Flood susceptibility mapping using a novel integration of multi-temporal sentinel-1 data and eXtreme deep learning model

Abstract

Flash floods (FFs) are amongst the most devastating hazards in arid regions in response to climate change and can cause the loss of agricultural land, human lives and infrastructure. One of the major challenges is the high-intensity rainfall events affecting low-lying areas that are vulnerable to FF. Several works in this field have been conducted using ensemble machine learning models and geohydrological models. However, the current advancement of eXtreme deep learning, which is named eXtreme deep factorisation machine (xDeepFM), for FF susceptibility mapping (FSM) is lacking in the literature. The current study introduces a new model and employs a previously unapplied approach to enhance FSM for capturing the severity of floods. The proposed approach has three main objectives: (i) During- and after-flood effects are assessed through flood detection techniques using Sentinel-1 data. (ii) Flood inventory is updated using remote sensing-based methods. The derived flood effects are implemented in the next step. (iii) An FSM map is generated using an xDeepFM model. Therefore, this study aims to apply xDeepFM to estimate susceptible areas using 13 factors in the emirates of Fujairah, UAE. The performance metrics show a recall of 0.9488), an F1-score of 0.9107), precision of (0.8756) and an overall accuracy of 90.41%. The accuracy of the applied xDeepFM model is compared with that of traditional machine learning models, specifically the deep neural network (78%), support vector machine (85.4%) and random forest (88.75%). Random forest achieves high accuracy, which is due to its strong performance that depends on factors contribution, dataset size and quality, and available computational resources. Comparatively, the xDeepFM model works efficiently for complicated prediction problems having high non-collinearity and huge datasets. The obtained map denotes that the narrow basins, lowland coastal areas and riverbank areas up to 5 km (Fujairah) are highly prone to FF, whilst the alluvial plains in Al Dhaid and hilly regions in Fujairah show low probability. The coastal city areas are bounded by high-rise steep hills and the Gulf of Oman, which can elevate the water levels during heavy rainfall. Four major synchronised influencing factors, namely, rainfall, elevation, drainage density, distance from drainage and geomorphology, account for nearly 50% of the total factors contributing to a very high flood susceptibility. This study offers a platform for planners and decision makers to take timely actions on potential areas in mitigating the effects of FF.

Keywords

Flood susceptibility mapping / eXtreme Deep Factorisation Machine / Sentinel-1 / Remote sensing

References

M.M. Abdelkader, A.I. Al-Amoud, M. El Alfy, A. El-Feky, M. Saber. Assessment of flash flood hazard based on morphometric aspects and rainfall-runoff modeling in Wadi Nisah, central Saudi Arabia. Remote Sens. Appl.: Soc. Environ., 23 (2021), Article 100562,

M. Ahmadlou, M. Karimi, S. Alizadeh, A. Shirzadi, D. Parvinnejhad, H. Shahabi, M. Panahi. Flood susceptibility assessment using integration of adaptive network-based fuzzy inference system (ANFIS) and biogeography-based optimization (BBO) and BAT algorithms (BA). Geocarto Int., 34 (11) (2019), pp. 1252-1272,

Al Murshidi, A.H., 2012. Flash flooding risk assessment using GIS in Dibba Fujairah, UAE. M.Sc. thesis in Remote Sensing and Geographic Information Systems, UAE University, 183 pp.

R. Al-Ruzouq, A. Shanableh, T. Merabtene, M. Siddique, M.A. Khalil, A. Idris, E. Almulla. Potential groundwater zone mapping based on geo-hydrological considerations and multi-criteria spatial analysis: North UAE. Catena, 173 (2019), pp. 511-524

A. Arabameri, K. Rezaei, A. Cerdà, C. Conoscenti, Z. Kalantari. A comparison of statistical methods and multi-criteria decision making to map flood hazard susceptibility in Northern Iran. Sci. Total Environ., 660 (2019), pp. 443-458

A. Bahremand, F. De Smedt, J. Corluy, Y.B. Liu, J. Poorova, L. Velcicka, E. Kunikova. WetSpa model application for assessing reforestation impacts on floods in Margecany-Hornad Watershed, Slovakia. Water Resour. Manag., 21 (2007), pp. 1373-1391

V.B. Bout, V.G. Jetten. The validity of flow approximations when simulating catchment-integrated flash floods. J. Hydrol., 556 (2018), pp. 674-688

D.T. Bui, P.T.T. Ngo, T.D. Pham, A. Jaafari, N.Q. Minh, P.V. Hoa, P. Samui. A novel hybrid approach based on a swarm intelligence optimized extreme learning machine for flash flood susceptibility mapping. Catena, 179 (2019), pp. 184-196

W. Chen, Y. Li, W. Xue, H. Shahabi, S. Li, H. Hong, X. Wang, H. Bian, S. Zhang, B. Pradhan, B.B. Ahmad. Modeling flood susceptibility using data-driven approaches of naïve bayes tree, alternating decision tree, and random forest methods. Sci. Total Environ., 701 (2020), Article 134979,

R. Costache, Q.B. Pham, E. Sharifi, N.T.T. Linh, S.I. Abba, M. Vojtek, J. Vojteková, P.T.T. Nhi, D.N. Khoi. Flash-flood susceptibility assessment using multi-criteria decision making and machine learning supported by remote sensing and GIS techniques. Remote Sens. (Basel), 12 (1) (2019), p. 106,

S. Das. Geospatial mapping of flood susceptibility and hydro-geomorphic response to the floods in Ulhas basin, India. Remote Sens. Appl.: Soc. Environ., 14 (2019), pp. 60-74

S. Das, A. Gupta. Multi-criteria decision based geospatial mapping of flood susceptibility and temporal hydro-geomorphic changes in the Subarnarekha basin, India. Geosci. Front., 12 (5) (2021), Article 101206,

L. Duan, C. Liu, H. Xu, H. Pan, H. Liu, X. Yan, T. Liu, Z. Yang, G. Liu, X. Dai, D. Zhang. Susceptibility Assessment of Flash Floods: A Bibliometrics Analysis and Review. Remote Sens. (Basel), 14 (21) (2022), p. 5432,

Elhakeem, M., 2017. Flood prediction at the northern region of UAE. In: Proc. International Symposium on Civil and Environmental Engineering 2016 (ISCEE 2016), EDP Sciences, Melaka, Malaysia, 04004. https://doi.org/10.1051/matecconf/201710304004.

S. Elmahdy, T. Ali, M. Mohamed. Flash Flood Susceptibility modeling and magnitude index using machine learning and geohydrological models: A modified hybrid approach. Remote Sens. (Basel), 12 (17) (2020), p. 2695,

F. Falah, O. Rahmati, M. Rostami, E. Ahmadisharaf, I.N. Daliakopoulos, H.R. Pourghasemi. Artificial neural networks for flood susceptibility mapping in data-scarce urban areas. H.R. Pourghasemi, C. Gokceoglu (Eds.), Spatial modeling in GIS and, R for Earth and Environmental Sciences, Nederland (2019), pp. 323-336

Z. Fang, Y. Wang, L. Peng, H. Hong. Predicting flood susceptibility using LSTM neural networks. J. Hydrol., 594 (2021), Article 125734,

D.S. Fernández, M.A. Lutz. Urban flood hazard zoning in Tucumán Province, Argentina, using GIS and multicriteria decision analysis. Eng. Geol., 111 (2010), pp. 90-98

Fujairah municipality, 2020. Emirate of Fujairah. https://web.archive.org/web/20201124150106/; https://www.fujmun.gov.ae/page.aspx?id=73&template=default&lang=ar (accessed 12 March 2023).

Fujairah Statistics Centre, 2018. Statistical year book. https://www.fscfuj.gov.ae/books/book2018.pdf (accessed 15 September 2019).

C.J. Gleason. Hydraulic geometry of natural rivers: A review and future directions. Prog. Phys. Geogr., 39 (3) (2015), pp. 337-360

E.P. Glenn, K. Morino, P.L. Nagler, R.S. Murray, S. Pearlstein, K.R. Hultine. Roles of saltcedar (Tamarix spp.) and capillary rise in salinizing a non-flooding terrace on a flow-regulated desert river. Journal of Arid Environments, 79 (2012), pp. 56-65

L. Goodarzi, M.E. Banihabib, A. Roozbahani, J. Dietrich. Bayesian network model for flood forecasting based on atmospheric ensemble forecasts. Nat. Hazards Earth Syst. Sci., 19 (11) (2019), pp. 2513-2524

T. Grabs, J. Seibert, K. Bishop, H. Laudon. Modeling spatial patterns of saturated areas: A comparison of the topographic wetness index and a dynamic distributed model. J. Hydrol., 373 (2009), pp. 15-23

Gulf Today, 2022. Fujairah’s Flood. https://www.gulftoday.ae/news/2022/07/29/at-least-six-dead-due-to-uae-floods (accessed 29 July 2023).

K. Hussein, K. Alkaabi, D. Ghebreyesus, M.U. Liaqat, H.O. Sharif. Land use/land cover change along the Eastern Coast of the UAE and its impact on flooding risk. Geomat. Nat. Haz. Risk, 11 (1) (2020), pp. 112-130

S.K. Jain, R.D. Singh, M.K. Jain, A.K. Lohani. Delineation of flood-prone areas using remote sensing techniques. Water Resour. Manag., 19 (2005), pp. 333-347

R.S.R.S. Jayakrishnan, R. Srinivasan, C. Santhi, J.G. Arnold. Advances in the application of the SWAT model for water resources management. Hydrol. Process., 19 (3) (2005), pp. 749-762

Khalifa, M., Ahmed, O., Abo El fetoh, A., 2022. The highest amount of rain in July in 27 years. https://www.albayan.ae/uae/news/2022-07-28-1.4484514 (accessed 28 July 2023).

R. Jena, B. Pradhan, S.P. Naik, A.M. Alamri. Earthquake risk assessment in NE India using deep learning and geospatial analysis. Geoscience Frontiers, 12 (3) (2021), p. 101110,

S. Khan, H.F. Gabriel, T. Rana. Standard precipitation index to track drought and assess impact of rainfall on watertables in irrigation areas. Irrig. Drain. Syst., 22 (2008), pp. 159-177

K. Khosravi, H. Shahabi, B.T. Pham, J. Adamowski, A. Shirzadi, B. Pradhan, J. Dou, H.B. Ly, G. Gróf, H.L. Ho, H. Hong. A comparative assessment of flood susceptibility modeling using multi-criteria decision-making analysis and machine learning methods. J. Hydrol., 573 (2019), pp. 311-323

Y. Li, H. Hong. Modelling flood susceptibility based on deep learning coupling with ensemble learning models. J. Environ. Manage., 325 (2023), Article 116450,

J. Lian, X. Zhou, F. Zhang, Z. Chen, X. Xie, G. Sun. Xdeepfm: Combining explicit and implicit feature interactions for recommender systems. Proc. 24th ACM SIGKDD international conference on knowledge discovery & data mining, London, United Kingdom (2018), pp. 1754-1763

J. Liu, J. Wang, J. Xiong, W. Cheng, Y. Li, Y. Cao, Y. He, Y. Duan, W. He, G. Yang. Assessment of flood susceptibility mapping using support vector machine, logistic regression and their ensemble techniques in the Belt and Road region. Geocarto Int., 37 (25) (2022), pp. 9817-9846

L. Loosvelt, J. Peters, H. Skriver, H. Lievens, F.M. Van Coillie, B. De Baets, N.E. Verhoest. Random Forests as a tool for estimating uncertainty at pixel-level in SAR image classification. Int. J. Appl. Earth Obs. Geoinf., 19 (2012), pp. 173-184

Q. Lu, S. Li, T. Yang, C. Xu. An adaptive hybrid XdeepFM based deep interest network model for click-through rate prediction system. PeerJ Comput. Sci., 7 (2021), p. e716

D.C. Mason, L. Giustarini, J. Garcia-Pintado, H.L. Cloke. Detection of flooded urban areas in high resolution Synthetic Aperture Radar images using double scattering. Int. J. Appl. Earth Obs. Geoinf., 28 (2014), pp. 150-159

S. Mehravar, S.V. Razavi-Termeh, A. Moghimi, B. Ranjgar, F. Foroughnia, M. Amani. Flood susceptibility mapping using multi-temporal SAR imagery and novel integration of nature-inspired algorithms into support vector regression. J. Hydrol., 617 (2023), Article 129100,

A.G. Mohammad, M.A. Adam. The impact of vegetative cover type on runoff and soil erosion under different land uses. Catena, 81 (2) (2010), pp. 97-103

M. Mohammady, H.R. Pourghasemi, M. Amiri. Assessment of land subsidence susceptibility in Semnan plain (Iran): A comparison of support vector machine and weights of evidence data mining algorithms. Nat. Hazards, 99 (2019), pp. 951-971

H. Moradkhani, S. Sorooshian. General review of rainfall-runoff modeling: model calibration, data assimilation, and uncertainty analysis. S. Sorooshian, K.L. Hsu, E. Coppola, B. Tomassetti, M. Verdecchia, G. Visconti (Eds.), Hydrological Modelling and the Water Cycle, Springer, Berlin, Heidelberg (2008), pp. 1-24

A. Nandi, A. Mandal, M. Wilson, D. Smith. Flood hazard mapping in Jamaica using principal component analysis and logistic regression. Environ. Earth Sci., 75 (2016), pp. 1-16

R. Nijzink, C. Hutton, I. Pechlivanidis, R. Capell, B. Arheimer, J. Freer, D. Han, T. Wagener, K. McGuire, H. Savenije, M. Hrachowitz. The evolution of root-zone moisture capacities after deforestation: a step towards hydrological predictions under change?. Hydrology and Earth System Sciences, 20 (12) (2016), pp. 4775-4799

F.N. Nkeki, E.I. Bello, I.G. Agbaje. Flood risk mapping and urban infrastructural susceptibility assessment using a GIS and analytic hierarchical raster fusion approach in the Ona River Basin, Nigeria. Int. J. Disaster Risk Reduct., 77 (2022), Article 103097,

B.T. Pham, T.V. Phong, H.D. Nguyen, C. Qi, N. Al-Ansari, A. Amini, L.S. Ho, T.T. Tuyen, H.P.H. Yen, H.B. Ly, I. Prakash. A comparative study of kernel logistic regression, radial basis function classifier, multinomial naïve bayes, and logistic model tree for flash flood susceptibility mapping. Water, 12 (1) (2020), p. 239,

P. Prasad, V.J. Loveson, B. Das, M. Kotha. Novel ensemble machine learning models in flood susceptibility mapping. Geocarto Int., 37 (16) (2022), pp. 4571-4593

A. Quesada-Román, J.A. Ballesteros-Cánovas, S. Granados-Bolaños, C. Birkel, M. Stoffel. Improving regional flood risk assessment using flood frequency and dendrogeomorphic analyses in mountain catchments impacted by tropical cyclones. Geomorphology, 396 (2022), Article 108000,

O. Rahmati, H.R. Pourghasemi, H. Zeinivand. Flood susceptibility mapping using frequency ratio and weights-of-evidence models in the Golastan Province, Iran. Geocarto Int., 31 (1) (2016), pp. 42-70

M.J. Reeve. Water retention, porosity, and composition inter-relationships of alluvial soils in mid Hawke's Bay and their relevance in irrigation planning. N. Z. J. Agric. Res., 29 (3) (1986), pp. 457-468

S. Rendle. Factorization machines with libfm. ACM Trans. Intell. Syst. Technol. (TIST), 3 (3) (2012), pp. 1-22

S. Samanta, D.K. Pal, B. Palsamanta. Flood susceptibility analysis through remote sensing, GIS and frequency ratio model. Appl. Water Sci., 8 (2) (2018), p. 66,

N. Şarlak. Flood frequency estimator with nonparametric approaches in Turkey. Fresen. Environ. Bull., 21 (5) (2012), pp. 1083-1089

V. Scorpio, N. Santangelo, A. Santo. Multiscale map analysis in alluvial fan flood-prone areas. J. Maps, 12 (2) (2016), pp. 382-393

H. Shafizadeh-Moghadam, R. Valavi, H. Shahabi, K. Chapi, A. Shirzadi. Novel forecasting approaches using combination of machine learning and statistical models for flood susceptibility mapping. J. Environ. Manage., 217 (2018), pp. 1-11

H. Shahabi, A. Shirzadi, S. Ronoud, S. Asadi, B.T. Pham, F. Mansouripour, M. Geertsema, J.J. Clague, D.T. Bui. Flash flood susceptibility mapping using a novel deep learning model based on deep belief network, back propagation and genetic algorithm. Geosci. Front., 12 (3) (2021), Article 101100,

A. Shanableh, R. Al-Ruzouq, A.G. Yilmaz, M. Siddique, T. Merabtene, M.A. Imteaz. Effects of land cover change on urban floods and rainwater harvesting: a case study in Sharjah. UAE. Water, 10 (5) (2018), p. 631,

M.S. Tehrany, B. Pradhan, M.N. Jebur. Flood susceptibility mapping using a novel ensemble weights-of-evidence and support vector machine models in GIS. J. Hydrol., 512 (2014), pp. 332-343

J.P. Terry, A. Al Ruheili, M.A. Almarzooqi, R.Y. Almheiri, A.K. Alshehhi. The rain deluge and flash floods of summer 2022 in the United Arab Emirates: Causes, analysis and perspectives on flood-risk reduction. J. Arid Environ., 215 (2023), Article 105013,

D. Tien Bui, K. Khosravi, S. Li, H. Shahabi, M. Panahi, V.P. Singh, K. Chapi, A. Shirzadi, S. Panahi, W. Chen, B. Bin Ahmad. New hybrids of anfis with several optimization algorithms for flood susceptibility modeling. Water, 10 (9) (2018), p. 1210,

K. Trepekli, T. Balstrøm, T. Friborg, B. Fog, A.N. Allotey, R.Y. Kofie, L. Møller-Jensen. UAV-borne, LiDAR-based elevation modelling: A method for improving local-scale urban flood risk assessment. Nat. Hazards, 113 (1) (2022), pp. 423-451

Y. Wang, Z. Fang, H. Hong, L. Peng. Flood susceptibility mapping using convolutional neural network frameworks. J. Hydrol., 582 (2020), Article 124482,

H. Waqas, L. Lu, A. Tariq, Q. Li, M.F. Baqa, J. Xing, A. Sajjad. Flash flood susceptibility assessment and zonation using an integrating analytic hierarchy process and frequency ratio model for the Chitral District, Khyber Pakhtunkhwa. Pakistan. Water, 13 (12) (2021), p. 1650,

Xu, L., Ren, J.S., Liu, C., Jia, J., 2014. Deep convolutional neural network for image deconvolution. Advances in neural information processing systems, in: Proc. Advances in Neural Information Processing Systems 27: Annual Conference on Neural Information Processing Systems 2014, Montreal, Quebec, Canada, 1-9.

M.M. Yagoub, A.A. Alsereidi, E.A. Mohamed, P. Periyasamy, R. Alameri, S. Aldarmaki, Y. Alhashmi. Newspapers as a validation proxy for GIS modeling in Fujairah, United Arab Emirates: identifying flood-prone areas. Nat. Hazards, 104 (2020), pp. 111-141

G. Zhao, B. Pang, Z. Xu, J. Yue, T. Tu. Mapping flood susceptibility in mountainous areas on a national scale in China. Sci. Total Environ., 615 (2018), pp. 1133-1142