Machine learning modelling of flood susceptibility in a tropical river basin of South India

N. Anjali; Girish Gopinath

doi:10.64866/j.ijdscr.2026.10023

Authors

N. Anjali Department of Climate Variability and Aquatic Ecosystems, Kerala University of Fisheries and Ocean Studies (KUFOS), Vypin Island, Kochi 682 508, India Author
Girish Gopinath Department of Climate Variability and Aquatic Ecosystems, Kerala University of Fisheries and Ocean Studies (KUFOS), Vypin Island, Kochi 682 508, India Author https://orcid.org/0000-0002-0404-6538

DOI:

https://doi.org/10.64866/j.ijdscr.2026.10023

Keywords:

Flood Susceptibility modelling, Achankovil, Kerala, India

Abstract

Flooding is a major recurring hazard in tropical monsoon climates, causing extensive damage to lives, infrastructure, and economic activities. The Achankovil River Basin in southern India is highly susceptible to recurrent monsoon-induced flooding, particularly in its low-lying downstream reaches. This study assesses flood susceptibility in the Achankovil River Basin using a machine-learning Maximum Entropy (MaxEnt) model and identifies the key environmental factors controlling flood occurrence. Ten geo-environmental variables, such as geomorphology, soil texture, Vertical Distance to Channel Network (VDCN), slope angle, rainfall, land use/land cover (LU/LC), distance from streams, Topographic Wetness Index (TWI), upslope curvature, and downslope curvature, were used together with a detailed flood inventory comprising 677 flood affected locations. The model is validated using the Receiver Operating Characteristic (ROC) curve and area under the curve (AUC) value (ROC–AUC). The predicted flood susceptibility map is further grouped into low, moderate, high, and very high susceptibility regions. The results show that high and very high flood susceptibility zones are mainly concentrated in the downstream and central lowland regions along major river channels, characterised by low elevation, gentle slopes, and proximity to drainage networks, which favours inundation. In contrast, the eastern highland sector of the study area exhibits predominantly low flood susceptibility zones. The model validation returns an AUC value of 0.89, indicating good model accuracy and reliability. Besides, the model identified Vertical Distance to the Channel Network (VDCN) as the most important factor, followed by rainfall and slope angle. The findings confirm the robustness of the maximum entropy model and provide valuable insights for flood early warning and land-use development in the study area.

Downloads

Download data is not yet available.

References

Achu, A.L., Aju, C.D., Raicy, M.C., Bhadran, A., George, A., Surendran, U., Girishbai, D., Ajayakumar, P., Gopinath, G., Pradhan, B., 2025. Improved flood risk assessment using multimodel ensemble machine learning techniques in a tropical river basin of Southern India. Physical Geography 46, 127–155. https://doi.org/10.1080/02723646.2025.2464536

Achu, A.L., Gopinath, G., Surendran, U., 2023. Machine learning framework for flood susceptibility modeling in a fastgrowing urban city of southern India, in: Timbadiya, P.V., Patel, P.L., Singh, V.P., Mirajkar, A.B. (Eds.), Geospatial and Soft Computing Techniques. HYDRO 2021. Lecture Notes in Civil Engineering. Springer, Singapore. volume 339. https://doi.org/10.1007/978-981-99-1901-7_43.

Ahmed, M.R., Rahaman, K.R., Kok, A., Hassan, Q.K., 2017. Remote sensing-based quantification of the impact of flash flooding on the rice production: A case study over Northeastern Bangladesh. Sensors 17, 2347. https://doi.org/10.3390/s17102347.

Ajin, R.S., Loghin, A.M., Vinod, P.G., Jacob, M.K., 2019. Flood hazard zone mapping in the tropical Achankovil river basin in Kerala: a study using remote sensing data and geographic information system. J Wetlands Biodiv 9, 45–58.

Allocca, V., Coda, S., Calcaterra, D., Vita, P., 2022. Groundwater rebound and flooding in the Naples’ periurban area (Italy). Journal of Flood Risk Management 15, 12775. https://doi.org/10.1111/jfr3.12775.

Azare, A., 2021. Risk analysis of urban flood in Bandar Abbas using machine learning model and Analytic hierarchy process. Environmental Erosion Research Journal 11, 36–57. https://doi.org/10.52547/jeer.11.1.36.

Beven, K., 1979. On the generalized kinematic routing method. Water Resources Research 15, 1238–1242. https://doi.org/10.1029/WR015i005p01238.

Central Groundwater Board, 2019. Dynamic Groundwater Resources of Kerala. CGWB Publ, Pathanamthitta district.

Chakrabortty, R., Chandra Pal, S., Rezaie, F., Arabameri, A., Lee, S., Roy, P., Moayedi, H., 2022. Flash-flood hazard susceptibility mapping in Kangsabati River Basin, India. Geocarto International 37, 6713–6735. https://doi.org/10.1080/10106049.2021.1953618.

Chattopadhyay, S., Edwards, D.R., Yu, Y., Hamidisepehr, A., 2017. An assessment of climate change impacts on future water availability and droughts in the Kentucky River Basin. Environ. Process. 4, 477–507. https://doi.org/10.1007/s40710-017-0259-2.

Darabi, H., Haghighi, A.T., Mohamadi, M.A., Rashidpour, M., Ziegler, A.D., Hekmatzadeh, A.A., Kløve, B., 2020. Urban flood risk mapping using data-driven geospatial techniques for a flood-prone case area in Iran. Nord. Hydrol 51, 127–142. https://doi.org/10.2166/nh.2019.090.

Das, S., 2019. Geospatial mapping of flood risk and hydrogeomorphic response to the floods in Ulhas basin, India. Remote Sens. Appl.: Society and Environment 14, 60–74. https://doi.org/10.1016/j.rsase.2019.02.006.

Das, S., Gupta, A., 2021. Multi-criteria decision based geospatial mapping of flood susceptibility and temporal hydrogeomorphic changes in the Subarnarekha basin, India. Geoscience Frontiers 12, 101206. https://doi.org/10.1016/j.gsf.2021.101206.

Davoudi Moghaddam, D., Haghizadeh, A., 2020. Detection of susceptible areas to flooding and its most important contributing factors using the maximum entropy model in the Tashan watershed, Khuzestan. Watershed Management Research Journal 33, 94–109.

De Risi, R., Jalayer, F., Paola, F., Carozza, S., Yonas, N., Giugni, M., Gasparini, P., 2020. From flood risk mapping toward reducing vulnerability: the case of Addis Ababa. Natural Hazards 100, 387–415. https://doi.org/10.1007/s11069-019-03817-8.

Fawcett, T., 2006. Introduction to receiver operator curves. Pattern Recognit Lett 27, 861–874. https://doi.org/10.1016/j.patrec.2005.10.010.

Feloni, E., Mousadis, I., Baltas, E., 2020. Flood vulnerability assessment using a GIS‐based multi‐criteria approach-The case of Attica region. Journal of Flood Risk Management 13, 12563. https://doi.org/10.1111/jfr3.12563.

Gorsevski, P.V., Gessler, P.E., Foltz, R.B., Elliot, W.J., 2006. Spatial prediction of landslide hazard using logistic regression and ROC analysis. Trans GIS 10, 395–415. https://doi.org/10.1111/j.1467-9671.2006.01004.x.

Hanley, J.A., McNeil, B.J., 1982. The meaning and use of the area under a receiver operating characteristic (ROC) curve. Radiology 143, 29. https://doi.org/10.1148/radiology.143.1.7063747.

Hosmer, D.W., Lemeshow, S., 2000. Applied Logistic Regression. Second ed., Wiley, New York. https://doi.org/10.1002/0471722146.

Javidan, N., Kavian, A., Pourghasemi, H.R., Conoscenti, C., Jafarian, Z., Rodrigo-Comino, J., 2021. Evaluation of multihazard map produced using MaxEnt machine learning technique. Sci. Rep. 11, 6496. https://doi.org/10.1038/s41598-021-85862-7.

Kazakis, N., Kougias, I., Patsialis, T., 2015. Assessment of flood hazard areas at a regional scale using an index-based approach and Analytical Hierarchy Process: Application in Rhodope-Evros region, Greece. Science of the Total Environment 538, 555–563. https://doi.org/10.1016/j.scitotenv.2015.08.055.

Khan, Z.A., Jhamnani, B., 2024. Development of flood susceptibility map using a GIS-based AHP approach: a novel case study on Idukki district, India. Journal of Spatial Science 69, 409–442. https:// doi.org/10.1080/14498596.2023.2236051.

Kulithalai Shiyam Sundar, P., Kundapura, S., 2023. Spatial mapping of flood susceptibility using decision tree-based machine learning models for the Vembanad Lake System in Kerala, India. Journal of Water Resources Planning and Management 149, 04023052. https://doi.org/10.1061/JWRMD5.WRENG-5858.

Kumar, R., Singh, R.D., Seth, S.M., 1999. Regional flood formulas for seven subzones of zone 3 of India. Journal of Hydrologic Engineering 4, 240–244. https://doi.org/10.1061/(ASCE)1084-0699(1999)4:3(240).

Lappas, I., Kallioras, A., 2019. Flood susceptibility assessment through GIS-based multi-criteria approach and analytical hierarchy process (AHP) in a river basin in Central Greece. Int Res J Eng Technol 6, 738–751.

Maharjan, K., Dangol, S., 2024. Climate Change and flood vulnerability analysis in the Narayani River of Nepal. Journal on Geoinformatics Nepal, 19–33. https://doi.org/10.3126/njg.v23i1.66047.

Mashao, F.M., Mothapo, M.C., Munyai, R.B., Letsoalo, J.M., Mbokodo, I.L., Muofhe, T.P., Matsane, W., Chikoore, H., 2023. Extreme rainfall and flood risk prediction over the East Coast of South Africa. Water 15, 50. https://doi.org/10.3390/w15010050.

Mishra, V., Aaadhar, S., Shah, H., Kumar, R., Pattanaik, D.R., Tiwari, A.D., 2018. The Kerala flood of 2018: combined impact of extreme rainfall and reservoir storage. Hydrology and Earth System Sciences Discussions, 1–13 https://doi.org/10.5194/hess-2018-480.

Moradi, E., Rajabi, A., Shabanlou, S., Yosefvand, F., 2021. Identification of the most important environmental variables in spatial prediction of flood-prone areas using the maximum entropy model in parts of Golestan Province. Iranian J. Soil Water Res. 52, 899–915. https://doi.org/10.22059/IJSWR.2021.316143.668851.

Murali, K.V., Srinivasan, K., 2025. GIS and AHP-based flood susceptibility mapping: A case study of Chalakudy River Basin, Kerala, India. International Journal of Environment and Climate Change 15, 18–34. https://doi.org/10.9734/ijecc/2025/v15i94992.

Norallahi, M., Seyed Kaboli, H., 2021. Urban flood hazard mapping using machine learning models: GARP, RF, MaxEnt and NB. Natural Hazards 106, 119–137. https://doi.org/10.1007/s11069-020-04453-3.

Parthasarathy, K.S.S., Deka, P.C., Saravanan, S., Abijith, D., Jennifer, J.J., 2021. Assessing the impact of 2018 tropical rainfall and the consecutive flood-related damages for the state of Kerala, India, in: Disaster Resilience and Sustainability. Elsevier, p. 379–395. https://doi.org/10.1016/B978-0-323-85195-4.00013-5.

Petry, B., 2002. Coping with floods: complementarity of structural and non-structural measures, in: Proceedings 2nd International Symposium on Flood Defence, Beijing, China.

Phillips, S.J., Anderson, R.P., Schapire, R.E., 2006. Maximum entropy modeling of species geographic distributions. Ecological Modelling 190, 231–259. https://doi.org/10.1016/j.ecolmodel.2005.03.026.

Prasad, M.B.K., Ramanathan, A.L., 2005. Solute sources and processes in the Achankovil River Basin, Western Ghats, Southern India/Sources de Solutés et Processus Associés Dans le Bassin du Fleuve Achankovil, Ghats Occidentaux, Inde du Sud. Hydrological Sciences Journal 50. https://doi.org/10.1623/hysj.50.2.341.61798.

Qasim, A.B., Isazade, V., Berndtsson, R., 2024. Flood susceptibility prediction using MaxEnt and frequency ratio modeling for Kokcha River in Afghanistan. Natural Hazards 120, 1367–1394. https://doi.org/10.1007/s11069-023-06232-2.

Rahmati, O., Zeinivand, H., Besharat, M., 2016. Flood hazard zoning in Yasooj region, Iran, using GIS and multi-criteria decision analysis. Geomatics, Natural Hazards and Risk 7, 1000–1017. https://doi.org/10.1080/19475705.2015.1045043.

Riadi, B., Barus, B., Yanuar, M.J.P., Pramudya, B., 2018. Identification and delineation of areas flood hazard using high accuracy of DEM data. IOP Conference Series: Earth and Environmental Science 149, 012035. https://doi.org/10.1088/1755-1315/149/1/012035.

Rodda, J.C., 1970. Rainfall excesses in the United Kingdom. Transactions of the Institute of British Geographers, 49–60 https://doi.org/10.2307/621640.

Saravanan, S., Abijith, D., Reddy, N.M., Kss, P., Janardhanam, N., Sathiyamurthi, S., Sivakumar, V., 2023. Flood susceptibility mapping using machine learning boosting algorithms techniques in Idukki district of Kerala India. Urban Climate 49, 101503. https://doi.org/10.1016/j.uclim.2023.101503.

Shahabi, H., Shirzadi, A., Ronoud, S., Asadi, S., Pham, B.T., Mansouripour, F., Geertsema, M., Clague, J.J., Bui, D.T., 2021. Flash flood susceptibility mapping using a novel deep learning model based on deep belief network, back propagation and genetic algorithm. Geosci Front 12, 101100. https://doi.org/10.1016/j.gsf.2020.10.007.

Shreevastav, B.B., Tiwari, K.R., Mandal, R.A., Singh, B., 2022. Flood risk modeling in the southern Bagmati corridor, Nepal (a study from Sarlahi and Rautahat, Nepal). Progress in Disaster Science 16, 100260. https://doi.org/10.1016/j.pdisas.2022.100260.

Smith, K., Ward, R., 1998. Floods: Physical Processes and Human Impacts. Wiley.

Sudheer, K.P., Bhallamudi, S.M., Narasimhan, B., Thomas, J., Bindhu, V.M., Vema, V., Kurian, C., 2019. Role of dams on the floods of August 2018 in Periyar River Basin, Kerala. Current Science 116, 780–794. https://doi.org/10.18520/cs/v116/i5/780-794.

Wang, Z., Lai, C., Chen, X., Yang, B., Zhao, S., Bai, X., 2015. Flood hazard risk assessment model based on random forest. Journal of Hydrology 527, 1130–1141. https://doi.org/10.1016/j.jhydrol.2015.06.008.