.png)
GAN-Enhanced Radial Basis Function Networks for Improved Landslide Susceptibility Mapping
Abstract
Landslide susceptibility modeling is a critical task for disaster mitigation, yet it is frequently undermined by a severe class imbalance inherent in landslide datasets, where non-landslide instances vastly outnumber actual landslide events. This imbalance leads to biased machine learning models with poor predictive power for the minority (landslide) class, resulting in unreliable hazard maps. This study, focusing on the high-risk area of Malang Regency, Indonesia, addresses this challenge by proposing an innovative framework that integrates a Generative Adversarial Network (GAN) for synthetic data augmentation with a Radial Basis Function Network (RBFN) for classification. A highly imbalanced dataset with a 1:10 ratio of landslide to non-landslide points was constructed to establish a realistic baseline. On this data, the RBFN model, while theoretically powerful for capturing non-linear relationships, failed completely, achieving a Recall of 0.00 for the landslide class. The novelty of this research lies in the specific application of a GAN, trained for 15,000 epochs, to generate high-fidelity synthetic landslide data, thereby creating a perfectly balanced training set. After retraining on this augmented data and undergoing a systematic hyperparameter tuning process, the RBFN’s performance was dramatically transformed. The optimized model achieved an F1-Score of 0.9333 and a Recall of 0.8750, elevating its performance from total failure to a level competitive with the robust Random Forest benchmark. This work validates that the integrated GAN-RBFN approach is a highly effective methodology for overcoming the data imbalance problem in geospatial hazard modeling. By turning a previously unreliable classifier into a powerful predictive tool, this method has significant practical implications for developing more accurate landslide susceptibility maps, which are crucial for informed spatial planning and enhancing early warning systems.
Keywords
Full Text:
PDFReferences
N. Nurwatik, M. H. Ummah, A. B. Cahyono, M. R. Darminto, and J.-H. Hong, “A Comparison Study of Landslide Susceptibility Spatial Modeling Using Machine Learning,” ISPRS International Journal of Geo-Information, vol. 11, no. 12, Art. no. 12, Dec. 2022, doi: 10.3390/ijgi11120602.
I. Maulita, S. Sugito, and L. S. P. Boli, “Spatiotemporal Analysis of B-Value at Mount Slamet (2014–2023),” Jurnal Fisika Flux: Jurnal Ilmiah Fisika FMIPA Universitas Lambung Mangkurat, vol. 21, no. 3, pp. 255–268, Jan. 2025, doi: 10.20527/flux.v21i3.20718.
M. Hürlimann, Z. Guo, C. P. i. Polo, and V. Medina, “Impacts of Future Climate and Land Cover Changes on Landslide Susceptibility: Regional Scale Modelling in the Val D’Aran Region (Pyrenees, Spain),” Landslides, vol. 19, no. 1, pp. 99–118, 2021, doi: 10.1007/s10346-021-01775-6.
T. Triani and B. Bulaka, “Identifikasi Daerah Rawan Longsor Di Kecamatan Kolaka Kabupaten Kolaka,” Saintifik, vol. 10, no. 1, pp. 51–59, 2024, doi: 10.31605/saintifik.v10i1.489.
I. Maulita, C. R. A. Widiawati, and A. M. Wahid, “Analisis Komparatif Linear Regression, Random Forest, dan Gradient Boosting untuk Prediksi Banjir,” Jurnal Pendidikan dan Teknologi Indonesia, vol. 4, no. 8, Art. no. 8, 2024, doi: 10.52436/1.jpti.599.
A. Wubalem, “Modeling of Landslide Susceptibility in a Part of Abay Basin, Northwestern Ethiopia,” Open Geosciences, vol. 12, no. 1, pp. 1440–1467, 2020, doi: 10.1515/geo-2020-0206.
G. Wicaksono et al., “Peningkatan Kapasitas Mitigasi Bencana Longsor Melalui Sosialisasi Bersama BPBD Dan Senkom Kota Balikpapan Di RT 038 Kelurahan Gunung Sari Ulu,” Jurnal Pengabdian Kepada Masyarakat Itk (Pikat), vol. 4, no. 1, pp. 65–71, 2023, doi: 10.35718/pikat.v4i1.878.
J. R. Araújo, A. M. Ramos, P. M. M. Soares, R. Melo, S. C. Oliveira, and R. M. Trigo, “Impact of Extreme Rainfall Events on Landslide Activity in Portugal Under Climate Change Scenarios,” Landslides, vol. 19, no. 10, pp. 2279–2293, 2022, doi: 10.1007/s10346-022-01895-7.
V. A. Zulfa, H. Widyasamratri, and J. Kautsary, “Mitigasi Bencana Berdasarkan Tingkat Risiko Bencana Tanah Longsor,” Jurnal Kajian Ruang, vol. 2, no. 2, p. 154, 2022, doi: 10.30659/jkr.v2i2.26532.
L. Zhao, H. Ma, J. Dong, X. Wu, H. Xu, and R. Niu, “A Comparative Study of Landslide Susceptibility Mapping Using Bagging PU Learning in Class-Prior Probability Shift Datasets,” Remote Sensing, vol. 15, no. 23, p. 5547, 2023, doi: 10.3390/rs15235547.
B. T. Pham et al., “Coupling RBF Neural Network With Ensemble Learning Techniques for Landslide Susceptibility Mapping,” Catena, vol. 195, p. 104805, 2020, doi: 10.1016/j.catena.2020.104805.
L. Yang and B. Li, “The Combination Forecasting Model of Grain Production Based on Stepwise Regression Method and RBF Neural Network,” Advance Journal of Food Science and Technology, vol. 7, no. 11, pp. 891–895, 2015, doi: 10.19026/ajfst.7.2528.
M. S. G. Adnan, M. S. Rahman, N. Ahmed, B. Ahmed, Md. F. Rabbi, and R. M. Rahman, “Improving Spatial Agreement in Machine Learning-Based Landslide Susceptibility Mapping,” Remote Sensing, vol. 12, no. 20, p. 3347, 2020, doi: 10.3390/rs12203347.
D. W. Apriani, C. Credidi, and S. Khala, “An Empirical-Statistical Model for Landslide Runout Distance Prediction in Indonesia,” Pondasi, vol. 27, no. 1, p. 15, 2022, doi: 10.30659/pondasi.v27i1.22618.
M. Di Napoli et al., “Machine learning ensemble modelling as a tool to improve landslide susceptibility mapping reliability,” Landslides, vol. 17, no. 8, pp. 1897–1914, Aug. 2020, doi: 10.1007/s10346-020-01392-9.
Y. Wang, X. Wu, Z. Chen, F. Ren, L. Feng, and Q. Du, “Optimizing the Predictive Ability of Machine Learning Methods for Landslide Susceptibility Mapping Using SMOTE for Lishui City in Zhejiang Province, China,” International Journal of Environmental Research and Public Health, vol. 16, no. 3, p. 368, 2019, doi: 10.3390/ijerph16030368.
S. F. Pratama and A. M. Wahid, “Fraudulent Transaction Detection in Online Systems Using Random Forest and Gradient Boosting,” Journal of Cyber Law, vol. 1, no. 1, Art. no. 1, Mar. 2025.
Q. Siddique and A. M. Wahid, “Analyzing Customer Spending Based on Transactional Data Using the Random Forest Algorithm,” International Journal for Applied Information Management, vol. 5, no. 2, Art. no. 2, May 2025, doi: 10.47738/ijaim.v5i2.103.
M. A. Albahar, A. Alharbi, M. S. Alsuwat, and H. Aljuaid, “A Hybrid Model Based on Radial Basis Function Neural Network for Intrusion Detection,” International Journal of Advanced Computer Science and Applications, vol. 11, no. 8, 2020, doi: 10.14569/ijacsa.2020.0110896.
S. R. Meena et al., “Landslide Detection in the Himalayas Using Machine Learning Algorithms and U-Net,” Landslides, vol. 19, no. 5, pp. 1209–1229, 2022, doi: 10.1007/s10346-022-01861-3.
C. R. Ajeng Widiawati, H. Adi Nugroho, I. Ardiyanto, and M. S. Amin, “Increasing Performance of Plasmodium Detection Using Bottom-Hat and Adaptive Thresholding,” in 2021 IEEE 5th International Conference on Information Technology, Information Systems and Electrical Engineering (ICITISEE), Nov. 2021, pp. 207–212. doi: 10.1109/ICITISEE53823.2021.9655903.
A. M. Wahid, T. Hariguna, and G. Karyono, “Optimization of Recommender Systems for Image-Based Website Themes Using Transfer Learning,” Journal of Applied Data Sciences, vol. 6, no. 2, Art. no. 2, Mar. 2025, doi: 10.47738/jads.v6i2.671.
A. Ageenko, L. C. Hansen, K. L. Lyng, L. Bodum, and J. J. Arsanjani, “Landslide Susceptibility Mapping Using Machine Learning: A Danish Case Study,” Isprs International Journal of Geo-Information, vol. 11, no. 6, p. 324, 2022, doi: 10.3390/ijgi11060324.
DOI: https://doi.org/10.47738/jads.v7i1.1035
Refbacks
- There are currently no refbacks.
Journal of Applied Data Sciences
| ISSN | : | 2723-6471 (Online) |
| Publisher | : | Bright Publisher |
| Website | : | http://bright-journal.org/JADS |
| : | taqwa@amikompurwokerto.ac.id (principal contact) | |
| support@bright-journal.org (technical issues) |
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0