چکیده مقاله
Developing reliable landslide susceptibility maps LSM represents a fundamental requirement for effective hazard mitigation, particularly within rapidly developing terrains While receiver operating characteristic–area under the curve ROC–AUC metrics serve as standard benchmarks for assessing model performance, research demonstrates these measures alone provide insufficient validation for map dependability This investigation examines the comparative performance of three machine learning approaches—logistic regression LR , random forest RF , and support vector machine SVM —for landslide hazard prediction within the mountainous terrain located east of Cairo, Egypt The research utilized a balanced dataset comprising 183 landslide occurrences and 183 stable locations, identified through comprehensive field investigations and high resolution satellite analysis Fourteen predictor variables spanning topographic, geological, hydrological, anthropogenic, and triggering factor categories served as input parameters for LSM development While all three algorithms demonstrated robust ROC–AUC performance RF: 0 95, SVM: 0 90, LR: 0 88 , supplementary evaluation using accuracy ACC , recall, precision, F1 score metrics, and spatial rationality assessment revealed substantial variations in model reliability The RF algorithm emerged as the most dependable approach, exhibiting superior performance across all evaluation criteria and minimal classification errors in high risk zones Conversely, both SVM and LR models displayed elevated misclassification frequencies for hazardous and stable areas alike These results emphasize that elevated ROC–AUC scores do not necessarily guarantee practical model reliability for landslide susceptibility assessment
کلیدواژهها
نویسندگان
Mohammad Sadegh Khajooei
Department of Civil Engineering, Hakim Sabzevari University, Sabzevar, Iran
Reza Tadayon Far
Assistant Professor, Department of Civil Engineering, Hakim Sabzevari University, Sabzevar, Iran
شیوه ارجاع
Khajooei, Mohammad Sadegh and Tadayon Far, Reza,1404,Validation and Accuracy Assessment in Landslide Susceptibility Mapping: A Machine Learning Model Comparison,9th International Conference on Civil Engineering Architecture and Urban planning with an approach to urban infrastructure Development
ارائهشده در
مجموعه مقالات نهمین کنفرانس بین المللی عمران، معماری، شهرسازی با رویکرد توسعه زیرساخت های شهری30 مرداد 1404