Comparative assessing the performance of ANN, RF and CNN machine learning methods in identifying landslide prone areas

Document Type : Original Article

Authors

1 Department of Physical Geography, Faculty of Social Science, University of Mohaghegh Ardabili, Ardabil, Iran

2 Department of RS & GIS, Faculty of Earth Sciences, Shahid Chamran University of Ahvaz , Ahvaz, Iran

3 Department of Climatology, Faculty of Social Sciences, University of Mohaghegh Ardabili, Ardabil, Iran

4 Department of Natural Resources, Faculty of Agriculture and Natural Resources, Water Management Research Center, University of Mohaghegh Ardabili, Ardabil, Iran

Abstract

Landslides are one of the natural hazards in mountainous areas that cause a lot of damage every year, thus, determining the landslide prone area is very important. This study assessed the performance of artificial neural network (ANN), Random Forest (RF), and Convolutional Neural Network (CNN) methods in identifying landslide prone areas. The study area is Lorestan Province, Khorramabad Watershed in western Iran, a region highly susceptible to landslides. After pre-processing the satellite images, the training samples were collected using field visits. Then, the neural network with a modifed structure was used for classification based on the simultaneous integration of the algorithm used. The available data were divided into 70% for the training, and 30 % for the validation stages. The performance of the generated classification maps of three employed methods were evaluated using the overall accuracy and confusion matrix. The results of evaluating the performance and accuracy of the CNN algorithm for identifying landslide areas show 93% overall accuracy. While the evaluation of the results obtained from ANN and RF methods shows that the overall accuracy of the neural network method is 90% and its overall accuracy is 88% and in the random forest method the overall accuracy is 84% and the overall accuracy is 82%; This study shows that the proposed method has shown the best performance compared to other methods according to evaluation criteria.These findings highlight the superiority of the CNN-based approach in accurately mapping landslide-prone areas, making it a reliable tool for future hazard assessment and risk management in mountainous regions.

Keywords

Main Subjects

References

Agboola, G., Beni, L.H., Elbayoumi, T. and Thompson, G., 2024. Optimizing landslide susceptibility mapping using machine learning and geospatial techniques. Ecological Informatics, v. 81, 102583. https://doi.org/10.1016/j.ecoinf.2024.102583
Aghayary, L., Asghari Saraskanrood, S. and Zeynali, B., 2024. Identification and zoning of landslide prone areas in Germi city. Journal of Hydrogeomorphology, v. 11(39), p. 1-18. https://doi.org/ 10.22034/hyd. 2024. 58703.1709 (In Persian).
Alavi, M., 2007. Structures of the Zagros fold-thrust belt in Iran. American Journal of science, v. 307(9), p. 1064-1095. http://dx.doi.org/10.2475/09.2007.02 (In Persian).
Ali, N., Chen, J., Fu, X., Ali, R., Hussain, M.A., Daud, H. and Altalbe, A., 2024. Integrating machine learning ensembles for landslide susceptibility mapping in Northern Pakistan. Remote Sensing, v. 16(6), 988 p. https://doi.org/10.3390/rs16060988
Alshehhi, R., Marpu, P.R., Woon, W.L. and Dalla Mura, M., 2017. Simultaneous extraction of roads and buildings in remote sensing imagery with convolutional neural networks. ISPRS Journal of Photogrammetry and Remote Sensing, v. 130, p. 139-149. https://doi.org/10.1016/j.isprsjprs.2017.05.002
Asghari Saraskanrood, S., Emami, R. and Piroozi, E., 2021. Evaluation and zonation of Landslide hazard with using OWA and ANN methods (case study: Paveh Township). Journal of Natural Environmental Hazards, v. 10(28), p. 131-150. 10.22111/jneh.2021.33729.1645 (In Persian).
Asghari Saraskanrood, S. and Piroozi, E., 2024. Identification and Zoning of Areas Prone to the Occurrence of Landslides Using the Aras Multi-Criteria Analysis Method (Study Area: Qaranqoochay Watershed in the Southeast of East Azarbaijan Province). Geography and Environmental Planning, v. 35(3), p. 65-94. 10.22108/gep.2024.140985.1639 (In Persian).
Bammou, Y., Benzougagh, B., Ouallali, A., Kader, S., Raougua, M. and Igmoullan, B., 2025. Improving landslide susceptibility mapping in semi-arid regions using machine learning and Geospatial techniques. DYSONA-Applied Science, v. 6(2), p. 269-290. 10.30493/das.2025.484839
Bostan, T., 2024. Generating a landslide susceptibility map using integrated meta-heuristic optimization and machine learning models. Sustainability, v. 16(21), 9396. https://doi.org/10.3390/su16219396
Bouaafia, S., Messaoud, S., Maraoui, A., Ammari, A.C., Khriji, L. and Machhout, M., 2021, March. Deep pre-trained models for computer vision applications: traffic sign recognition. In 2021 18th International Multi-Conference on Systems, Signals & Devices (SSD), p. 23-28. IEEE. DOI: 10.1109/ SSD52085. 2021.9429420
Bragagnolo, L., Da Silva, R.V. and Grzybowski, J.M.V., 2020a. Artificial neural network ensembles applied to the mapping of landslide susceptibility. Catena, v. 184, 104240. https://doi.org/10.1016/j.catena.2019.104240
Bragagnolo, L., da Silva, R.V. and Grzybowski, J.M.V., 2020b. Landslide susceptibility mapping with r. landslide: A free open-source GIS-integrated tool based on Artificial Neural Networks. Environmental Modelling & Software, v. 123, 104565. https://doi.org/10.1016/j.envsoft.2019.104565
Chicas, S.D., Li, H., Mizoue, N., Ota, T., Du, Y. and Somogyvári, M., 2024. Landslide susceptibility mapping core-base factors and models’ performance variability: A systematic review. Natural Hazards, v. 1-21. 10.1007/s11069-024-06697-9
Dou, J., Yunus, A.P., Bui, D.T., Merghadi, A., Sahana, M., Zhu, Z. and Pham, B.T., 2019. Assessment of advanced random forest and decision tree algorithms for modeling rainfall-induced landslide susceptibility in the Izu-Oshima Volcanic Island, Japan. Science of the total environment, v. 662, p. 332-346. https://doi.org/10.1016/j.scitotenv.2019.01.221
Esfandyari Darabad, F., Rostami, G., Mostafazadeh, R. and Abedini, M., 2024. Spatial assessment and zoning of landslide risk in Zamkan watershed using support vector machine and logistic regression. Journal of Hydrogeomorphology, v. 11(40), p. 123-102. 10.22034/hyd.2024.61467.1737 (In Persian).
Feng, Q., Niu, B., Chen, B., Ren, Y., Zhu, D., Yang, J. and Li, B., 2021. Mapping of plastic greenhouses and mulching films from very high resolution remote sensing imagery based on a dilated and non-local convolutional neural network. International Journal of Applied Earth Observation and Geoinformation, v. 102, 102441. https:// doi.org/ 10.1016/ j.jag. 2021.102441
Feng, L., Maosheng, Z., Mao, Y., Liu, H., Yang, Ch., Ying Dong and Yaser A., 2025. Nanehkaran, Convolutional neural network-based deep learning for landslide susceptibility mapping in the Bakhtegan watershed, Scientific Reports 15:13250 | 10.1038/s41598-025-96748-3
Froude, M.J. and Petley, D.N., 2018. Global fatal landslide occurrence from 2004 to 2016. Natural Hazards and Earth System Sciences, v. 18(8), p. 2161-2181. 10.5194/nhess-18-2161-2018
Ghorbani, A., Mostafazadeh, R., Zabihi, M. and Jafari Roodsari, M., 2023. GIS-based determining the landslide hotspot occurrence using Getis-Ord Index in Gharnaveh Watershed, Golestan Province. Journal of Hydrogeomorphology, v. 10(36), p. 1-18. 10.22034/hyd.2023.55449.1679 (In Persian).
Gomez, H. and Kavzoglu, T., 2005. Assessment of shallow landslide susceptibility using artificial neural networks in Jabonosa River Basin, Venezuela. Engineering Geology, v. 78(1-2), p. 11-27. https://doi.org/ 10.1016/ j.enggeo.2004.10.004
Hemasinghe, H., Rangali, R.S.S., Deshapriya, N.L. and Samarakoon, L., 2018. Landslide susceptibility mapping using logistic regression model (a case study in Badulla District, Sri Lanka). Procedia engineering, v. 212, p. 1046-1053. https://doi.org/10.1016/j.proeng. 2018.01.135
James, G., Witten, D., Hastie, T. and Tibshirani, R., 2013. An Introduction to Statistical Learning: with Applications in R (v. 103). Springer.
Lee, S., 2005. Application and cross-validation of spatial logistic multiple regression for landslide susceptibility analysis. Geosciences Journal, v. 9, p. 63-71. 10.1007/BF02910555
Lee, S., Ryu, J.H., Lee, M.J. and Won, J.S., 2006. The application of artificial neural networks to landslide susceptibility mapping at Janghung, Korea. Mathematical Geology, v. 38, p. 199-220. DOI: 10.1007/s11004-005-9012-x
Li, J., Cai, Y., Li, Q., Kou, M. and Zhang, T., 2024. A review of remote sensing image segmentation by deep learning methods. International Journal of Digital Earth, v. 17(1), 2328827. https://doi.org/10.1080/17538947.2024.2328827
Lokesh, P., Madhesh, C., Mathew, A. and Shekar, P.R., 2025. Machine learning and deep learning-based landslide susceptibility mapping using geospatial techniques in Wayanad, Kerala state, India. HydroResearch, v. 8, p. 113-126. https://doi.org/10.1016/ j.hydres. 2024.10.001
Martinović, K., Gavin, K. and Reale, C., 2016. Development of a landslide susceptibility assessment for a rail network. Engineering Geology, v. 215, p. 1-9. https://doi.org/10.1016/j.enggeo.2016.10.011
Mazzia, V., Khaliq, A. and Chiaberge, M., 2019. Improvement in land cover and crop classification based on temporal features learning from Sentinel-2 data using recurrent-convolutional neural network (R-CNN). Applied Sciences, v. 10(1), 238 p. https://doi.org/10.3390/app10010238
Merghadi, A., Yunus, A.P., Dou, J., Whiteley, J., ThaiPham, B., Bui, D.T. and Abderrahmane, B., 2020. Machine learning methods for landslide susceptibility studies: A comparative overview of algorithm performance. Earth-Science Reviews, v. 207, 103225. https://doi.org/10.1016/j.earscirev.2020.103225
Mogaji, K.A., Lim, H.S. and Abdullah, K., 2015. Regional prediction of groundwater potential mapping in a multifaceted geology terrain using GIS-based Dempster–Shafer model. Arabian Journal of Geosciences, v. 8, p. 3235-3258. 10.1007/s12517-014-1391-1
Mohammadi, N. and Sasanpour, F., 2021. Landslide and debris flow risk analysis in Haraz and Lavasanat roads. Water and Soil Management and Modelling, v. 1(4), p. 14-29. Doi: 10.22098/mmws.2021.9138.1023
Pham, B.T., Shirzadi, A., Bui, D.T., Prakash, I. and Dholakia, M.B., 2018. A hybrid machine learning ensemble approach based on a radial basis function neural network and rotation forest for landslide susceptibility modeling: A case study in the Himalayan area, India. International Journal of Sediment Research, v. 33(2), p. 157-170. https://doi.org/10.1016/j.ijsrc.2017.09.008
Qi, G., Wang, H., Haner, M., Weng, C., Chen, S. and Zhu, Z., 2019. Convolutional neural network based detection and judgement of environmental obstacle in vehicle operation. CAAI Transactions on Intelligence Technology, v. 4(2), p. 80-91. https://doi.org/10.1049/trit.2018.1045
Rostamizad, G. and Dastranj, A., 2024. Evaluating the sensitivity of the landslide event using the support vector machine algorithm. Water and Soil Management and Modelling, v. 4(4), p. 299-312. 10.22098/mmws.2023.13934.1379 (In Persian).
Ruuska, S., Hämäläinen, W., Kajava, S., Mughal, M., Matilainen, P. and Mononen, J., 2018. Evaluation of the confusion matrix method in the validation of an automated system for measuring feeding behaviour of cattle. Behavioural processes, v. 148, p. 56-62. https://doi.org/10.1016/j.beproc.2018.01.004
Sharma, A., Sajjad, H., Rahaman, M.H., Saha, T.K. and Bhuyan, N., 2024b. Effectiveness of hybrid ensemble machine learning models for landslide susceptibility analysis: Evidence from Shimla district of North-west Indian Himalayan region. Journal of Mountain Science, v. 21(7), p. 2368-2393. 10.1007/s11629-024-8651-7
Sharma, N., Saharia, M. and Ramana, G.V., 2024a. High resolution landslide susceptibility mapping using ensemble machine learning and geospatial big data. Catena, v. 235, 107653. https://doi.org/10.1016/j.catena.2023.107653
Stöcklin, J., 1968. Structural history and tectonics of Iran: a review. AAPG bulletin, v. 52(7), p. 1229-1258. https://doi.org/10.1306/5D25C4A5-16C1-11D7-8645000102C1865D
Sun, D., Wen, H., Wang, D. and Xu, J., 2020. A random forest model of landslide susceptibility mapping based on hyperparameter optimization using Bayes algorithm Geomorphology, v. 362, 107201. https://doi.org/10.1016/j. geomorph. 2020. 107201
Sun, D., Xu, J., Wen, H. and Wang, D., 2021. Assessment of landslide susceptibility mapping based on Bayesian hyperparameter optimization: A comparison between logistic regression and random forest. Engineering Geology, v. 281, 105972. https://doi.org/10.1016/ j.enggeo. 2020.105972
Trigila, A., Iadanza, C., Esposito, C. and Scarascia-Mugnozza, G., 2015. Comparison of Logistic Regression and Random Forests techniques for shallow landslide susceptibility assessment in Giampilieri (NE Sicily, Italy). Geomorphology, v. 249, p. 119-136. https://doi.org/10.1016/j.geomorph.2015.06.001
Tsangaratos, P., Ilia, I., Hong, H., Chen, W. and Xu, C., 2017. Applying Information Theory and GIS-based quantitative methods to produce landslide susceptibility maps in Nancheng County, China. Landslides, v. 14, p. 1091-1111. 10.1007/s10346-016-0769-4
Vorpahl, P., Elsenbeer, H., Märker, M. and Schröder, B., 2012. How can statistical models help to determine driving factors of landslides? Ecological Modelling, v. 239, p. 27-39. https://doi.org/ 10.1016/ j.ecolmodel. 2011.12.007
Wang, L., Zhang, M., Gao, X. and Shi, W., 2024. Advances and challenges in deep learning-based change detection for remote sensing images: A review through various learning paradigms. Remote Sensing, v. 16(5), 804 p. https://doi.org/10.3390/rs16050804
Wang, Y., Fang, Z., Wang, M., Peng, L. and Hong, H., 2020. Comparative study of landslide susceptibility mapping with different recurrent neural networks. Computers & Geosciences, v. 138, 104445. https://doi.org/10.1016/j.cageo.2020.104445
Zali, M. and Shahedi, K., 2021. Landslide sensitivity assessment using fuzzy logic approach and GIS in Neka Watershed. Water and Soil Management and Modelling, v. 1(1), p. 67-80. Doi: 10.22098/mmws.2021.1183. 10.22098/mmws.2021.1183
Zhou, X., Wen, H., Zhang, Y., Xu, J. and Zhang, W., 2021. Landslide susceptibility mapping using hybrid random forest with GeoDetector and RFE for factor optimization. Geoscience Frontiers, v. 12(5), 101211. https://doi.org/10.1016/j.gsf.2021.101211
 
Researches in Earth Sciences
Volume 16, Special Issue - Serial Number 64
Special Issue
December 2025
Pages 73-91

Files

Share

How to cite

Statistics