Flood Area Prediction using a Stacked Ensemble of Tree-Based Algorithms

Abstract

Floods cause significant loss of life, property damage, and long-term socioeconomic disruptions, with over 100 annual deaths globally. This research addresses the drawbacks of the existing models, such as overfitting effects, inadequate dataset and limited study areas through the adoption of a stacked ensemble-based model. The model contained five different tree - based models namely hoeffding tree, decision tree, functional tree, reduced error pruning (REP) tree and decision stump algorithms. The model was implemented as a system using MATLAB Simulink, version 2020a on laptop with 4GB Memory. Experimental results indicate that REP Tree performed better than other four individual tree algorithms with accuracy of 98.74%, 97.81% and 97.43% for Dataset A, Dataset B and Dataset C respectively. For Dataset A, stacked ensemble model performed better than single algorithms with accuracy, precision, specificity, f1score and recall of 99.62%, 99.51%, 99.51%, 99.63% and 99.73% respectively. For Dataset B, stacked ensemble model also performed better than single algorithms with accuracy, precision, specificity, f1score and recall of 98.45%, 99.11%, 98.12%, 97.37% and 99.06% respectively. For Dataset C, stacked ensemble model performed better than single algorithms with accuracy, precision, specificity, f1score and recall of 98.75%, 99.25%, 99.64%, 99.90% and 99.24% respectively. Our model’s 99.62% accuracy on Dataset A demonstrates potential for integration with real-time sensor networks, enabling scalable flood early-warning systems in vulnerable regions like Lagos and Kuala Lumpur.

Keywords

• Ensemble
• Flood
• Stacked
• Tree Based

References

1. I. M. Magami, S. Yahaya,K. Mohammed, “Causes and consequences of flooding in Nigeria: a review Alternative coagulants for water clarification in low-and middle-income communities View project”, no November 2016, 2014, [Online]. Available at: https://www.researchgate.net/publication/262562763
2. V. Nhu, P. T. Ngo, T. D. Pham, J. Dou,X. Song, “A New Hybrid Firefly – PSO Optimized Random Subspace Tree Intelligence for Torrential Rainfall-Induced Flash Flood Susceptible Mapping”, bll 1–18, 2020.
3. O. Petrucci, “Review article: Factors leading to the occurrence of flood fatalities: A systematic review of research papers published between 2010 and 2020”, Nat. Hazards Earth Syst. Sci., vol 22, no 1, bll 71–83, 2022, doi: 10.5194/nhess-22-71-2022.
4. A. Arora et al., “Optimization of state-of-the-art fuzzy-metaheuristic ANFIS-based machine learning models for fl ood susceptibility prediction mapping in the Middle Ganga Plain , India”, Sci. Total Environ., vol 750, bl 141565, 2021, doi: 10.1016/j.scitotenv.2020.141565.
5. S. Žurovec, J.; Čadro, “SOIL-WATER CHARACTERISTIC CURVE AND RETENTION OF WATER FOR DIFFERENT TYPES OF AGRICULTURAL SOILS IN TUZLA CANTON Jasminka Žurovec 1 , Sabrija Čadro 1 Original scientific paper”, vol LXI, no 66, bll 1–6, 2013.
6. M. G. Grillakis, A. G. Koutroulis, J. Komma, I. K. Tsanis, W. Wagner,G. Blöschl, “Initial soil moisture effects on flash flood generation – A comparison between basins of contrasting hydro-climatic conditions”, J. Hydrol., vol 541, bll 206–217, 2016, doi: 10.1016/j.jhydrol.2016.03.007.
7. A. Rakhim, Nurnawaty, “An Environmental Development Study: The Effect of Vegetation to Reduce Runoff”, IOP Conf. Ser. Earth Environ. Sci., vol 382, no 1, bll 1–6, 2019, doi: 10.1088/1755-1315/382/1/012027.
8. J. Geris et al., “Surface water-groundwater interactions and local land use control water quality impacts of extreme rainfall and flooding in a vulnerable semi-arid region of Sub-Saharan Africa”, J. Hydrol., vol 609, no September 2021, bl 127834, 2022, doi: 10.1016/j.jhydrol.2022.127834.

9. P. O. Youdeowei, H. O. Nwankwoala,D. D. Desai, “Dam structures and types in Nigeria: Sustainability and effectiveness”, Water Conserv. Manag., vol 3, no 1, bll 20–26, 2019, doi: 10.26480/wcm.01.2019.20.26.
10. M. Antonetti, C. Horat, I. V Sideris, M. Zappa, “Ensemble flood forecasting considering dominant runoff processes – Part 1 : Set-up and application to nested basins ( Emme , Switzerland )”, bll 19–40, 2019.
11. A. Shirzadi, S. Asadi, H. Shahabi, S. Ronoud, J. J. Clague, “A novel ensemble learning based on Bayesian Belief Network coupled with an extreme learning machine for flash flood susceptibility mapping”, Eng. Appl. Artif. Intell., vol 96, no September, bl 103971, 2020, doi: 10.1016/j.engappai.2020.103971.
12. A. V Kalyuzhnaya, A. V Boukhanovsky, “Computational uncertainty management for coastal flood prevention system”, Procedia - Procedia Comput. Sci., vol 51, bll 2317–2326, 2015, doi: 10.1016/j.procs.2015.05.397.
13. X. Zhang, E. N. Anagnostou, C. S. Schwartz, “NWP-Based Adjustment of IMERG Precipitation for Flood-Inducing Complex Terrain Storms : Evaluation over CONUS”, Am. Rom. Acad. Arts Sci., 2018, doi: 10.3390/rs10040642.
14. S. N. Jonkman, A. Curran, and L. M. Bouwer, “Floods have become less deadly: an analysis of global flood fatalities 1975–2022,” Nat. Hazards, vol. 120, no. 7, pp. 6327–6342, 2024, doi: 10.1007/s11069-024-06444-0.
15. Q. B. Pham et al., “Evaluation of various boosting ensemble algorithms for predicting flood hazard susceptibility areas,” Geomatics, Nat. Hazards Risk, vol. 12, no. 1, pp. 2607–2628, 2021, doi: 10.1080/19475705.2021.1968510.
16. A. Towfiqul Islam et al., “Flood susceptibility modelling using advanced ensemble machine learning models,” Geosci. Front., vol. 12, no. 3, 2021, doi: 10.1016/j.gsf.2020.09.006.
17. O. J. Adetunji, I. A. Adeyanju,A. O. Esan, “Flood Areas Prediction in Nigeria using Artificial Neural Network”, 2023 Int. Conf. Sci. Eng. Bus. Sustain. Dev. Goals, bll 1–6, 2023, doi: 10.1109/SEB-SDG57117.2023.10124629.
18. T. Rahman et al., “Flood Prediction Using Ensemble Machine Learning Model,” 2023 5th Int. Conf. Hum. - Comput. Interact. Optim. Robot. Appl. (HORA), IEEE, no. July, 2023, doi: 10.1109/HORA58378.2023.10156673.
19. K. R. Oloruntoba, K. Taiwo, and J. B. Agbogun, “Flood Prediction in Nigeria Using Ensemble Machine Learning Techniques,” Ilorin J. Sci., vol. 10, no. 1, 2023, doi: 10.54908/iljs.2023.10.01.004.
20. S. Hajji et al., “Enhancing flood prediction through remote sensing, machine learning, and Google Earth Engine,” Front. Water, vol. 7, no. March, 2025, doi: 10.3389/frwa.2025.1514047.
21. E. M. Ferrouhi and I. Bouabdallaoui, “A comparative study of ensemble learning algorithms for high-frequency trading,” Sci. African, vol. 24, no. August 2023, p. e02161, 2024, doi: 10.1016/j.sciaf.2024.e02161.
22. I. O. Adelekan, “Flood risk management in the coastal city of Lagos, Nigeria”, J. Flood Risk Manag., vol 9, no 3, bll 255–264, 2016, doi: 10.1111/jfr3.12179.
23. A. Domeneghetti et al., “Flood risk mitigation in developing countries: Deriving accurate topographic data for remote areas under severe time and economic constraints”, J. Flood Risk Manag., vol 8, no 4, bll 301–314, 2015, doi: 10.1111/jfr3.12095.
24. A. O. Julius, A. O. Ayokunle,F. O. Ibrahim, “Early Diabetic Risk Prediction using Machine Learning Classification Techniques”, Int. J. Innov. Sci. Res. Technol., vol 6, no 9, bll 502–507, 2021.
25. H. Bao et al., “Coupling ensemble weather predictions based on TIGGE database with Grid-Xinanjiang model for flood forecast”, Adv. Geosci., bll 61–67, 2011, doi: 10.5194/adgeo-29-61-2011.
26. E. H. Ighile, H. Shirakawa, en H. Tanikawa, “A Study on the Application of GIS and Machine Learning to Predict Flood Areas in Nigeria”, Sustain., vol 14, no 9, 2022, doi: 10.3390/su14095039.
27. S. H. Elsafi, “Artificial Neural Networks ( ANNs ) for flood forecasting at Dongola Station in the River Nile , Sudan Sulafa Hag Elsafi”, ALEXANDRIA Eng. J., 2019, doi: 10.1016/j.aej.2014.06.010.
28. J. Wu, H. Liu, G. Wei, T. Song, C. Zhang,H. Zhou, “Flash flood forecasting using support vector regression model in a small mountainous catchment”, Water (Switzerland), vol 11, no 7, 2019, doi: 10.3390/w11071327.
29. M. Madhuram, A. Kakar, A. Sharma, S. Chaudhuri, “Flood Prediction and warning system using SVM and ELM models .”, no 4, bll 5366–5369, 2019, doi: 10.35940/ijrte.D7573.118419.
30. R. Costache, D. Tien, “Identi fi cation of areas prone to fl ash- fl ood phenomena using multiple- criteria decision-making , bivariate statistics , machine learning and their ensembles”, Sci. Total Environ., vol 712, bl 136492, 2020, doi: 10.1016/j.scitotenv.2019.136492.
31. B. T. Pham et al., “Improved flood susceptibility mapping using a best first decision tree integrated with ensemble learning techniques”, Geosci. Front., vol 12, no 3, bl 101105, 2021, doi: 10.1016/j.gsf.2020.11.003.
32. S. Janizadeh et al., “Prediction Success of Machine Learning Methods for Flash Flood sustainability Prediction Success of Machine Learning Methods for Flash Flood Susceptibility Mapping in the Tafresh Watershed , Iran”, no September, 2019, doi: 10.3390/su11195426.
33. N. M. Nawi, M. Makhtar, M. Z. Salikon,Z. A. Afip, “A comparative analysis of classification techniques on predicting flood risk”, vol 18, no 3, bll 1342–1350, 2020, doi: 10.11591/ijeecs.v18.i3.pp1342-1350.
34. N. Razali, S. Ismail,A. Mustapha, “Machine learning approach for flood risks prediction”, vol 9, no 1, bll 73–80, 2020, doi: 10.11591/ijai.v9.i1.pp73-80.
35. J. H. Rao, D. Patle,S. K. Sharma, “Remote Sensing and GIS Technique for Mapping Land Use / Land Cover of Kiknari Watershed”, Ind. J. Pure App. Biosci., vol 8, bll 455–463, 2020.
36. A. Ali, M. Ahmed, S. Naeem, S. Anam,M. M. Ahmed, “An Unsupervised Machine Learning Algorithms: Comprehensive Review”, Int. J. Comput. Digit. Syst., vol 20, no April, bll 2210–142, 2023, doi: 10.12785/ijcds/130172.
37. A. H. Tanim, C. B. McRae, H. Tavakol‐davani, E. Goharian, “Flood Detection in Urban Areas Using Satellite Imagery and Machine Learning”, Water (Switzerland), vol 14, no 7, 2022, doi: 10.3390/w14071140.
38. O. J. Adetunji, I. A. Adeyanju, A. O. Esan, A. A. Sobowale, “Flood Image Classification using Convolutional Neural Networks”, ABUAD J. Eng. Res. Dev., vol 6, no 2, bll 113–121, 2023.
39. P. Domingos and G. Hulten, “Mining High-Speed Data Streams,” Proc. 6th ACM SIGKDD Int. Conf. Knowl. Discov. Data Mining, Bost., pp. 71–80, 2000.
40. J. Gama, “Functional trees for classification,” Proc. 2001 IEEE Int. Conf. Data Min., pp. 147–154, 2001.
41. I. H. Witten, E. Frank, and M. A. Hall, “Data Mining: Practical machine learning tools and techniques,” Morgan Kaufmann Publ. Inc., 2011.
42. A. Arabameri et al., “Modeling spatial flood using novel ensemble artificial intelligence approaches in northern Iran,” Remote Sens., vol. 12, no. 20, pp. 1–30, 2020, doi: 10.3390/rs12203423.
43. P. G. Sonia Singh, “Comparative Study ID3,CART AND C4.5 Decision Tree Algorithm,” Int. J. Adv. Inf. Sci. Technol., vol. 27, no. 27, p. 98, 2014.
44. S. K. Jayanthi and S. Sasikala, “REPTREE CLASSIFIER FOR IDENTIFYING LINK SPAM IN WEB SEARCH ENGINES,” ICTACT J. SOFT Comput., pp. 498–505, 2013, doi: 10.21917/ijsc.2013.0075.
45. M. Chiu, Y. Yu, H. . Liaw, and L. Hao, “The use of facial micro-expression state and tree-forest model for predicting conceptual-conflict based conceptual change.Science Education Research,” Engag. Learn. a Sustain. Futur. (ESERA e proceeding, 2016.
46. O. J. Adetunji and O. T. Ibitoye, “Development of an Intrusion Detection Model using Long Short Term Memory Algorithm,” 2024 IEEE 5th Int. Conf. Electro-Computing Technol. Humanit., pp. 1–5, 2024, doi: 10.1109/NIGERCON62786.2024.10926945.
47. O. T. Ibitoye, A. O. Ojo, I. O. Bisirodipe, M. A. Ogunlade, N. I. Ogbodo, and O. J. Adetunji, “A Deep Learning-Based Autonomous Fire Detection and Suppression Robot,” 2024 IEEE 5th Int. Conf. Electro-Computing Technol. Humanit., pp. 1–4, 2024, doi: 10.1109/NIGERCON62786.2024.10927352.
48. W. Dai, Y. Tang, N. Liao, S. Shujie and Z. Cai, “Urban flood prediction using ensemble artificial neural network: an investigation on improving model uncertainty”, Applied Water Science, pp. 1 – 10, 2024, doi.org/10.1007/s13201-024-02201-7
49. S. Hajji, Sonia, K. Abdelrahman, A. Boudhar, A. Elaloui, M. Ismaili, M. El Bouzekraoui, M. Chikh Essbiti, A. Kahal, B. Mondal and M. Namous, “ Enhancing flood prediction through remote sensing, machine learning, and Google Earth Engine”, Frontiers in Water, 2025, doi: 10.3389/frwa.2025.1514047