Natural disasters such as landslides often occur in the Eastern Black Sea region of Turkey owing to its geological, topographical, and climatic characteristics. Landslide events occur nearly every year in the Arhavi, Hopa, and Kemalpaşa districts located on the Black Sea coast in the Artvin province. In this study, the landslide susceptibility map of the Arhavi, Hopa, and Kemalpaşa districts was produced using the random forest (RF) model, which is widely used in the literature and yields more accurate results compared with other machine learning techniques. A total of 10 landslide-conditioning factors were considered for the susceptibility analysis, i.e., lithology, land cover, slope, aspect, elevation, curvature, topographic wetness index, and distances from faults, drainage networks, and roads. Furthermore, 70% of the landslides on the landslide inventory map were used for training, and the remaining 30% were used for validation. The RF-based model was validated using the area under the receiver operating characteristic (ROC) curve. Evaluation results indicated that the success and prediction rates of the model were 98.3% and 97.7%, respectively. Moreover, it was determined that incorrect land-use decisions, such as transforming forest areas into tea and hazelnut cultivation areas, induce the occurrence of landslides.

Landslides cause serious damage to infrastructure and property in many cities of Turkey, as well as the loss of life. Samsun is one of the cities where landslides are most frequently seen in Turkey. Most of the landslides occurred throughout the province, especially within the Atakum, Canik and İlkadım districts, have been described as natural disaster. In this study, the aim was to produce landslide susceptibility maps for one of these highly sensitive districts, Canik. For this purpose, the parameters of slope, aspect, altitude, topographic wetness index, profile and plan curvature, lithology, distance to drainage network and roads have been used in the landslide susceptibility analysis. Bayesian Probability (BP) and frequency ratio (FR) models have been used in the study. The areas in the produced susceptibility maps have been classified into five groups as "very low, low, moderate, high and very high susceptible". The verification and control results revealed that the landslide susceptibility map generated using the BP model is more accurate than the FR model. At the same time, the very high and high susceptible areas in the landslide susceptibility map produced by BP model were compatible with the control landslides with a rate of 83.5%. These results indicated that the landslide susceptibility map generated using the BP model can be used for land use planning and landslide risk reduction studies. Key Words: GIS, Landslide susceptibility, Bayesian probability model, Frequency ratio model, Canik, Samsun. Bayes Olasılık ve Frekans Oranı Modelleri Kullanılarak Canik (Samsun) İlçesinin HeyelanDuyarlılığının Haritalanması ÖZ: Heyelanlar, Türkiye'nin birçok şehrinde altyapı ve mülkiyete ciddi zarar vermenin yanı sıra can kaybına da neden olmaktadır. Samsun, Türkiye'de heyelanların en sık görüldüğü şehirlerden birisidir. İl genelinde doğal afet olarak nitelendirilen çok sayıda heyelan meydana gelmiştir. Bu çalışmada, Samsun ili Canik ilçesinin heyelan duyarlılık haritaları üretilmiştir. Heyelan duyarlılık analizinde eğim, bakı, yükseklik, topoğrafik nemlilik indeksi, profil ve plan eğriliği, litoloji, drenaj ağlarına ve yola uzaklık parametreleri kullanılmıştır. Çalışmada, bayes olasılık (BO) ve frekans oranı (FO) modelleri kullanılmıştır. Üretilen duyarlılık haritaları, "çok düşük, düşük, orta, yüksek ve çok yüksek derecede duyarlı" alanlar olmak üzere 5 grup altında sınıflandırılmıştır. Doğrulama ve kontrol sonuçları, BO modeli kullanılarak üretilen heyelan duyarlılık harita sının FO modelinden daha doğru olduğunu ortaya koymuştur. Aynı zamanda, BO modeli kullanılarak üretilen heyelan duyarlılık haritasın daki çok yüksek ve yüksek derecede heyelana duyarlı alanların kontrol heyelanları ile %83,5 oranında uyumlu olduğuNote: This paper has been presented at

The aim of this study is to produce landslide susceptibility maps of Şavşat district of Artvin Province using machine learning (ML) models and to compare the predictive performances of the models used. Tree-based ensemble learning models, including random forest (RF), gradient boosting machines (GBM), and extreme gradient boosting (XGBoost), were used in the study. A landslide inventory map consisting of 85 landslide polygons was used in the study. The inventory map comprises 32,777 landslide pixels at 30 m resolution. Randomly selected 70% of the landslide pixels were used for training the models and the remaining 30% were used for the validation of the models. In susceptibility analysis, altitude, aspect, curvature, distance to drainage network, distance to faults, distance to roads, land cover, lithology, slope, slope length, and topographic wetness index parameters were used. The validation of the models was conducted using success and prediction rate curves. The validation results showed that the success rates for the GBM, RF, and XGBoost models were 91.6%, 98.4%, and 98.6%, respectively, whereas the prediction rate were 91.4%, 97.9%, and 98.1%, respectively. Therefore, it was concluded that landslide susceptibility map produced with XGBoost model can help decision makers in reducing landslide-associated damages in the study area.

No abstract