 2019, The Science of the total environment.

[30]  M. D. White,et al.  The effects of watershed urbanization on the stream hydrology and riparian vegetation of Los Peñasquitos Creek, California , 2006 .

[31]  Ilan Kelman,et al.  An analysis of the causes and circumstances of flood disaster deaths. , 2005, Disasters.

[32]  A. Mostafavi,et al.  Unraveling the dynamic importance of county-level features in trajectory of COVID-19 , 2021, Scientific Reports.

[33]  Ali Mostafavi,et al.  Spatio-Temporal Graph Convolutional Networks for Road Network Inundation Status Prediction during Urban Flooding , 2021, Comput. Environ. Urban Syst..

[34]  Yan Liu,et al.  A CyberGIS Approach to Generating High-resolution Height Above Nearest Drainage (HAND) Raster for National Flood Mapping , 2016 .

[35]  B. Pham,et al.  Prediction Success of Machine Learning Methods for Flash Flood Susceptibility Mapping in the Tafresh Watershed, Iran , 2019, Sustainability.

[36]  Ali Mostafavi,et al.  Probabilistic modeling of cascading failure risk in interdependent channel and road networks in urban flooding , 2020 .

[37]  A. W. Western,et al.  An analysis of the influence of riparian vegetation on the propagation of flood waves , 2006, Environ. Model. Softw..

[38]  H. Lyu,et al.  Inundation analysis of metro systems with the storm water management model incorporated into a geographical information system: a case study in Shanghai , 2019, Hydrology and Earth System Sciences.

[39]  Zhu Qian,et al.  Without zoning: Urban development and land use controls in Houston , 2010 .

[40]  F. Jiguet,et al.  Selecting pseudo‐absences for species distribution models: how, where and how many? , 2012 .

[41]  P. Versini.  Use of radar rainfall estimates and forecasts to prevent flash flood in real time by using a road inundation warning system , 2012 .

[42]  Walter J. Rawls,et al.  Green‐ampt Infiltration Parameters from Soils Data , 1983 .

[43]  Robert E. Schapire,et al.  Explaining AdaBoost , 2013, Empirical Inference.

[44]  P. D. Batesa,et al.  A simple raster-based model for flood inundation simulation , 2000 .

[45]  R. Wilby,et al.  Modelling the impact of land subsidence on urban pluvial flooding: A case study of downtown Shanghai, China. , 2016, The Science of the total environment.

[46]  C. Arnold,et al.  IMPERVIOUS SURFACE COVERAGE: THE EMERGENCE OF A KEY ENVIRONMENTAL INDICATOR , 1996 .

[47]  David G. Tarboton,et al.  Terrain Analysis Enhancements to the Height Above Nearest Drainage Flood Inundation Mapping Method , 2019, Water Resources Research.

[48]  Chao Fan,et al.  A network percolation-based contagion model of flood propagation and recession in urban road networks , 2020, Scientific Reports.

[49]  C. Rennó,et al.  Height Above the Nearest Drainage – a hydrologically relevant new terrain model , 2011 .

[50]  S. Brody,et al.  Quantification of continuous flood hazard using random forest classification and flood insurance claims at large spatial scales: a pilot study in southeast Texas , 2021 .

[51]  Hyung-Sup Jung,et al.  Spatial prediction of flood susceptibility using random-forest and boosted-tree models in Seoul metropolitan city, Korea , 2017 .

[52]  Stuart J. Russell,et al.  Online bagging and boosting , 2005, 2005 IEEE International Conference on Systems, Man and Cybernetics.

[53]  Xiang-Yu Hou,et al.  Flood fatalities in contemporary Australia (1997–2008) , 2010, Emergency medicine Australasia : EMA.

[54]  Jie Yin,et al.  Evaluating the impact and risk of pluvial flash flood on intra-urban road network: A case study in the city center of Shanghai, China , 2016 .

[55]  Arnold Vedlitz,et al.  Institutional Connectedness in Resilience Planning and Management of Interdependent Infrastructure Systems , 2020 .

[56]  Enrico Zio,et al.  Network reliability analysis based on percolation theory , 2015, Reliab. Eng. Syst. Saf..

[57]  Christian Urich,et al.  A rapid urban flood inundation and damage assessment model , 2018, Journal of Hydrology.

[58]  V. R. Schneider,et al.  GUIDE FOR SELECTING MANNING'S ROUGHNESS COEFFICIENTS FOR NATURAL CHANNELS AND FLOOD PLAINS , 1989 .

[59]  D. Bae,et al.  Correcting mean areal precipitation forecasts to improve urban flooding predictions by using long short-term memory network , 2020 .

[60]  A. Prasad,et al.  Newer Classification and Regression Tree Techniques: Bagging and Random Forests for Ecological Prediction , 2006, Ecosystems.

[61]  Ali Mostafavi,et al.  An integrated physical-social analysis of disrupted access to critical facilities and community service-loss tolerance in urban flooding , 2020, Comput. Environ. Urban Syst..

[62]  Ali Mostafavi,et al.  Unraveling the Temporal Importance of Community-Scale Human Activity Features for Rapid Assessment of Flood Impacts , 2021, IEEE Access.

[63]  Terrence Fong,et al.  Automatic boosted flood mapping from satellite data , 2016, International journal of remote sensing.

[64]  Pijush Samui,et al.  A novel hybrid approach based on a swarm intelligence optimized extreme learning machine for flash flood susceptibility mapping , 2019, CATENA.

[65]  Faxi Yuan,et al.  Quantifying community resilience based on fluctuations in visits to points-of-interest derived from digital trace data , 2021, Journal of the Royal Society Interface.

[66]  C. Sutton.  Classification and Regression Trees, Bagging, and Boosting , 2005 .

[67]  Wesley E. Highfield,et al.  An Analysis of the Effects of Land Use and Land Cover on Flood Losses along the Gulf of Mexico Coast from 1999 to 2009 , 2015 .

[68]  Dapeng Yu,et al.  Beyond ‘flood hotspots’: Modelling emergency service accessibility during flooding in York, UK , 2017 .

[69]  Shangjia Dong,et al.  Bayesian modeling of flood control networks for failure cascade characterization and vulnerability assessment , 2019, Comput. Aided Civ. Infrastructure Eng..

[70]  R. Blessing,et al.  Disentangling the impacts of human and environmental change on catchment response during Hurricane Harvey , 2019, Environmental Research Letters.