Developing an explainable and interpretable machine learning model for flood susceptibility mapping

• Autorzy: Khaldi Loubna , El Bilali Ali , El Abed Alae , Krakauer Nir , El Khanchoufi Abdessalam

Identyfikatory

DOI

10.12912/27197050/195845

• Języki publikacji: EN

Abstrakty

EN

This study evaluates flood susceptibility in the Fez-Meknes region of Morocco by comparing the performance of five machine learning (ML) models using 14 environmental variables. The selected models, including Random Forest (RF), Support Vector Machine (SVM), K-Nearest Neighbor (KNN), Recursive Partitioning and Regression Trees (RPART), and Logistic Regression (LR), were assessed for prediction accuracy and enhanced with Partial Dependence Plots (PDP) and Local Interpretable Model-Agnostic Explanations (LIME) to increase interpretability. Results indicate that the RF model outperforms other models, achieving a high prediction accuracy with an AUC of 96%, low Mean Absolute Error (MAE) of 0.26, and Root Mean Squared Error (RMSE) of 0.31, along with strong Nash-Sutcliffe Efficiency (NSE) and correlation coefficient (R²). Through PDP and LIME, the primary factors influencing flood susceptibility were identified as proximity to rivers, drainage density, slope, NDVI (Normalized Difference Vegetation Index), TRI (Terrain Roughness Index), and LULC (Land Use and Land Cover). These findings highlight the potential of interpretable ML models to enhance flood risk assessment, providing valuable insights for urban planning and flood mitigation strategies in vulnerable regions.

Słowa kluczowe

EN

flood susceptibility; modeling and mapping; random forest model; Fez-Meknes region

• Wydawca: Lubelski Oddział Polskiego Towarzystwo Inżynierii Ekologicznej ; Lublin University of Technology ; WNGB Wydawnictwo Naukowe
• Czasopismo: Ecological Engineering & Environmental Technology
• Rocznik: 2025
• Tom: Vol. 26, iss. 1
• Strony: 201--215
• Opis fizyczny: Bibliogr. 45 poz., rys., tab.

Twórcy

autor

Khaldi Loubna

• Faculty of Sciences Dhar El Mahraz, Sidi Mohamed Ben Abdellah University, Fez, Morocco

• https://orcid.org/0000-0001-8493-051X

autor

El Bilali Ali

• River Basin Agency of Bouregreg and Chaouia, Benslimane, Morocco

• https://orcid.org/0000-0002-5744-3086

autor

El Abed Alae

• Faculty of Sciences Dhar El Mahraz, Sidi Mohamed Ben Abdellah University, Fez, Morocco

• https://orcid.org/0000-0003-0844-6413

autor

Krakauer Nir

• Department of Civil Engineering, The City College of New York, New York, NY 10031, USA
• Earth and Environmental Sciences, City University of New York Graduate Center, New York, NY 10016, USA

• https://orcid.org/0000-0002-4926-5427

autor

El Khanchoufi Abdessalam

• Faculty of Sciences Dhar El Mahraz, Sidi Mohamed Ben Abdellah University, Fez, Morocco

• https://orcid.org/0000-0003-2664-267X

Bibliografia

• 1. Al-areeq, A.M., Saleh, R.A.A., Ghaleb, M., Abba, S.I., Yaseen, M., (2024). Implication of novel hybrid machine learning model for flood subsidence susceptibility mapping : A representative case study in Saudi Arabia. J. Hydrol. 630, 130692. https://doi.org/10.1016/j.jhydrol.2024.130692
• 2. Althuwaynee, O.F., Balogun, A., Al Madhoun, W., (2020). Air pollution hazard assessment using decision tree algorithms and bivariate probability cluster polar function: evaluating inter-correlation clusters of PM10 and other air pollutants. GIScience Remote Sens. 57, 207–226. https://doi.org/10.1080/154816 03.2020.1712064
• 3. Avand, M., Moradi, H., lasboyee, M.R., (2021). Using machine learning models, remote sensing, and GIS to investigate the effects of changing climates and land uses on flood probability. J. Hydrol. 595, 125663. https://doi.org/10.1016/j. jhydrol.2020.125663
• 4. Bastiaan, R.M., Salaki, D.T., Hatidja, D., (2022). Comparing the Performance of Prediction Model of Ridge and Elastic Net in Correlated Dataset. Oper. Res. Int. Conf. Ser. 3, 8–13. https://doi.org/10.47194/ orics.v3i1.127
• 5. Belgiu, M., Dra, L., (2016). Random forest in remote sensing : A review of applications and future directions. ISPRS Journal of Photogrammetry and Remote Sensing 114, 24–31. https://doi.org/10.1016/j. isprsjprs.2016.01.011
• 6. Bouamrane, A., Derdous, O., Dahri, N., Tachi, S.E., Boutebba, K., Bouziane, M.T., (2022). A comparison of the analytical hierarchy process and the fuzzy logic approach for flood susceptibility mapping in a semi-arid ungauged basin (Biskra basin: Algeria). Int. J. River Basin Manag. 20, 203–213. https://doi.org/10.1080/15715124.2020.1830786
• 7. Breiman, L.E.O., 2001. Random Forests 5–32.
• 8. Bui, D.T., Ngo, P.T.T., Pham, T.D., Jaafari, A., Minh, N.Q., Hoa, P.V., Samui, P., (2019). A novel hybrid approach based on a swarm intelligence optimized extreme learning machine for flash flood susceptibility mapping. Catena 179, 184–196. https://doi.org/10.1016/j.catena.2019.04.009
• 9. Bunmi Mudashiru, R., Sabtu, N., Abdullah, R., Saleh, A., Abustan, I., (2022). Optimality of flood influencing factors for flood hazard mapping: An evaluation of two multi-criteria decision-making methods. J. Hydrol. 612, 128055. https://doi.org/10.1016/j.jhydrol.2022.128055
• 10. Chapi, K., Singh, V.P., Shirzadi, A., Shahabi, H., Bui, D.T., Pham, B.T., Khosravi, K., (2017a). A novel hybrid artificial intelligence approach for flood susceptibility assessment. Environ. Model. Softw. 95, 229–245. https://doi.org/10.1016/j. envsoft.2017.06.012
• 11. Chapi, K., Singh, V.P., Shirzadi, A., Shahabi, H., Tien, D., (2017b). Environmental Modelling & Software A novel hybrid arti fi cial intelligence approach for fl ood susceptibility assessment. Environ. Model. Softw. 95, 229–245. https://doi.org/10.1016/j.envsoft.2017.06.012
• 12. Chen, W., Hong, H., Li, S., Shahabi, H., Wang, Y., Wang, X., Bin, B., (2019). Flood susceptibility modelling using novel hybrid approach of reduced-error pruning trees with bagging and random subspace ensembles. J. Hydrol. 575, 864–873. https://doi.org/10.1016/j.jhydrol.2019.05.089
• 13. Chen, W., Li, Y., Xue, W., Shahabi, H., Li, S., Hong, H., Wang, X., Bian, H., Zhang, S., Pradhan, B., Ahmad, B. Bin, (2020). Modeling flood susceptibility using data-driven approaches of naïve Bayes tree, alternating decision tree, and random forest methods. Sci. Total Environ. 701, 134979. https://doi.org/10.1016/j.scitotenv.2019.134979
• 14. Cracknell, M.J., Reading, A.M., 2014. Computers & Geosciences Geological mapping using remote sensing data: A comparison of fi ve machine learning algorithms , their response to variations in the spatial distribution of training data and the use of explicit spatial information. Comput. Geosci. 63, 22–33. https://doi.org/10.1016/j.cageo.2013.10.008
• 15. Davoudi Moghaddam, D., Pourghasemi, H.R., Rahmati, O., (2019). Assessment of the contribution of geo-environmental factors to flood inundation in a semi-arid region of SW Iran: comparison of different advanced modeling approaches. Adv. Nat. Technol. Hazards Res. 48, 59–78. https://doi.org/10.1007/978-3-319-73383-8_3
• 16. Dolchinkov, N.T., (2024). Natural emergencies and some causes of their occurrence: a review. trends ecol. Indoor Environ. Eng. 2, 18–27. https://doi.org/10.62622/teiee.024.2.1.18-27
• 17. Dormann, C.F., Elith, J., Bacher, S., Buchmann, C., Carl, G., Carré, G., Marquéz, J.R.G., Gruber, B., Lafourcade, B., Leitão, P.J., Münkemüller, T., Mcclean, C., Osborne, P.E., Reineking, B., Schröder, B., Skidmore, A.K., Zurell, D., Lautenbach, S., (2013). Collinearity: A review of methods to deal with it and a simulation study evaluating their performance. Ecography (Cop.). 36, 27–46. https://doi.org/10.1111/j.1600-0587.2012.07348.x
• 18. Friedman, H., (2001). Greedy function approximation : A gradient boosting machine author ( s ): Jerome H. Friedman Source : The Annals of Statistics, Oct 29(5) ( Oct., 2001 ), 1189–1232 Published by : Institute of Mathematical Statistics Stable UR 29, 1189–1232.
• 19. Gocic, M., Trajkovic, S., (2013). Analysis of changes in meteorological variables using Mann-Kendall and Sen’s slope estimator statistical tests in Serbia. Glob. Planet. Change 100, 172–182. https://doi.org/10.1016/j.gloplacha.2012.10.014
• 20. Gudiyangada Nachappa, T., Tavakkoli Piralilou, S., Gholamnia, K., Ghorbanzadeh, O., Rahmati, O., Blaschke, T., (2020). Flood susceptibility mapping with machine learning, multi-criteria decision analysis and ensemble using Dempster Shafer Theory. J. Hydrol. 590, 125275. https://doi.org/10.1016/j. jhydrol.2020.125275
• 21. Guo, G., Wang, H., Bell, D., Bi, Y., Greer, K., (2003). KNN Model-Based Approach in Classification 986–996.
• 22. Holzinger, A., Goebel, R., Fong, R., Moon, T., Müller, Klaus-Robert, Samek, W., (2022). xxAI-Beyond Explainable AI.
• 23. Kavzoglu, T., Colkesen, I., (2009). A kernel functions analysis for support vector machines for land cover classification. Int. J. Appl. Earth Obs. Geoinf. 11, 352–359. https://doi.org/10.1016/j. jag.2009.06.002
• 24. Khaldi, L., Elabed, A., El Khanchoufi, A., (2023). Quantitative assessment of the relative impacts of different factors on flood susceptibility modelling: Case study of Fez-Meknes region in Morocco. E3S Web Conf. 364. https://doi.org/10.1051/ e3sconf/202336402005
• 25. Khosravi, K., Shahabi, H., Pham, B.T., Adamowski, J., Shirzadi, A., Pradhan, B., Dou, J., Ly, H.B., Gróf, G., Ho, H.L., Hong, H., Chapi, K., Prakash, I., (2019). A comparative assessment of flood susceptibility modeling using Multi-Criteria Decision- Making Analysis and Machine Learning Methods. J. Hydrol. 573, 311–323. https://doi.org/10.1016/j. jhydrol.2019.03.073
• 26. Kia, M.B., Pirasteh, S., Pradhan, B., Mahmud, A.R., Nor, W., Sulaiman, A., Moradi, A., (2012). An artificial neural network model for flood simulation using GIS : Johor River Basin , Malaysia. Environ. Earth Sci. 251–264. https://doi.org/10.1007/ s12665-011-1504-z
• 27. Lee, S., Sambath, T., (2006). Landslide susceptibility mapping in the Damrei Romel area, Cambodia using frequency ratio and logistic regression models. Environ. Geol. 50, 847–855. https://doi.org/10.1007/s00254-006-0256-7
• 28. Mahdizadeh Gharakhanlou, N., Perez, L., (2022). Spatial prediction of current and future flood susceptibility: examining the implications of changing climates on flood susceptibility using machine learning models, Entropy. https://doi.org/10.3390/e24111630
• 29. Maxwell, A.E., Warner, T.A., Fang, F., Maxwell, A.E., Warner, T.A., (2018). Implementation of machine-learning classification in remote sensing : an applied review sensing: an applied review. Int. J. Remote Sens. 39, 2784–2817. https://doi.org/10.10 80/01431161.2018.1433343
• 30. Mc fadden, D., 1974. Conditional logit analysis of qualitative choice behavior. Front. Econom. https://doi.org/10.1080/07373937.2014.997882
• 31. Menuka, M., Sachin, T., Santosh, A., Bikram, S., Bikram, M., Amir, S., (2022). Flood susceptibility assessment using machine learning approach in the Mohana- Khutiya River of Nepal. Nat. Hazard Res. https://doi.org/10.1016/j.nhres.2024.01.001
• 32. Mishra, S., Sturm, B.L., Dixon, S., (2017). Local interpretable model-agnostic explanations for music content analysis. Proc. 18th Int. Soc. Music Inf. Retr. Conf. ISMIR, 537–543.
• 33. Mohammadi, M., Darabi, H., Mirchooli, F., Bakhshaee, A., Torabi Haghighi, A., (2021). Flood risk mapping and crop-water loss modeling using water footprint analysis in agricultural watershed, northern Iran. Nat. Hazards 105, 2007–2025. https://doi.org/10.1007/s11069-020-04387-w
• 34. Mountrakis, G., Im, J., Ogole, C., 2011. ISPRS Journal of photogrammetry and remote sensing support vector machines in remote sensing : A review. ISPRS J. Photogramm. Remote Sens. 66, 247–259. https://doi.org/10.1016/j.isprsjprs.2010.11.001
• 35. Mousavi, S.M., Ataie-Ashtiani, B., Hosseini, S.M., (2022). Comparison of statistical and MCDM approaches for flood susceptibility mapping in northern Iran. J. Hydrol. 612, 128072. https://doi.org/10.1016/j.jhydrol.2022.128072
• 36. Mudashiru, R.B., Sabtu, N., Abustan, I., (2021). Quantitative and semi-quantitative methods in flood hazard/susceptibility mapping: a review. Arab. J. Geosci. 14. https://doi.org/10.1007/ s12517-021-07263-4
• 37. Munawar, H.S., Hammad, A.W.A., Waller, S.T., (2021). A review on flood management technologies related to image processing and machine learning. Autom. Constr. 132, 103916. https://doi.org/10.1016/j.autcon.2021.103916
• 38. Ogden, F.L., Raj Pradhan, N., Downer, C.W., Zahner, J.A., (2011). Relative importance of impervious area, drainage density, width function, and subsurface storm drainage on flood runoff from an urbanized catchment. Water Resour. Res. 47. https://doi.org/10.1029/2011WR010550
• 39. Pham, B.T., Luu, C., Phong, T. Van, Nguyen, H.D., Le, H. Van, Tran, T.Q., Ta, H.T., Prakash, I., (2021). Flood risk assessment using hybrid artificial intelligence models integrated with multi-criteria decision analysis in Quang Nam Province, Vietnam. J. Hydrol. 592, 125815. https://doi.org/10.1016/j. jhydrol.2020.125815
• 40. Rahman, M., Ningsheng, C., Mahmud, G.I., Islam, M.M., Pourghasemi, H.R., Ahmad, H., Habumugisha, J.M., Washakh, R.M.A., Alam, M., Liu, E., Han, Z., Ni, H., Shufeng, T., Dewan, A., (2021). Flooding and its relationship with land cover change, population growth, and road density. Geosci. Front. 12, 101224. https://doi.org/10.1016/j.gsf.2021.101224
• 41. Saha, S., Arabameri, A., Saha, A., Blaschke, T., Thao, P., Ngo, T., Ha, V., Band, S.S., (2021). Science of the total environment prediction of landslide susceptibility in Rudraprayag , India using novel ensemble of conditional probability and boosted regression tree-based on cross-validation method. Sci. Total Environ. 764, 142928. https://doi.org/10.1016/j.scitotenv.2020.142928
• 42. Sayers, P., Galloway, G., Penning-Rowsell, E., Yuanyuan, L., Fuxin, S., Yiwei, C., Kang, W., Le Quesne, T., Wang, L., Guan, Y., (2015). Strategic flood management: ten ‘golden rules’ to guide a sound approach. Int. J. River Basin Manag. 13, 137–151. https://doi.org/10.1080/15715124.2014.902378
• 43. Tehrany, M.S., Jones, S., Shabani, F., (2019). Identifying the essential flood conditioning factors for flood prone area mapping using machine learning techniques. Catena 175, 174–192. https://doi.org/10.1016/j.catena.2018.12.011
• 44. Tehrany, M.S., Pradhan, B., Jebur, M.N., (2013). 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, 69–79. https://doi.org/10.1016/j. jhydrol.2013.09.034
• 45. Zhang, R., Chen, Y., Zhang, X., Ma, Q., Ren, L., (2022). Mapping homogeneous regions for flash floods using machine learning: A case study in Jiangxi province, China. Int. J. Appl. Earth Obs. Geoinf. 108. https://doi.org/10.1016/j.jag.2022.102717