A novel flood conditioning factor based on topography for flood susceptibility modeling

Abstract

Flood is one of the most devastating natural hazards. Employing machine learning models to construct flood susceptibility maps has become a pivotal step for decision-makers in disaster prevention and management. Existing flood conditioning factors inadequately account for regional characteristics of flood in the depiction of topography, potentially leading to an overestimation of flood susceptibility in flat areas. Addressing this gap, this study proposes a novel flood conditioning factor, local convexity factor (LCF), to enhance the accuracy of flood susceptibility modeling. Initially, LCF is computed based on a standard normal Gaussian surface to highlight elevation variations in local terrain. Subsequently, LCF is applied to flood susceptibility modeling using seven machine learning models across four distinct basins. Comparative analysis is conducted between flood susceptibility maps with and without the application of LCF to evaluate its impact on flood susceptibility modeling. The results demonstrate that the proposed LCF can enhance the accuracy of flood susceptibility modeling to varying degrees, across the four basins investigated. The Fujiang basin exhibited the most substantial improvement, with its AUC improved from 0.861 to 0.886, Producer’s Agreement improved from 0.869 to 0.899, and Overall Agreement improved from 0.778 to 0.811. Comparation with hydrodynamic inundation maps shows that particularly in relatively flat terrain areas, flood susceptibility maps incorporating LCF offer more precise delineation between flood-prone and non-flood-prone zones. This research holds potential for widespread application in the prediction of flood susceptibility using machine learning models, providing a novel perspective for enhancing their accuracy.

Keywords

Flood susceptibility prediction / Flood conditioning factor / Machine learning model / Local terrain features

References

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 (2019), pp. 1252-1272,

A.M. Al-Abadi, B. Pradhan. In flood susceptibility assessment, is it scientifically correct to represent flood events as a point vector format and create flood inventory map?. J. Hydrol., 590 (2020), Article 125475,

A.M. Al-Areeq, R.A.A. Saleh, M. Ghaleb, S.I. Abba, Z.M. Yaseen. Implication of novel hybrid machine learning model for flood subsidence susceptibility mapping: a representative case study in Saudi Arabia. J. Hydrol., 630 (2024), Article 130692,

R. Al-Ruzouq, A. Shanableh, R. Jena, M.B.A. Gibril, N.A. Hammouri, F. Lamghari. Flood susceptibility mapping using a novel integration of multi-temporal sentinel-1 data and eXtreme deep learning model. Geosci. Front., 15 (3) (2024), p. 101780,

M.J. Alshayeb, H.T. Hang, A.A.A. Shohan, A.A. Bindajam. Novel optimized deep learning algorithms and explainable artificial intelligence for storm surge susceptibility modeling and management in a flood-prone island. Nat. Hazards, 120 (2024), pp. 5099-5128,

A. Amiri, K. Soltani, I. Ebtehaj, H. Bonakdari. A novel machine learning tool for current and future flood susceptibility mapping by integrating remote sensing and geographic information systems. J. Hydrol., 632 (2024), Article 130936,

C. Ben Khalfallah, S. Saidi. Spatiotemporal floodplain mapping and prediction using HEC-RAS - GIS tools: case of the Mejerda river. Tunisia. J. Afr. Earth Sci., 142 (2018), pp. 44-51,

Y. Bhattarai, S. Duwal, S. Sharma, R. Talchabhadel. Leveraging machine learning and open-source spatial datasets to enhance flood susceptibility mapping in transboundary river basin. Int. J. Digital Earth, 17 (1) (2024), p. 2313857,

Brunner, G.W., 2016. HEC-RAS river analysis system user’s manual version 5.0, US Army Corps of Engineers, 962.

D.T. Bui, N.D. Hoang, F. Martínez-Alvarez, P.T.T. Ngo, P.V. Hoa, T.D. Pham, P. Samui, R. Costache. A novel deep learning neural network approach for predicting flash flood susceptibility: a case study at a high frequency tropical storm area. Sci. Total Environ., 701 (2020), p. 134413,

C. Chaabani, M. Chini, R. Abdelfattah, R. Hostache, K. Chokmani. Flood mapping in a complex environment using bistatic TanDEM-X/TerraSAR-X InSAR coherence. Remote Sens., 10 (12) (2018), p. 1873,

R. Chakrabortty, S.C. Pal, F. Rezaie, A. Arabameri, S. Lee, P. Roy, A. Saha, I. Chowdhuri, H. Moayedi. Flash-flood hazard susceptibility mapping in Kangsabati River Basin, India. Geocarto Int., 37 (2022), pp. 6713-6735,

B. Choubin, E. Moradi, M. Golshan, J. Adamowski, F. Sajedi-Hosseini, A. Mosavi. An ensemble prediction of flood susceptibility using multivariate discriminant analysis, classification and regression trees, and support vector machines. Sci. Total Environ., 651 (2019), pp. 2087-2096,

R. Costache, D.T. Bui. Spatial prediction of flood potential using new ensembles of bivariate statistics and artificial intelligence: a case study at the Putna river catchment of Romania. Sci. Total Environ., 691 (2019), pp. 1098-1118,

R. Costache, T.T. Tin, A. Arabameri, A. Craciun, R.S. Ajin, I. Costache, A.M.T. Islam, S.I. Abba, M. Sahana, M. Avand, B.T. Pham. Flash-flood hazard using deep learning based on H2O R package and fuzzy-multicriteria decision-making analysis. J. Hydrol., 609 (2022), p. 127747,

P.R. Dhote, Y. Joshi, A. Rajib, P.K. Thakur, B.R. Nikam, S.P. Aggarwal. Evaluating topography-based approaches for fast floodplain mapping in data-scarce complex-terrain regions: findings from a Himalayan basin. J. Hydrol., 620 (2023), Article 129309,

L. Fang, J. Huang, J. Cai, V. Nitivattananon. Hybrid approach for flood susceptibility assessment in a flood-prone mountainous catchment in China. J. Hydrol., 612 (2022), p. 128091,

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

I. Goodfellow, Y. Bengio, A. Courville. Deep Learning. MIT Press (2016)

S. Hadian, H. Afzalimehr, N. Soltani, E.S. Tabarestani, M. Karakouzian, M. Nazari-Sharabian. Determining flood zonation maps, using new ensembles of multi-criteria decision-making, bivariate statistics, and artificial neural network. Water, 14 (2022),

S. Hammami, L. Zouhri, D. Souissi, A. Souei, A. Zghibi, A. Marzougui, M. Dlala. Application of the GIS based multi-criteria decision analysis and analytical hierarchy process (AHP) in the flood susceptibility mapping (Tunisia). Arabian J. Geosci., 12 (2019), p. 653,

M.A. Hamouda, A.G. Awadallah, R.H. Abdel-Maguid. Extension of the Geomorphic Flood Index classifier to predict flood inundation maps for uncalibrated rainfall depths in arid regions. Nat. Hazards, 120 (2024), pp. 4633-4655,

H.Y. Hong, P. Tsangaratos, I. Ilia, J.Z. Liu, A.X. Zhu, W. Chen. Application of fuzzy weight of evidence and data mining techniques in construction of flood susceptibility map of Poyang County, China. Sci. Total Environ., 625 (2018), pp. 575-588,

H.Y. Hong, D.S. Wang, A.X. Zhu, Y. Wang. Landslide susceptibility mapping based on the reliability of landslide and non-landslide sample. Expert Syst. Appl., 243 (2024), p. 122933,

G. Hu, W. Dai, S. Li, L. Xiong, G. Tang, J. Strobl. Quantification of terrain plan concavity and convexity using aspect vectors from digital elevation models. Geomorphology, 375 (2021), Article 107553,

N. Huu Duy. Flood susceptibility assessment using hybrid machine learning and remote sensing in Quang Tri province, Vietnam. Trans. Gis, 26 (2022), pp. 2776-2801,

A. Jamali, S.K. Roy, L. Hashemi Beni, B. Pradhan, J. Li, P. Ghamisi. Residual wave vision U-Net for flood mapping using dual polarization Sentinel-1 SAR imagery. Int. J. Appl. Earth Observ. Geoinform., 127 (2024), Article 103662,

M. Kaiser, S. Günnemann, M. Disse. Regional-scale prediction of pluvial and flash flood susceptible areas using tree-based classifiers. J. Hydrol., 612 (2022), Article 128088,

R.B. Kheir, M.H. Greve, C. Abdallah, T. Dalgaard. Spatial soil zinc content distribution from terrain parameters: a GIS-based decision-tree model in Lebanon. Environ. Pollut., 158 (2010), pp. 520-528,

K. Khosravi, H. Shahabi, B.T. Pham, J. Adamowski, A. Shirzadi, B. Pradhan, J. Dou, H.-B. Ly, G. Gróf, H.L. Ho. 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. LeCun, Y. Bengio, G.J.N. Hinton. . Deep Learning, 521 (2015), pp. 436-444

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

J. Liu, J.Y. Wang, J.N. Xiong, W.M. Cheng, H.Z. Sun, Z.W. Yong, N. Wang. Hybrid models incorporating bivariate statistics and machine learning methods for flash flood susceptibility assessment based on remote sensing datasets. Remote Sens., 13 (23) (2021), p. 4945,

J. Liu, J.Y. Wang, J.N. Xiong, W.M. Cheng, Y. Li, Y.F. Cao, Y.F. 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 (2022), pp. 9817-9846,

Y.S. Liu, Z.S. Yang, Y.H. Huang, C.J. Liu. Spatiotemporal evolution and driving factors of China’s flash flood disasters since 1949. Sci. China-Earth Sci., 61 (2018), pp. 1804-1817,

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,

Q. Miao, D. Yang, H. Yang, Z. Li. Establishing a rainfall threshold for flash flood warnings in China’s mountainous areas based on a distributed hydrological model. J. Hydrol., 541 (2016), pp. 371-386,

S. Moghim, M.A. Gharehtoragh, A. Safaie. Performance of the flood models in different topographies. J. Hydrol., 620 (2023), Article 129446,

A. Mosavi, P. Ozturk, K.-W. Chau. Flood prediction using machine learning models: literature review. Water, 10 (2018), p. 1536,

H.D. Nguyen, Q.T. Bui, Q.H. Nguyen, T.G. Nguyen, L.T. Pham, X.L. Nguyen, P.L. Vu, T.H.T. Nguyen, A.T. Nguyen, A.I. Petrisor. A novel hybrid approach to flood susceptibility assessment based on machine learning and land use change. Case study: a river watershed in Vietnam. Hydrol. Sci. J., 67 (2022), pp. 1065-1083,

H. Özdemir, M.B. Koçyigit, D. Akay. Flood susceptibility mapping with ensemble machine learning: a case of Eastern Mediterranean basin, Turkiye. Stochastic Environ. Res. Risk Assess., 37 (2023), pp. 4273-4290,

B.T. Pham, D. Tien Bui, H.R. Pourghasemi, P. Indra, M.B. Dholakia. Landslide susceptibility assesssment in the Uttarakhand area (India) using GIS: a comparison study of prediction capability of naïve bayes, multilayer perceptron neural networks, and functional trees methods. Theor. Appl. Climatol., 128 (2017), pp. 255-273,

K. Plataridis, Z. Mallios. Flood susceptibility mapping using hybrid models optimized with Artificial Bee Colony. J. Hydrol., 624 (2023), Article 129961,

H.R. Pourghasemi, S.V. Razavi-Termeh, N. Kariminejad, H.Y. Hong, W. Chen. An assessment of metaheuristic approaches for flood assessment. J. Hydrol., 582 (2020), p. 124536,

B. Pradhan, S. Lee, A. Dikshit, H. Kim. Spatial flood susceptibility mapping using an explainable artificial intelligence (XAI) model. Geosci. Front., 14 (2023), Article 101625,

Y.W. Rabby, M.B. Hossain, J. Abedin. Landslide susceptibility mapping in three Upazilas of Rangamati hill district Bangladesh: application and comparison of GIS-based machine learning methods. Geocarto Int., 37 (2022), pp. 3371-3396,

A. Rajib, Z. Liu, V. Merwade, A.A. Tavakoly, M.L. Follum. Towards a large-scale locally relevant flood inundation modeling framework using SWAT and LISFLOOD-FP. J. Hydrol., 581 (2020), Article 124406,

S. ReferencesAfshari, A.A. Tavakoly, M.A. Rajib, X. Zheng, M.L. Follum, E. Omranian, B.M. Fekete. Comparison of new generation low-complexity flood inundation mapping tools with a hydrodynamic model. J. Hydrol., 556 (2018), pp. 539-556,

C.S. Renschler, Z. Wang. Multi-source data fusion and modeling to assess and communicate complex flood dynamics to support decision-making for downstream areas of dams: The 2011 hurricane irene and schoharie creek floods, NY. Int. J. Appl. Earth Observ. Geoinform., 62 (2017), pp. 157-173,

A. Safaei-Moghadam, D. Tarboton, B. Minsker. Estimating the likelihood of roadway pluvial flood based on crowdsourced traffic data and depression-based DEM analysis. Nat. Hazards Earth Syst. Sci., 23 (2023), pp. 1-19

H. Saito, D. Nakayama, H. Matsuyama. Comparison of landslide susceptibility based on a decision-tree model and actual landslide occurrence: the Akaishi Mountains, Japan. Geomorphology, 109 (2009), pp. 108-121,

A. Saleh, A. Yuzir, N. Sabtu, S.K.M. Abujayyab, M.R. Bunmi, Q.B. Pham. Flash flood susceptibility mapping in urban area using genetic algorithm and ensemble method. Geocarto Int., 37 (2022), pp. 10199-10228,

S.T. Seydi, Y. Kanani-Sadat, M. Hasanlou, R. Sahraei, J. Chanussot, M. Amani. Comparison of machine learning algorithms for flood susceptibility mapping. Remote Sens., 15 (1) (2023), p. 192,

H. Shahabi, A. Shirzadi, K. Ghaderi, E. Omidvar, N. Al-Ansari, J.J. Clague, M. Geertsema, K. Khosravi, A. Amini, S. Bahrami, O. Rahmati, K. Habibi, A. Mohammadi, H. Nguyen, A.M. Melesse, B.B. Ahmad, A. Ahmad. Flood detection and susceptibility mapping using sentinel-1 remote sensing data and a machine learning approach: hybrid intelligence of bagging ensemble based on K-nearest neighbor classifier. Remote Sens., 12 (2020), p. 266,

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 (2021), Article 101100,

A. Shirzadi, K. Solaimani, M.H. Roshan, A. Kavian, K. Chapi, H. Shahabi, S. Keesstra, B. Bin Ahmad, D.T. Bui. Uncertainties of prediction accuracy in shallow landslide modeling: sample size and raster resolution. Catena, 178 (2019), pp. 172-188,

M. Siegert, R.B. Alley, E. Rignot, J. Englander, R. Corell. Twenty-first century sea-level rise could exceed IPCC projections for strong-warming futures. One Earth, 3 (2020), pp. 691-703,

L. Smith, Q. Liang, P. James, W. Lin. Assessing the utility of social media as a data source for flood risk management using a real-time modelling framework. J. Flood Risk Manag., 10 (2017), pp. 370-380,

X. Tang, J. Li, M. Liu, W. Liu, H. Hong. Flood susceptibility assessment based on a novel random Naïve Bayes method: a comparison between different factor discretization methods. CATENA, 190 (2020), Article 104536,

X. Tang, T. Machimura, W. Liu, J. Li, H. Hong. A novel index to evaluate discretization methods: a case study of flood susceptibility assessment based on random forest. Geosci. Front., 12 (2021), Article 101253,

M.S. Tehrany, B. Pradhan, M.N. Jebur. Spatial prediction of flood susceptible areas using rule based decision tree (DT) and a novel ensemble bivariate and multivariate statistical models in GIS. J. Hydrol., 504 (2013), pp. 69-79,

M. Tehrany, F. Shabani, M. Jebur, H. Hong, W. Chen, X. Xie. GIS-based spatial prediction of flood prone areas using standalone frequency ratio, logistic regression, weight of evidence and their ensemble techniques. Geomatics Nat. Hazards Risk, 8 (2017), pp. 1538-1561,

S.V.R. Termeh, A. Kornejady, H.R. Pourghasemi, S. Keesstra. Flood susceptibility mapping using novel ensembles of adaptive neuro fuzzy inference system and metaheuristic algorithms. Sci. Total Environ., 615 (2018), pp. 438-451,

D. Tien Bui, T.A. Tuan, H. Klempe, B. Pradhan, I. Revhaug. Spatial prediction models for shallow landslide hazards: a comparative assessment of the efficacy of support vector machines, artificial neural networks, kernel logistic regression, and logistic model tree. Landslides, 13 (2016), pp. 361-378,

D. Tien Bui, K. Khosravi, H. Shahabi, P. Daggupati, J.F. Adamowski, A.M. Melesse, B. Thai Pham, H.R. Pourghasemi, M. Mahmoudi, S. Bahrami. Flood spatial modeling in northern Iran using remote sensing and gis: a comparison between evidential belief functions and its ensemble with a multivariate logistic regression model. Remote Sens., 11 (2019), p. 1589,

D. Tien Bui, N.-D. Hoang, F. Martínez-Álvarez, P.-T.-T. Ngo, P.V. Hoa, T.D. Pham, P. Samui, R. Costache. A novel deep learning neural network approach for predicting flash flood susceptibility: a case study at a high frequency tropical storm area. Sci. Total Environ., 701 (2020), Article 134413,

P. Tsangaratos, I. Ilia, A.A. Chrysafi, I. Matiatos, W. Chen, H.Y. Hong. Applying a 1D convolutional neural network in flood susceptibility assessments-the case of the island of Euboea, Greece. Remote Sens., 15 (2023),

C.P. Wang, Y.C. Lin, Z.W. Tao, J.Y. Zhan, W.K. Li, H.B. Huang. An inverse-occurrence sampling approach for urban flood susceptibility mapping. Remote Sens., 15 (2023),

R. Wei, C. Ye, T. Sui, Y. Ge, Y. Li, J. Li. Combining spatial response features and machine learning classifiers for landslide susceptibility mapping. Int. J. Appl. Earth Observ. Geoinform., 107 (2022), Article 102681,

L.K. Widya, F. Rezaie, W.J. Lee, C.W. Lee, N. Nurwatik, S.R. Lee. Flood susceptibility mapping of Cheongju, South Korea based on the integration of environmental factors using various machine learning approaches. J. Environ. Manag., 364 (2024),

X.M. Yuan, Y.S. Liu, Y.H. Huang, F.C. Tian. An approach to quality validation of large-scale data from the Chinese Flash Flood Survey and Evaluation (CFFSE). Nat. Hazards, 89 (2017), pp. 693-704,

X.L. Zhang, A.Q. Kang, M. Ye, Q.X. Song, X.H. Lei, H. Wang. Influence of terrain factors on urban pluvial flooding characteristics: a case study of a small Watershed in Guangzhou, China. Water, 15 (2023),

S.H. Zhang, B.Z. Pan. An urban storm-inundation simulation method based on GIS. J. Hydrol., 517 (2014), pp. 260-268,

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

G. Zhao, B. Pang, Z. Xu, D. Peng, D. Zuo. Urban flood susceptibility assessment based on convolutional neural networks. J. Hydrol., 590 (2020), Article 125235,

Y. Zheng, Y.Z. Xie, X.J. Long. A comprehensive review of Bayesian statistics in natural hazards engineering. Nat. Hazards, 108 (2021), pp. 63-91,