Invited perspectives: How machine learning will change flood risk and impact assessment

Abstract. Increasing amounts of data, together with more computing power and better machine learning algorithms to analyse the data, are causing changes in almost every aspect of our lives. This trend is expected to continue as more data keep becoming available, computing power keeps improving and machine learning algorithms keep improving as well. Flood risk and impact assessments are also being influenced by this trend, particularly in areas such as the development of mitigation measures, emergency response preparation and flood recovery planning. Machine learning methods have the potential to improve accuracy as well as reduce calculating time and model development cost. It is expected that in the future more applications will become feasible and many process models and traditional observation methods will be replaced by machine learning. Examples of this include the use of machine learning on remote sensing data to estimate exposure and on social media data to improve flood response. Some improvements may require new data collection efforts, such as for the modelling of flood damages or defence failures. In other components, machine learning may not always be suitable or should be applied complementary to process models, for example in hydrodynamic applications. Overall, machine learning is likely to drastically improve future flood risk and impact assessments, but issues such as applicability, bias and ethics must be considered carefully to avoid misuse. This paper presents some of the current developments on the application of machine learning in this field and highlights some key needs and challenges.

[1]  Stephen Jarvis,et al.  Predicting floods with Flickr tags , 2017, PloS one.

[2]  L. Gnanappazham,et al.  Comparison of Urban Growth Modeling Using Deep Belief and Neural Network Based Cellular Automata Model—A Case Study of Chennai Metropolitan Area, Tamil Nadu, India , 2019, Journal of Geographic Information System.

[3]  Kwok-wing Chau,et al.  Flood Prediction Using Machine Learning Models: Literature Review , 2018, Water.

[4]  Bruno Merz,et al.  Multi-variate flood damage assessment: a tree-based data-mining approach , 2013 .

[5]  Laura Giurca Vasilescu,et al.  Disaster Management CYCLE – a theoretical approach , 2008 .

[6]  Wei You,et al.  Detecting the Boundaries of Urban Areas in India: A Dataset for Pixel-Based Image Classification in Google Earth Engine , 2016, Remote. Sens..

[7]  C. Cao,et al.  A study of waterborne diseases during flooding using Radarsat-2 imagery and a back propagation neural network algorithm , 2015 .

[8]  Bruno Merz,et al.  How useful are complex flood damage models? , 2014 .

[9]  Animesh K. Gain,et al.  Multi-Variate Analyses of Flood Loss in Can Tho City, Mekong Delta , 2015 .

[10]  Frieder. Andreas Perthes.  Carolus Fridericus Gauss Theoria motus corporum coelestium in sectionibus conicis solem ambientium , 1855 .

[11]  G. Mountrakis,et al.  Urban Growth Prediction: A Review of Computational Models and Human Perceptions , 2012 .

[12]  Leonardo Alfonso,et al.  Can assimilation of crowdsourced data in hydrological modelling improve flood prediction , 2017 .

[13]  Henry V. Burton,et al.  Replicating the Recovery following the 2014 South Napa Earthquake using Stochastic Process Models , 2018, Earthquake Spectra.

[14]  Mahmoud Reza Delavar,et al.  Urban Growth Modeling Using Cellular Automata with Multi-Temporal Remote Sensing Images Calibrated by the Artificial Bee Colony Optimization Algorithm , 2016, Sensors.

[15]  Marcello Restelli,et al.  Tree‐based reinforcement learning for optimal water reservoir operation , 2010 .

[16]  R. Muir-Wood,et al.  Flood risk and climate change: global and regional perspectives , 2014 .

[17]  B. Merz,et al.  Development of FLEMOcs – a new model for the estimation of flood losses in the commercial sector , 2010 .

[18]  J. Townshend,et al.  Characterizing the magnitude, timing and duration of urban growth from time series of Landsat-based estimates of impervious cover , 2016 .

[19]  Pieter van Gelder,et al.  Computational intelligence methods for the efficient reliability analysis of complex flood defence structures , 2011 .

[20]  Scott B. Miles,et al.  Integrating Performance-Based Engineering and Urban Simulation to Model Post-Earthquake Housing Recovery , 2018, Earthquake Spectra.

[21]  Heidi Kreibich,et al.  Development and assessment of uni- and multivariable flood loss models for Emilia-Romagna (Italy) , 2017, Natural Hazards and Earth System Sciences.

[22]  V. Klemas,et al.  Remote Sensing of Floods and Flood-Prone Areas: An Overview , 2015 .

[23]  Ioana Popescu,et al.  Citizen observations contributing to flood modelling: opportunities and challenges , 2017 .

[24]  S. Noble.  Algorithms of Oppression: How Search Engines Reinforce Racism , 2018 .

[25]  S. Jonkman,et al.  Developments in the management of flood defences and hydraulic infrastructure in the Netherlands , 2018 .

[26]  Cheryl A. Palm,et al.  Socioecologically informed use of remote sensing data to predict rural household poverty , 2019, Proceedings of the National Academy of Sciences.

[27]  A. C. Neves,et al.  Structural health monitoring of bridges: a model-free ANN-based approach to damage detection , 2017, Journal of Civil Structural Health Monitoring.

[28]  B. Merz,et al.  Development and evaluation of FLEMOps - a new Flood Loss Estimation MOdel for the private sector , 2008 .

[29]  Asaad Y. Shamseldin,et al.  Application of surrogate artificial intelligent models for real‐time flood routing , 2013 .

[30]  Fernando Nardi,et al.  Integrating VGI and 2D hydraulic models into a data assimilation framework for real time flood forecasting and mapping , 2019, Geo spatial Inf. Sci..

[31]  Bruno Merz,et al.  Review article "Assessment of economic flood damage" , 2010 .

[32]  K. M. de Bruijn,et al.  Uncertainty in flood damage estimates and its potential effect on investment decisions , 2015 .

[33]  J.A.E. Ten Veldhuis,et al.  Decision-tree analysis of factors influencing rainfall-related building structure and content damage , 2014 .

[34]  Valeria V. Krzhizhanovskaya,et al.  Machine learning methods for environmental monitoring and flood protection , 2011 .

[35]  Dimitri P. Solomatine,et al.  River flow forecasting using artificial neural networks , 2001 .

[36]  P. D. Heermann,et al.  Classification of multispectral remote sensing data using a back-propagation neural network , 1992, IEEE Trans. Geosci. Remote. Sens..

[37]  Peter Kontschieder,et al.  The Mapillary Vistas Dataset for Semantic Understanding of Street Scenes , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[38]  Robert C. Balling,et al.  Using Landsat and nighttime lights for supervised pixel-based image classification of urban land cover , 2018 .

[39]  Luke J. Prendergast,et al.  Structural Health Monitoring for Performance Assessment of Bridges under Flooding and Seismic Actions , 2018, Structural Engineering International.

[40]  Robert J. Abrahart,et al.  Neural network modelling of non-linear hydrological relationships , 2007 .

[41]  Wei-Yin Loh,et al.  Classification and regression trees , 2011, WIREs Data Mining Knowl. Discov..

[42]  Fabio Roli,et al.  Design of effective neural network ensembles for image classification purposes , 2001, Image Vis. Comput..

[43]  Geoffrey E. Hinton,et al.  Learning representations by back-propagating errors , 1986, Nature.

[44]  Suzana Dragicevic,et al.  Machine Learning Techniques for Modelling Short Term Land-Use Change , 2017, ISPRS Int. J. Geo Inf..

[45]  A. Keane,et al.  Evolutionary Optimization of Computationally Expensive Problems via Surrogate Modeling , 2003 .

[46]  Jeroen C. J. H. Aerts,et al.  Accounting for risk aversion, income distribution and social welfare in cost‐benefit analysis for flood risk management , 2017 .

[47]  Aydan Menderes,et al.  Automatic Detection of Damaged Buildings after Earthquake Hazard by Using Remote Sensing and Information Technologies , 2015 .

[48]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[49]  W.P.S. Dias,et al.  Evaluating adaptation measures for reducing flood risk: A case study in the city of Colombo, Sri Lanka , 2019, International Journal of Disaster Risk Reduction.

[50]  João Cardoso,et al.  Review and application of Artificial Neural Networks models in reliability analysis of steel structures , 2015 .

[51]  Dit-Yan Yeung,et al.  Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting , 2015, NIPS.

[52]  Emma M. Hill,et al.  Urban Flood Detection with Sentinel-1 Multi-Temporal Synthetic Aperture Radar (SAR) Observations in a Bayesian Framework: A Case Study for Hurricane Matthew , 2019, Remote. Sens..

[53]  S. Jonkman.  Global Perspectives on Loss of Human Life Caused by Floods , 2005 .

[54]  Anna Rita Scorzini,et al.  Testing empirical and synthetic flood damage models: the case of Italy , 2019, Natural Hazards and Earth System Sciences.

[55]  Arnejan van Loenen,et al.  Harvesting Social Media for Generation of Near Real-time Flood Maps☆ , 2016 .

[56]  Andreas Dengel,et al.  Multi-Task Learning for Segmentation of Building Footprints with Deep Neural Networks , 2017, 2019 IEEE International Conference on Image Processing (ICIP).

[57]  Bruno Merz,et al.  Probabilistic, Multivariable Flood Loss Modeling on the Mesoscale with BT‐FLEMO , 2017, Risk analysis : an official publication of the Society for Risk Analysis.

[58]  Mike Kama,et al.  Predictive risk mapping of an environmentally-driven infectious disease using spatial Bayesian networks: A case study of leptospirosis in Fiji , 2018, PLoS neglected tropical diseases.

[59]  Molly E. Brown,et al.  Environmental variability and child growth in Nepal. , 2015, Health & place.

[60]  Virginia E. Eubanks.  Automating Inequality: How High-Tech Tools Profile, Police, and Punish the Poor , 2018 .

[61]  Dimitri Solomatine,et al.  Comparative analysis of conceptual models with error correction, artificial neural networks and committee models , 2014 .

[62]  Dennis Wagenaar,et al.  Improved Transferability of Data‐Driven Damage Models Through Sample Selection Bias Correction , 2020, Risk analysis : an official publication of the Society for Risk Analysis.

[63]  Joost van de Weijer,et al.  Multi-modal Deep Learning Approach for Flood Detection , 2017, MediaEval.

[64]  T. Schweckendiek,et al.  Value of Information of Structural Health Monitoring in Asset Management of Flood Defences , 2019, Infrastructures.

[65]  Morgan G. Ames.  Deconstructing the algorithmic sublime , 2018, Big Data Soc..

[66]  Jeroen C. J. H. Aerts,et al.  Regional disaster impact analysis: comparing Input-Output and Computable General Equilibrium models , 2015 .

[67]  Heidi Kreibich,et al.  Social media as an information source for rapid flood inundation mapping , 2015 .

[68]  Robert Soden,et al.  Infrastructuring the Imaginary: How Sea-Level Rise Comes to Matter in the San Francisco Bay Area , 2019, CHI.

[69]  Avi Ostfeld,et al.  Data-driven modelling: some past experiences and new approaches , 2008 .

[70]  Li-Chiu Chang,et al.  Building ANN-Based Regional Multi-Step-Ahead Flood Inundation Forecast Models , 2018, Water.

[71]  B. Modu,et al.  Towards a Predictive Analytics-Based Intelligent Malaria Outbreak Warning System , 2017 .

[72]  Giovanni Coco,et al.  Simulation of urban expansion via integrating artificial neural network with Markov chain – cellular automata , 2019, Int. J. Geogr. Inf. Sci..

[73]  A. Thieken,et al.  Adaptability and transferability of flood loss functions in residential areas , 2013 .

[74]  Dimitri P. Solomatine,et al.  Machine learning in real-time control of water systems , 2002 .

[75]  B. Ligon.  Infectious diseases that pose specific challenges after natural disasters: a review. , 2006, Seminars in pediatric infectious diseases.

[76]  Dennis Wagenaar,et al.  Multi-variable flood damage modelling with limited data using supervised learning approaches , 2017 .

[77]  Florian Pappenberger,et al.  Action-based flood forecasting for triggering humanitarian action , 2016 .

[78]  Peter M. A. Sloot,et al.  Time-Frequency Methods for Structural Health Monitoring , 2014, Sensors.

[79]  Os Keyes,et al.  The Misgendering Machines , 2018, Proc. ACM Hum. Comput. Interact..

[80]  Stefan Lüdtke,et al.  Flood loss estimation using 3D city models and remote sensing data , 2018, Environ. Model. Softw..

[81]  A.C.W.M. Vrouwenvelder,et al.  Reliability analysis of flood defence systems , 2004 .

[82]  Wei Lee Woon,et al.  Simultaneous extraction of roads and buildings in remote sensing imagery with convolutional neural networks , 2017 .

[83]  E. Ryan,et al.  Infectious diseases of severe weather-related and flood-related natural disasters , 2006, Current opinion in infectious diseases.

[84]  Stefan Lüdtke,et al.  Regional and Temporal Transferability of Multivariable Flood Damage Models , 2018 .

[85]  M. Kok,et al.  Large Scale Flood Hazard Analysis by Including Defence Failures on the Dutch River System , 2019, Water.

[86]  A. Soldati,et al.  Artificial neural network approach to flood forecasting in the River Arno , 2003 .

[87]  Kozo Watanabe,et al.  Machine learning methods reveal the temporal pattern of dengue incidence using meteorological factors in metropolitan Manila, Philippines , 2018, BMC Infectious Diseases.