Akçasu Dere Havzası’nda (İnegöl, Bursa) Heyelan Duyarlılığının Makine Öğrenmesi Modelleri ile Karşılaştırmalı Analizi

Melike Durak; Muhammed Mustafa Özdel

doi:10.46453/jader.1883674

TR EN

Akçasu Dere Havzası’nda (İnegöl, Bursa) Heyelan Duyarlılığının Makine Öğrenmesi Modelleri ile Karşılaştırmalı Analizi

Öz

Heyelan önleme ve risk azaltma stratejilerinin temel yapı taşını oluşturan heyelan duyarlılık analizleri, sahaya ait fiziksel parametreleri değerlendirerek tehdit altındaki alanların önceden belirlenmesine imkan tanır. Bu çalışma kapsamında, makine öğrenmesi algoritmaları aracılığıyla Akçasu Dere Havzası’nın heyelan duyarlılık potansiyelinin modellenmesi ve bu duyarlılığın mekânsal dağılımının ortaya konulması amaçlanmıştır. Bu amaç doğrultusunda belirlenen 10 farklı bağımsız değişken temel alınarak; Rastgele Orman (RF), Destek Vektör Makineleri (DVM), Lojistik Regresyon (LR), Yapay Sinir Ağları (YSA) ve Maksimum Entropi (MaxEnt) gibi makine öğrenmesi algoritmalarıyla heyelan duyarlılık modelleri üretilmiştir. Hazırlanan heyelan duyarlılık haritaları düşük, orta, yüksek ve çok yüksek şeklinde dört sınıfa ayrılmıştır. Model sonuçları, heyelan envanteri ve AFAD verileriyle çakıştırılarak sahadaki gerçek kütle hareketleriyle uyumu sayısal olarak ortaya konulmuştur. Model çıktıları, Akçasu Dere Havzası’nda heyelan duyarlılığının orta çığırda yer alan ve akarsular tarafından derince yarılmış platoluk sahalarda kümelendiğini göstermektedir. Bu alanlar aynı zamanda antropojenik (insan kaynaklı) baskıların da en üst seviyeye ulaştığı bölgeleri temsil etmektedir. Aktif kütle hareketlerinin gözlemlendiği Çayyaka, Çayyaka (Kümlük), Dipsizgöl, Hamidiye (Gençali), Hayriye, İclaliye, Kestanealanı, Konurlar, Lütfiye ve Muratbey kırsal mahalleleri yüksek duyarlılık bölgeleri içerisinde yer almaktadır. Bu tür afetlerin zararlarının minimize edilmesi amacıyla; yüksek duyarlılıklı sahaların imar planlarında yerleşime kapatılması ve bu bölgelerdeki mevcut yapıların kademeli olarak tahliyesi önerilmektedir. Yerleşimin sürdüğü orta ve yüksek duyarlı alanlarda ise geoteknik iyileştirmeler (fore kazık, ankraj vb.) ve drenaj sistemleriyle entegre edilmiş teraslama çalışmaları titizlikle uygulanmalı; yamaç dengesini korumak için kontrolsüz mühendislik müdahaleleri denetim altına alınmalıdır.

Anahtar Kelimeler

Akçasu Dere Havzası , Heyelan Duyarlılığı , Makine Öğrenmesi , Afet Risk Yönetimi

Comparative Analysis of Landslide Susceptibility Using Machine Learning Models in the Akcasu Stream Basin (İnegöl, Bursa)

Abstract

Landslide susceptibility analyses, which constitute the fundamental component of landslide prevention and risk reduction strategies, enable the early identification of areas under threat by evaluating the physical parameters of the terrain. In this study, it is aimed to model the landslide susceptibility potential of the Akçasu Stream Basin using machine learning algorithms and to reveal the spatial distribution of this susceptibility. In line with this objective, landslide susceptibility models were generated using machine learning algorithms—such as Random Forest (RF), Support Vector Machines (SVM), Logistic Regression (LR), Artificial Neural Networks (ANN), and Maximum Entropy (MaxEnt)—based on 10 different independent variables determined for the study. The landslide susceptibility maps produced were classified into four categories: low, moderate, high, and very high. The model outputs were overlaid with the landslide inventory and AFAD data, and their consistency with actual mass movements in the field was quantitatively assessed. The model outputs indicate that landslide susceptibility within the Akçasu Stream Basin is concentrated in the middle course, particularly in plateau-like areas that have been deeply incised by fluvial processes. These areas also correspond to the regions where anthropogenic pressures reach their highest intensity. The rural neighborhoods of Çayyaka, Çayyaka (Kümlük), Dipsizgöl, Hamidiye (Gençali), Hayriye, İclaliye, Kestanealanı, Konurlar, Lütfiye, and Muratbey—where active mass movements have been observed—are located within the high-susceptibility zones. In order to minimize the impacts of such hazards, it is recommended that high‑susceptibility areas be excluded from settlement in zoning plans, and that existing structures within these zones be gradually evacuated. In medium‑ and high‑susceptibility areas where settlement continues, geotechnical stabilization measures (such as bored piles, anchors, etc.) and terracing works integrated with drainage systems should be implemented meticulously; and uncontrolled engineering interventions must be regulated in order to maintain slope stability.

Keywords

Akçasu Stream Basin , Landslide Susceptibility , Machine Learning , Disaster Risk Management

Kaynakça

Abdelkader, M. M., & Csámer, Á. (2025). Comparative assessment of machine learning models for landslide susceptibility mapping: a focus on validation and accuracy. Natural Hazards, 1-23. https://doi.org/10.1007/s11069-025-07197-0
Abdo, H. G., Richi, S. M., Prasad, P., Katipoğlu, O. M., Halder, B., Niknam, A., ... & Mallick, J. (2025). Mapping landslide susceptibility in the Eastern Mediterranean mountainous region: a machine learning perspective. Environmental Earth Sciences, 84(9), 250. https://doi.org/10.1007/s12665-025-12242-z
Achour, Y., & Pourghasemi, H. R. (2020). How do machine learning techniques help in increasing accuracy of landslide susceptibility maps?. Geoscience Frontiers, 11(3), 871-883. https://doi.org/10.1016/j.gsf.2019.10.001
Akıncı, H., Kılıçoğlu, C., & Doğan, S. (2020). Random forest-based landslide susceptibility mapping in coastal regions of Artvin, Turkey. ISPRS International Journal of Geo-Information, 9(9), 553. https://doi.org/10.3390/ijgi9090553
Akıncı, H., & Zeybek, M. (2021). Comparing classical statistic and machine learning models in landslide susceptibility mapping in Ardanuc (Artvin), Turkey. Natural Hazards, 108(2), 1515-1543. https://doi.org/10.1007/s11069-021-04743-4
Berber, S., Ercanoglu, M., & Ceryan, S. (2024). Landslide susceptibility evaluation of southeastern Çanakkale strait (NW Türkiye) using logistic regression, artificial neural network and support vector machine. Iranian Journal of Science and Technology, Transactions of Civil Engineering, 48(6), 4575-4591. https://doi.org/10.1007/s40996-024-01367-z
Breiman, L., Cutler, A., Liaw, A., & Wiener, M., (2024). randomForest: Breiman and Cutlers Random Forests for Classification and Regression [R paketi randomForest version 4.7-1.2]. https://doi.org/10.32614/CRAN.package.randomForest
Chen, W., Yan, X., Zhao, Z., Hong, H., Bui, D. T., & Pradhan, B. (2019). Spatial prediction of landslide susceptibility using data mining-based kernel logistic regression, naive Bayes and RBFNetwork models for the Long County area (China). Bulletin of Engineering geology and the Environment, 78(1), 247-266. https://doi.org/10.1007/s10064-018-1256-z
Chen, W., Peng, J., Hong, H., Shahabi, H., Pradhan, B., Liu, J., ... & Duan, Z. (2018). Landslide susceptibility modelling using GIS-based machine learning techniques for Chongren County, Jiangxi Province, China. Science of the total environment, 626, 1121-1135. https://doi.org/10.1016/j.scitotenv.2018.01.124
Chen, W., Pourghasemi, H. R., Kornejady, A., & Zhang, N. (2017). Landslide spatial modeling: Introducing new ensembles of ANN, MaxEnt, and SVM machine learning techniques. Geoderma, 305, 314-327. https://doi.org/10.1016/j.geoderma.2017.06.020

Chowdhuri, I., Pal, S. C., Chakrabortty, R., Malik, S., Das, B., & Roy, P. (2021). Torrential rainfall-induced landslide susceptibility assessment using machine learning and statistical methods of eastern Himalaya. Natural Hazards, 107(1), 697-722. https://doi.org/10.1007/s11069-021-04601-3
CORİNE. (2018). Land cover/landuse maps [Arazi kullanımı haritaları]. Erişim: https://land.copernicus.eu/paneuropean/corine-land-cover
Cruden, D. M. & Varnes, D. J. (1996). Landslides: investigation and mitigation. Chapter 3-Landslide types and processes. Transportation research board special report, (247).
Dai, FC., Lee, CF., Ngai, YY. (2002) Landslide risk assessment and management: an overview. Eng Geol, 64(1):65-87. https://doi.org/10.1016/S0013-7952(01)00093-X
Fidan, S. & Görüm, T. (2020). Türkiye’de ölümcül heyelanların dağılım karakteristikleri ve ulusal ölçekte öncelikli alanların belirlenmesi. Türk Coğrafya Dergisi, 74, 123-134. https://doi.org/10.17211/tcd.731596
Fritsch, S., Guenther, F., Wright, M. N. Suling, M. & Mueller, S. M. (2019). neuralnet: Training of Neural Networks [R paketi neuralnet version 1.44.2]. https://doi.org/10.32614/CRAN.package.neuralnet
Froude, M. J., & Petley, D. N. (2018). Global fatal landslide occurrence from 2004 to 2016. Natural Hazards and Earth System Sciences, 18, 2161-2181. https://doi.org/10.5194/nhess-18-2161-2018
Görüm, T., & Nefeslioğlu, H. (2015). Çok zamanlı heyelan aktivitesinin belirlenmesinde jeomorfolojik bir yaklaşım. Türk Coğrafya Dergisi, (65), 47-58. https://doi.org/10.17211/tcd.19041
Guzzetti, F. (2006). Landslide hazard and risk assessment (PhD Thesis). Mathematisch Naturwissenschaftlichen Fakultät der Rheinischen Friedrich-Wilhelms- Universität, University of Bonn, Bonn, Germany.
Habumugisha, J. M., Chen, N., Rahman, M., Islam, M. M., Ahmad, H., Elbeltagi, A., ... & Dewan, A. (2022). Landslide susceptibility mapping with deep learning algorithms. Sustainability, 14(3), 1734. https://doi.org/10.3390/su14031734
Haque U da Silva PF, Devoli G, Pilz J, Zhao B, Khaloua A, Wilopo W, Andersen P, Lu P, Lee J, Yamamoto T, Keellings D, Wu J-H. & Glass GE. (2019). The human cost of global warming: deadly landslides and their triggers (1995-2014). Sci Tot Environ, 682:673-684. https://doi.org/10.1016/j.scitotenv.2019.03.415
Harmouzi, H., Nefeslioglu, H. A., Rouai, M., Sezer, E. A., Dekayir, A., & Gokceoglu, C. (2019). Landslide susceptibility mapping of the Mediterranean coastal zone of Morocco between Oued Laou and El Jebha using artificial neural networks (ANN). Arabian Journal of Geosciences, 12(22), 696. https://doi.org/10.1007/s12517-019-4892-0
He, Q., Wu, S., Zhao, X., Hui, Z., Wang, Z., Tsangaratos, P., ... & Hao, Y. (2025). Evaluation of landslide susceptibility of mountain highway based on RF and SVM models. Scientific Reports, 15(1), 24991. https://doi.org/10.1038/s41598-025-08774-w
Hossain, M. I., Ferdous, M. N., Bhattacharjee, S., & Rahman, M. (2025). Remote sensing and GIS-driven landslide susceptibility mapping using machine learning for sustainable land management: a study from the Chittagong Hill Tracts of Bangladesh. Discover Sustainability, 6(1), 1200. https://doi.org/10.1007/s43621-025-02084-x
Huqqani, I. A., Tay, L. T., & Mohamad-Saleh, J. (2023). Spatial landslide susceptibility modelling using metaheuristic-based machine learning algorithms. Engineering with Computers, 39(1), 867-891. https://doi.org/10.1007/s00366-022-01695-6
İnegöl Belediyesi (2024). İnegöl istatistik raporu. Bursa: İnegöl Belediyesi.
Jari, A., Khaddari, A., Hajaj, S., Bachaoui, E. M., Mohammedi, S., Jellouli, A., ... & Barakat, A. (2023). Landslide susceptibility mapping using multi-criteria decision-making (MCDM), statistical, and machine learning models in the Aube Department, France. Earth, 4(3), 698-713. https://doi.org/10.3390/earth4030037
Javidan, N., Kavian, A., Pourghasemi, H. R., Conoscenti, C., Jafarian, Z., & Rodrigo-Comino, J. (2021). Evaluation of multi-hazard map produced using MaxEnt machine learning technique. Scientific reports, 11(1), 6496. https://doi.org/10.1038/s41598-021-85862-7
Kavzoglu, T. & Teke, A. (2022). Predictive performances of ensemble machine learning algorithms in landslide susceptibility mapping using random forest, extreme gradient boosting (XGBoost) and natural gradient boosting (NGBoost). Arabian Journal for Science and Engineering, 47(6), 7367-7385. https://doi.org/10.1007/s13369-022-06560-8
Klose, M., Damm, B. & Highland L.M. (2015). Databases in geohazard science: an introduction. Geomorphology, 249:1-3.
Kosmidis, I., Pagui, E. C. K., Boiocchi, F., Sterzinger, P., Konis, K. & Sartori, N. (2025). brglm2: Bias Reduction in Generalized Linear Models [R paketi brglm2 version 1.0.0]. https://doi.org/10.32614/CRAN.package.brglm2
Köy Hizmetleri Genel Müdürlüğü (1995). Bursa ili arazi varlığı. Rapor no: 16, Ankara: T.C. Tarım ve Orman Bakanlığı.
Liu, S., Wang, L., Zhang, W., He, Y., & Pijush, S. (2023). A comprehensive review of machine learning‐based methods in landslide susceptibility mapping. Geological Journal, 58(6), 2283-2301. https://doi.org/10.1002/gj.4666
Lu, Z., Liu, G., Song, Z., Sun, K., Li, M., Chen, Y. & Zhang, W. (2024). Advancements in technologies and methodologies of machine learning in landslide susceptibility research: current trends and future directions. Applied Sciences, 14(21), 9639. https://doi.org/10.3390/app14219639
Ma, S., Shao, X., & Xu, C. (2023). Estimating the quality of the most popular machine learning algorithms for landslide susceptibility mapping in 2018 Mw 7.5 Palu earthquake. Remote Sensing, 15(19), 4733. https://doi.org/10.3390/rs15194733
Ma, T., Yi, X., Ci, H., Wang, R., Yang, H., & Yan, Z. (2026). Landslide Susceptibility Evaluation Integrating Machine Learning and SBAS-InSAR-Derived Deformation Characteristics: A Case Study of Yining County, Xinjiang. Sensors, 26(2), 707. https://doi.org/10.3390/s26020707
Maden Tetkik ve Arama Genel Müdürlüğü Yerbilimleri Çizim Editörü (2023). 1:100.000 ölçekli İnegöl heyelan envanteri haritası. Erişim: https://yerbilimleri.mta.gov.tr/
Maden Tetkik ve Arama Genel Müdürlüğü. (2023). 1:25.000 ölçekli İnegöl jeoloji haritaları. Ankara: Maden Tetkik ve Arama Genel Müdürlüğü.
Mayer, D., Dimitriadou, E., Hornik, K., Weingessel, A., Leisch, F., Chang, C. C., & Lin, C.C. (2024). e1071: Misc Functions of the Department of Statistics, Probability Theory Group (Formerly: E1071), TU Wien [R paketi e1071 version 1.7–16]. https://doi.org/10.32614/CRAN.PACKAGE.E1071
Merghadi, A., Yunus, A. P., Dou, J., Whiteley, J., ThaiPham, B., Bui, D. T., ... & Abderrahmane, B. (2020). Machine learning methods for landslide susceptibility studies: A comparative overview of algorithm performance. Earth-Science Reviews, 207, 103225. https://doi.org/10.1016/j.earscirev.2020.103225
Meteoroloji Genel Müdürlüğü. (2022). İnegöl sıcaklık ve yağış verileri [Veri Seti]. Ankara: Meteoroloji Genel Müdürlüğü.
Orhan, O., Bilgilioglu, S. S., Kaya, Z., Ozcan, A. K., & Bilgilioglu, H. (2022). Assessing and mapping landslide susceptibility using different machine learning methods. Geocarto International, 37(10), 2795-2820. https://doi.org/10.1080/10106049.2020.1837258
Öncü, S. (2021). CBS yöntemiyle Bursa’nın bütünleşik doğal tehlike analizi (Tez No: 696829) [Yüksek Lisans Tezi, Bursa Uludağ Üniversitesi]. Yükseköğretim Kurulu Başkanlığı Tez Merkezi.
Pandey, V. K., Pourghasemi, H. R., & Sharma, M. C. (2020). Landslide susceptibility mapping using maximum entropy and support vector machine models along the Highway Corridor, Garhwal Himalaya. Geocarto International, 35(2), 168-187. https://doi.org/10.1080/10106049.2018.1510038
Park, S., & Kim, J. (2019). Landslide susceptibility mapping based on random forest and boosted regression tree models, and a comparison of their performance. Applied Sciences, 9(5), 942. https://doi.org/10.3390/app9050942
Petley, D. (2012). Global patterns of loss of life from landslides. Geology, 40 (10), 927-930. https://doi.org/10.1130/G33217.1
Pham, B. T., Pradhan, B., Bui, D. T., Prakash, I., & Dholakia, M. B. (2016). A comparative study of different machine learning methods for landslide susceptibility assessment: A case study of Uttarakhand area (India). Environmental modelling & software, 84, 240-250. https://doi.org/10.1016/j.envsoft.2016.07.005
Pham, B. T., Shirzadi, A., Shahabi, H., Omidvar, E., Singh, S. K., Sahana, M., ... & Lee, S. (2019). Landslide susceptibility assessment by novel hybrid machine learning algorithms. Sustainability, 11(16), 4386. https://doi.org/10.3390/su11164386
Phillips, S. J., Anderson, R. P., & Schapire, R. E. (2006). Maximum entropy modeling of species geographic distributions. Ecological modelling, 190(3-4), 231-259. https://doi.org/10.1016/j.ecolmodel.2005.03.026
Reichenbach, P., Rossi, M., Malamud, B. D., Mihir, M., & Guzzetti, F. (2018). A review of statistically-based landslide susceptibility models. Earth-science reviews, 180, 60-91. https://doi.org/10.1016/j.earscirev.2018.03.001
Saha, A., Villuri, V. G. K., & Bhardwaj, A. (2025). Development and assessment of a novel hybrid machine learning-based landslide susceptibility mapping model in the Darjeeling Himalayas. Stochastic Environmental Research and Risk Assessment, 39(10), 4145-4168. https://doi.org/10.1007/s00477-023-02528-8
Schreiber P (1904) Über die beziehungen zwischen dem niederschlag und der wasserführung der flüsse in Mitteleuropa. Meteor 21: 441–452.
Shahzad, N., Ding, X., & Abbas, S. (2022). A comparative assessment of machine learning models for landslide susceptibility mapping in the rugged terrain of northern Pakistan. Applied Sciences, 12(5), 2280. https://doi.org/10.3390/app12052280
Tien Bui, D., Shahabi, H., Omidvar, E., Shirzadi, A., Geertsema, M., Clague, J. J., ... & Lee, S. (2019). Shallow landslide prediction using a novel hybrid functional machine learning algorithm. Remote Sensing, 11(8), 931. https://doi.org/10.3390/rs11080931
URL 1: https://www.olay.com.tr/bursada-heyelan-iki-mahalleyi-tehdit-ediyor-343543
Uzun, M. (2024). Yenişehir (Bursa) Havzası’nın coğrafi karakterizasyonuna dayalı jeoekolojik risk duyarlılığı analizi. International Journal of Geography and Geography Education (IGGE), 51, 85-114. http://dx.doi.org/10.32003/igge.1326841
Uzun, M. (2025). Frekans Oranı ve Yapay Sinir Ağları Yöntemleri İle Samanlı Dağları Kütlesinde Heyelan Duyarlılık Analizi. Doğal Afetler ve Çevre Dergisi,11(2), 538-556. https://doi.org/10.21324/dacd.1663672
Uzun, M., & Garipağaoğlu, N. (2022a). Mekânsal otokorelasyon ve kümeleme analizi yaklaşımı ile Göksu Çayı Havzası’nın (Sakarya Nehri Havzası) bütünleşik ve sür¬dürülebilir havza yönetim modeli. Türk Coğrafya Dergisi, (81), 23-38. https://doi. org/10.17211/tcd.1173420
Uzun, M., & Garipağaoğlu, N. (2022b). Göksu Çayı Havzası’nın (Sakarya Nehri Havzası) tehlike duyarlılık analizleri kapsamında havza yönetimi. Ege Coğrafya Dergisi, 31(2), 2022, s. 449-471. https://doi.org/10.51800/ecd.1160134
Varnes, D. J. (1978). Slope movement types and processes. Special report, 176, 11-33.
Youssef, A. M., El‑Haddad, B. A., Skilodimou, H. D., Bathrellos, G. D., Golkar, F., & Pourghasemi, H. R. (2024). Landslide susceptibility, ensemble machine learning, and accuracy methods in the southern Sinai Peninsula, Egypt: Assessment and Mapping. Natural Hazards, 120(15), 14227-14258. https://doi.org/10.1007/s11069-024-06769-w
Zhou, C., Yin, K., Cao, Y., Ahmed, B., Li, Y., Catani, F., & Pourghasemi, H. R. (2018). Landslide susceptibility modeling applying machine learning methods: A case study from Longju in the Three Gorges Reservoir area, China. Computers & geosciences, 112, 23-37. https://doi.org/10.1016/j.cageo.2017.11.019
Zhao, B., Zhu, J., Hu, Y., Liu, Q., & Liu, Y. (2022). Mapping landslide sensitivity based on machine learning: A case study in Ankang City, Shaanxi Province, China. Geofluids, 2022(1), 2058442. https://doi.org/10.1155/2022/2058442
Zhu, A. X., Wang, R., Qiao, J., Qin, C. Z., Chen, Y., Liu, J., ... & Zhu, T. (2014). An expert knowledge-based approach to landslide susceptibility mapping using GIS and fuzzy logic. Geomorphology, 214, 128-138. https://doi.org/10.1016/j.geomorph.2014.02.003

Ayrıntılar

Birincil Dil

Türkçe

Konular

Doğal Afetler

Bölüm

Araştırma Makalesi

Yazarlar

Melike Durak ^*
0000-0003-3102-9132
Türkiye

Muhammed Mustafa Özdel
0000-0003-0715-4566
Türkiye

Yayımlanma Tarihi

17 Mart 2026

Gönderilme Tarihi

6 Şubat 2026

Kabul Tarihi

2 Mart 2026

Yayımlandığı Sayı

Yıl 1970 Cilt: 0 Sayı: 16

DOI

https://doi.org/10.46453/jader.1883674

IZ

https://izlik.org/JA76SX73CL

APA

Durak, M., & Özdel, M. M. (2026). Akçasu Dere Havzası’nda (İnegöl, Bursa) Heyelan Duyarlılığının Makine Öğrenmesi Modelleri ile Karşılaştırmalı Analizi. Jeomorfolojik Araştırmalar Dergisi, 16, 148-172. https://doi.org/10.46453/jader.1883674

Jeomorfolojik Araştırmalar Dergisi ( JADER ) / Journal of Geomorphological Researches

TR Dizin - Crossref - Google Scholar tarafından taranmaktadır.

Jeomorfoloji Derneği / Turkish Society for Geomorphology ( www.jd.org.tr )

Akçasu Dere Havzası’nda (İnegöl, Bursa) Heyelan Duyarlılığının Makine Öğrenmesi Modelleri ile Karşılaştırmalı Analizi

Öz

Anahtar Kelimeler

Comparative Analysis of Landslide Susceptibility Using Machine Learning Models in the Akcasu Stream Basin (İnegöl, Bursa)

Abstract

Keywords

Kaynakça

Ayrıntılar

Birincil Dil

Konular

Bölüm

Yazarlar

Yayımlanma Tarihi

Gönderilme Tarihi

Kabul Tarihi

Yayımlandığı Sayı

DOI

IZ

Kaynak Göster