A Comprehensive Review of Machine Learning Approaches for Flood Depth Estimation

Abstract

In the context of increasing frequency and impact of flood events, traditional methods for estimating flood depth have become insufficient to meet current demands, leading to a gradual shift toward machine learning approaches. This article reviews, for the first time, the applications of machine learning models—including both single and hybrid models—in flood depth estimation, referencing 108 relevant studies. Through statistical analysis, this research explored the most commonly used machine learning models and their primary data sources. Building on this foundation, we also examined the potential for integrating machine learning methods with smart city frameworks and artificial intelligence large models for flood depth calculations. The findings indicate that machine learning models excel in handling large-scale complex data and nonlinear relationships, and their performance can be further optimized through combinations with various models, significantly enhancing the accuracy and efficiency of flood depth estimation. However, these models also face challenges such as data dependency, model interpretability, and transferability. This review reveals the potential of applying machine learning models in flood depth estimation, providing directions for future research and reliable support for disaster prevention and reduction efforts.

Keywords

Deep learning / Flood depth / Inundation height / Literature statistics / Machine learning

References

[1] Abd EllahRG, SparavignaAC. Combining bathymetric measurements, RS, and GIS technologies for monitoring the inland water basins: A case study of Toshka Lakes, Egypt. Egyptian Journal of Aquatic Research, 2023, 49(1): 1-8

[2] AbrilJB, KnightDW. Stage-discharge prediction for rivers in flood applying a depth-averaged model. Journal of Hydraulic Research, 2004, 42(6): 616-629

[3] AkinboyewaT, NingH, LessaniMN, LiZ. Automated floodwater depth estimation using large multimodal model for rapid flood mapping. Computational Urban Science, 2024, 4(1): 12

[4] AlizadehB, LiD, HillinJ, MeyerMA, ThompsonCM, ZhangZ, BehzadanAH. Human-centered flood mapping and intelligent routing through augmenting flood gauge data with crowdsourced street photos. Advanced Engineering Informatics, 2022, 54: 101730

[5] Bhatti, M. 2024. Using large language models for early flood analysis: A case study. Master’s thesis. LUT University, Finland.

[6] BhusalA, ParajuliU, RegmiS, KalraA. Application of machine learning and process-based models for rainfall-runoff simulation in Dupage River basin, Illinois. Hydrology, 2022, 9(7): 117

[7] Binoy, C.N., N. Arjun, C. Keerthi, S. Sreerag, and A.H. Nair. 2019. Flood prediction using flow and depth measurement with artificial neural network in canals. In Proceedings of the 2019 3rd International Conference on Computing Methodologies and Communication (ICCMC 2019), 27–29 March 2019, Erode, India, 798–801.

[8] Briseid StorrøstenE, Ragu RamalingamN, LoritoS, VolpeM, Sánchez-LinaresC, LøvholtF, GibbonsSJ. Machine learning emulation of high resolution inundation maps. Geophysical Journal International, 2024, 238(1): 382-399

[9] Brunner, G.W. 2016. HEC-RAS river analysis system: Hydraulic reference manual, version 5.0. Davis, CA: US Army Corps of Engineers–Hydrologic Engineering Center.

[10] BurnamaNS, RohmatFIW, FaridM, KuntoroAA, KardhanaH, RohmatFIW, WijayasariW. The utilization of satellite data and machine learning for predicting the inundation height in the Majalaya watershed. Water, 2023, 15(17): 3026

[11] CaiHB, RasdorfW, TilleyC. Approach to determine extent and depth of highway flooding. Journal of Infrastructure Systems, 2007, 13(2): 157-167

[12] CarionN, MassaF, SynnaeveG, UsunierN, KirillovA, ZagoruykoS VedaldiA, BischofH, BroxT, FrahmJM. End-to-end object detection with transformers. Computer vision – ECCV 2020. Lecture notes in computer science, 2020 Cham Springer 213-229 12346

[13] ChangM, ChangH, ChenY, LinG, ChenP, LaiJ, TanY. A support vector machine forecasting model for typhoon flood inundation mapping and early flood warning systems. Water, 2018, 10(12): 1734

[14] ChangL, ShenH, WangY, HuangJ, LinY. Clustering-based hybrid inundation model for forecasting flood inundation depths. Journal of Hydrology, 2010, 385(1–4): 257-268

[15] ChenG, HouJ, LiuY, XueS, WuH, WangT, LvJ, JingJ, YangS. Urban inundation rapid prediction method based on multi-machine learning algorithm and rain pattern analysis. Journal of Hydrology, 2024, 633: 131059

[16] ChenJ, LiY, ZhangS. Fast prediction of urban flooding water depth based on CNN- LSTM. Water, 2023, 15(7): 1397

[17] ChoiC, KimJ, HanH, HanD, KimHS. Development of water level prediction models using machine learning in wetlands: A case study of Upo wetland in South Korea. Water, 2019, 12(1): 93

[18] CianF, MarconciniM, CeccatoP, GiupponiC. Flood depth estimation by means of high-resolution SAR images and LiDAR data. Natural Hazards and Earth System Sciences, 2018, 18(11): 3063-3084

[19] CohenS, BrakenridgeGR, KettnerA, BatesB, NelsonJ, McDonaldR, HuangYF, MunasingheD, ZhangJQ. Estimating floodwater depths from flood inundation maps and topography. Journal of the American Water Resources Association, 2018, 54(4): 847-858

[20] Cohen, S., A. Raney, D. Munasinghe, J. Galantowicz, and G.R. Brakenridge. 2018. Estimating floodwater depths from flood inundation maps and topography. Remote Sensing of the Open and Coastal Ocean and Inland Waters: Article 10778.

[21] Colverd, G., P. Darm, L. Silverberg, and N. Kasmanoff. 2023. Floodbrain: Flood disaster reporting by web-based retrieval augmented generation with an LLM. arXiv preprint arXiv: 2311.02597.

[22] DangTQ, TranBH, LeQN, DangTD, TanimAH, PhamQB, BuiV, MaiST, et al.. Application of machine learning-based surrogate models for urban flood depth modeling in Ho Chi Minh City, Vietnam. Applied Soft Computing, 2024, 150: 111031

[23] Das, P., K. Jensen, S. De, and A.R. Ganguly. 2023. Flood depth estimation using synthetic aperture radar (SAR) imagery and topography: A case study of the 2021 and 2022 floods in Hawkesbury Valley, Australia. In Proceedings of IGARSS 2023 – 2023 IEEE International Geoscience and Remote Sensing Symposium, 16–21 July 2023, Pasadena, CA, USA, 2402–2405.

[24] ElkhrachyI. Flash flood water depth estimation using SAR images, digital elevation models, and machine learning algorithms. Remote Sensing, 2022, 14(3): 440

[25] EtterS, StroblB, SeibertJ, van MeerveldHI. Value of crowd-based water level class observations for hydrological model calibration. Water Resources Research, 2020, 56(2): e2019WR026108

[26] FengY, BrennerC, SesterM. Flood severity mapping from volunteered geographic information by interpreting water level from images containing people: A case study of Hurricane Harvey. ISPRS Journal of Photogrammetry and Remote Sensing, 2020, 169: 301-319

[27] FohringerJ, DranschD, KreibichH, SchröterK. Social media as an information source for rapid flood inundation mapping. Natural Hazards and Earth System Sciences, 2015, 15(12): 2725-2738

[28] GoodchildMF. Citizens as sensors: The world of volunteered geography. GeoJournal, 2007, 69: 211-221

[29] HaoX, LyuH, WangZ, FuS, ZhangC. Estimating the spatial-temporal distribution of urban street ponding levels from surveillance videos based on computer vision. Water Resources Management, 2022, 36(6): 1799-1812

[30] HervouetJ Hydrodynamics of free surface flows: Modelling with the finite element method, 2007 Hoboken John Wiley & Sons

[31] HosseinyH. A deep learning model for predicting river flood depth and extent. Environmental Modelling & Software, 2021, 145: 105186

[32] HosseinyH, NazariF, SmithV, NatarajC. A framework for modeling flood depth using a hybrid of hydraulics and machine learning. Scientific Reports, 2020, 10(1): 8222

[33] HuangJ, KangJ, WangH, WangZ, QiuT. A novel approach to measuring urban waterlogging depth from images based on mask region-based convolutional neural network. Sustainability, 2020, 12(5): 2149

[34] JinH, LuH, ZhaoY, ZhuZ, YanW, YangQ, ZhangS. Integration of an improved transformer with physical models for the spatiotemporal simulation of urban flooding depths. Journal of Hydrology: Regional Studies, 2024, 51: 101627

[35] KamojiS, KallaM. Effective flood prediction model based on Twitter text and image analysis using BMLP and SDAE-HHNN. Engineering Applications of Artificial Intelligence, 2023, 123: 106365

[36] Kumbam, P.R., and K.M. Vejre. 2024. Floodlense: A framework for ChatGPT-based real-time flood detection. arXiv preprint arXiv: 2401.15501.

[37] Kurihara, K., Y. Toyoda, and M. Sugita. 2022. Flood depth estimation via SAR satellite analysis using prior knowledge of flood hazard mapping. In Proceedings of the 2022 IEEE International Geoscience and Remote Sensing Symposium (IGARSS 2022), 17–22 July 2022, Kuala Lumpur, Malaysia, 3371–3373.

[38] LausheyLM, HuangBG LiG. Real-time flood forecasting by tracing depth contours. Forecasting and mitigation of water-related disasters, Theme C, Proceedings: 21st Century: The new era for hydraulic research and its applications, 2001 Beijing Tsinghua University Press 120-129

[39] LiJ, CaiR, TanY, ZhouH, SadickA, ShouW, WangX. Automatic detection of actual water depth of urban floods from social media images. Measurement, 2023, 216: 112891

[40] LinY, LinY, HanJ. Automatic water-level detection using single-camera images with varied poses. Measurement, 2018, 127: 167-174

[41] LiouY, HoangD. Improved flood depth estimation with SAR image, digital elevation model, and machine learning schemes. Journal of Hydrology: Regional Studies, 2024, 53: 101775

[42] LiuB, LiY, FengX, LianP. BEW-YOLOv8: A deep learning model for multi-scene and multi-scale flood depth estimation. Journal of Hydrology, 2024, 645: 132139

[43] LiuS, ZhengW, WangX, XiongH, ChengJ, YongC, ZhangW, ZouX. A novel depth measurement method for urban flooding based on surveillance video images and a floating ruler. Natural Hazards, 2023, 119(3): 1967-1989

[44] LöweR, BöhmJ, JensenDG, LeandroJ, RasmussenSH. U-FLOOD – Topographic deep learning for predicting urban pluvial flood water depth. Journal of Hydrology, 2021, 603: 126898

[45] MangukiyaNK, KushwahaS, SharmaA. A novel multi-model ensemble framework for fluvial flood inundation mapping. Environmental Modelling & Software, 2024, 180: 106163

[46] MekanikF, ImteazMA, Gato-TrinidadS, ElmahdiA. Multiple regression and artificial neural network for long-term rainfall forecasting using large scale climate modes. Journal of Hydrology, 2013, 503: 11-21

[47] Meng, Z.L., B. Peng, and Q.Y. Huang. 2019. Flood depth estimation from web images. In ARIC 2019: Proceedings of the 2nd Acm Sigspatial International Workshop on Advances in Resilient and Intelligent Cities (ARIC-2019), ed. B. Kar, O.A. Omitaomu, X. Ye, S. Mohebbi, and G. Fu, 37–40. New York: Association for Computing Machinery.

[48] MerzB, BlöschlG, VorogushynS, DottoriF, AertsJCJH, BatesP, BertolaM, KemterM, et al.. Causes, impacts and patterns of disastrous river floods. Nature Reviews Earth & Environment, 2021, 2(9): 592-609

[49] MiyamotoH, KomatsuG, BakerVR, DohmJM, ItoK, TosakaH. Cataclysmic scabland flooding: Insights from a simple depth-averaged numerical model. Environmental Modelling & Software, 2007, 22(10): 1400-1408

[50] MontelloF, ArnaudoE, RossiC. Mmflood: A multimodal dataset for flood delineation from satellite imagery. IEEE Access, 2022, 10: 96774-96787

[51] MosaviA, OzturkP, ChauK. Flood prediction using machine learning models: Literature review. Water, 2018, 10(11): 1536

[52] MoyaL, MasE, KoshimuraS. Sparse representation-based inundation depth estimation using SAR data and digital elevation model. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2022, 15: 9062-9072

[53] Nair, B.B., and S. Rao. 2016. Flood water depth estimation – A survey. In Proceedings of the 2016 IEEE International Conference on Computational Intelligence and Computing Research, 15–17 December 2016, Tamil Nadu, India, 845–848.

[54] NguyenHD, DangDK, NguyenNY, Van PhamC, Van NguyenTT, NguyenQ, NguyenXL, PhamLT, et al.. Integration of machine learning and hydrodynamic modeling to solve the extrapolation problem in flood depth estimation. Journal of Water and Climate Change, 2024, 15(1): 284-304

[55] OttoFE, Van OldenborghGJ, EdenJ, StottPA, KarolyDJ, AllenMR. The attribution question. Nature Climate Change, 2016, 6(9): 813-816

[56] PallyRJ, SamadiS. Application of image processing and convolutional neural networks for flood image classification and semantic segmentation. Environmental Modelling & Software: With Environment Data News, 2022, 148: 105285

[57] ParkS, BaekF, SohnJ, KimH. Computer vision based estimation of flood depth in flooded-vehicle images. Journal of Computing in Civil Engineering, 2021

[58] PhilipS, KewS, van OldenborghGJ, OttoF, VautardR, van Der WielK, KingA, LottF, et al.. A protocol for probabilistic extreme event attribution analyses. Advances in Statistical Climatology, Meteorology and Oceanography, 2020, 6(2): 177-203

[59] PrakashG, GuptaPK, RaoGV, PratapD. Flood inundation mapping and depth modelling using machine learning algorithms and microwave data. Journal of Geomatics, 2021, 15(2): 221-229

[60] QinJ, GaoL, LinK, ShenP. A novel and efficient method for real-time simulating spatial and temporal evolution of coastal urban pluvial flood without drainage network. Environmental Modelling & Software, 2024, 172: 105888

[61] Qiu, W., and A. Yuille. 2016. UnrealCV: Connecting computer vision to unreal engine. In Proceedings of Computer vision – ECCV 2016 workshops, Amsterdam, The Netherlands, 8–10 and 15–16 October 2016, Part III, ed G. Hua, and H. Jégou, 909–916. Cham: Springer.

[62] RanaM, PatelD, VakhariaV, SinghSK. UAV-based DEM augmentation using ConSinGAN for efficient flood parameter prediction with machine learning and 1D hydrodynamic models. Physics and Chemistry of the Earth, Parts A/B/C, 2024, 135: 103675

[63] RentschlerJ, AvnerP, MarconciniM, SuR, StranoE, VousdoukasM, HallegatteS. Global evidence of rapid urban growth in flood zones since 1985. Nature, 2023, 622(7981): 87-92

[64] RentschlerJ, SalhabM, JafinoBA. Flood exposure and poverty in 188 countries. Nature Communications, 2022, 13(1): 3527

[65] RossiC, AcerboFS, YlinenK, JugaI, NurmiP, BoscaA, TarasconiF, CristoforettiM, AlikadicA. Early detection and information extraction for weather-induced floods using social media streams. International Journal of Disaster Risk Reduction, 2018, 30: 145-157

[66] Schmidt, V., A.S. Luccioni, M. Teng, T. Zhang, A. Reynaud, S. Raghupathi, G. Cosne, A. Juraver, et al. 2021. Climategan: Raising climate change awareness by generating images of floods. arXiv preprint arXiv: 2110.02871.

[67] ScorziniAR, RadiceA, MolinariD. A new tool to estimate inundation depths by spatial interpolation (RAPIDE): Design, application and impact on quantitative assessment of flood damages. Water, 2018, 10(12): 1805

[68] SeibertJ, StroblB, EtterS, HummerP, van MeerveldHJ. Virtual staff gauges for crowd-based stream level observations. Frontiers in Earth Science, 2019, 7: 70

[69] SeleemO, AyzelG, BronstertA, HeistermannM. Transferability of data-driven models to predict urban pluvial flood water depth in Berlin, Germany. Natural Hazards and Earth System Sciences Discussions, 2022, 2023(2): 809-822

[70] SituZ, WangQ, TengS, FengW, ChenG, ZhouQ, FuG. Improving urban flood prediction using LSTM-DeepLabv3+ and Bayesian optimization with spatiotemporal feature fusion. Journal of Hydrology, 2024, 630: 130743

[71] SongZQ, TuoY. Automated flood depth estimates from online traffic sign images: Explorations of a convolutional neural network-based method. Sensors, 2021, 21(16): 5614

[72] Soria-Ruiz, J., Y.M. Fernandez-Ordoñez, and J.P. Ambrosio-Ambrosio. 2023. Extent and depth of flooding using SAR Sentinel-1 and machine learning algorithms. In Proceedings of IGARSS 2023 – 2023 IEEE International Geoscience and Remote Sensing Symposium, 16–21 July 2023, Pasadena, CA, USA, 2246–2249.

[73] Soria-Ruiz, J., Y.M. Fernandez-Ordoñez, J.P. Ambrosio-Ambrosio, and M.A. Escalona-Maurice. 2022. Sentinel-1 SAR and LiDAR to detect extent and depth flood using Random Forests machine learning. In Proceedings of the 2022 IEEE International Geoscience and Remote Sensing Symposium (IGARSS 2022), 17–22 July 2022, Kuala Lumpur, Malaysia, 5113–5116.

[74] Sun, Y., C. Wang, and Y. Peng. 2023. Unleashing the potential of large language model: Zero-shot VQA for flood disaster scenario. In Proceedings of the 4th International Conference on Artificial Intelligence and Computer Engineering, 17–19 November 2023, Dalian, China, 368–373.

[75] TellmanB, SullivanJA, KuhnC, KettnerAJ, DoyleCS, BrakenridgeGR, EricksonTA, SlaybackDA. Satellite imaging reveals increased proportion of population exposed to floods. Nature, 2021, 596(7870): 80-86

[76] Teng, Y., B. Lang, and Z. Gu. 2017. Flood event recognition from images based on CNN and semantics. In Proceedings of the 2017 International Conference on Computational Science and Computational Intelligence (CSCI), 14–16 December 2017, Nevada, USA.

[77] Tychsen-SmithL, ArminMA, KarimF. Towards non-region specific large-scale inundation modelling with machine learning methods. Water, 2024, 16(16): 2263

[78] Vahdat-NejadH, TamadonT, SalmaniF, Kiani-ZadeganZ, AbbasiS, SeyyediF Al-EmranM, ShaalanK. A survey on crowdsourcing applications in smart cities. Recent innovations in artificial intelligence and smart applications, 2022 Cham Springer 239-253

[79] Vallimeena, P., B.B. Nair, and S.N. Rao. 2018. Machine vision based flood depth estimation using crowdsourced images of humans. In Proceedings of the 2018 IEEE International Conference on Computational Intelligence and Computing Research (IEEE ICCIC 2018), 3–15 December 2018, Madurai, India, 111–114.

[80] WangHF, GuanXJ, MengY, WuZN, WangK, WangHL. Coupling time and non-time series models to simulate the flood depth at urban flooded area. Water Resources Management, 2023, 37(3): 1275-1295

[81] WangR, MaoH, WangY, RaeC, ShawW. Hyper-resolution monitoring of urban flooding with social media and crowdsourcing data. Computers & Geosciences, 2018, 111: 139-147

[82] WangHL, WangHF, WuZN, ZhouYH. Using multi-factor analysis to predict urban flood depth based on naive Bayes. Water, 2021, 13(4): 432

[83] WarrenIR, BachHK. MIKE 21: A modelling system for estuaries, coastal waters and seas. Environmental Software, 1992, 7(4): 229-240

[84] WuZ, HuangY, HuangK, YanK, ChenH. A review of non-contact water level measurement based on computer vision and radar technology. Water, 2023, 15(18): 3233

[85] WuZN, ZhouYH, WangHL, JiangZH. Depth prediction of urban flood under different rainfall return periods based on deep learning and data warehouse. Science of the Total Environment, 2020, 716: 137077

[86] XuK, HanZ, XuH, BinL. Rapid prediction model for urban floods based on a light gradient boosting machine approach and hydrological-hydraulic model. International Journal of Disaster Risk Science, 2023, 14(1): 79-97

[87] YanX, XuK, FengW, ChenJ. A rapid prediction model of urban flood inundation in a high-risk area coupling machine learning and numerical simulation approaches. International Journal of Disaster Risk Science, 2021, 12(6): 903-918

[88] YangF, DingW, ZhaoJ, SongL, YangD, LiX. Rapid urban flood inundation forecasting using a physics-informed deep learning approach. Journal of Hydrology, 2024, 643: 131998

[89] YangSY, JhongYD, JhongBC, LinYY. Enhancing flooding depth forecasting accuracy in an urban area using a novel trend forecasting method. Water Resources Management, 2024, 38(4): 1359-1380

[90] YangSY, JhongBC, JhongYD, TsaiTT, ChenCS. Long short-term memory integrating moving average method for flood inundation depth forecasting based on observed data in urban area. Natural Hazards, 2023, 116(2): 2339-2361

[91] ZahuraFT, GoodallJL, SadlerJM, ShenY, MorsyMM, BehlM. Training machine learning surrogate models from a high-fidelity physics-based model: Application for real-time street-scale flood prediction in an urban coastal community. Water Resources Research, 2020, 56(10): e2019WR027038

[92] ZhangD, TongJ. Robust water level measurement method based on computer vision. Journal of Hydrology, 2023, 620: 129456

[93] ZhangW, LiuY, TangW, ChenS, XieW. Rapid spatio-temporal prediction of coastal urban floods based on deep learning approaches. Urban Climate, 2023, 52: 101716

[94] ZhangZ, MaY, LiuP. A global multimodal flood event dataset with heterogeneous text and multi-source remote sensing images. Big Earth Data, 2024

[95] ZhongP, LiuY, ZhengH, ZhaoJ. Detection of urban flood inundation from traffic images using deep learning methods. Water Resources Management, 2024, 38(1): 287-301

[96] ZhouY, WuW, NathanR, WangQJ. A rapid flood inundation modelling framework using deep learning with spatial reduction and reconstruction. Environmental Modelling & Software, 2021, 143: 105112

[97] ZhuJ, DangP, CaoY, LaiJ, GuoY, WangP, LiW. A flood knowledge-constrained large language model interactable with GIS: Enhancing public risk perception of floods. International Journal of Geographical Information Science, 2024, 38(4): 603-625

[98] Zou, B.Y., B. Peng, and Q.Y. Huang. 2022. Flood depth assessment with location-based social network data and Google Street View – A case study with buildings as reference objects. In Proceedings of the 2022 IEEE International Geoscience and Remote Sensing Symposium (IGARSS 2022), 17–22 July 2022, Kuala Lumpur, Malaysia, 1344–1347.

RIGHTS & PERMISSIONS

The Author(s)