The hydrological system of thebasin of Lake Urmia is complex, deriving its supply from a network comprising 13 perennial rivers, along withnumerous small springs and direct precipitation onto the lake’s surface. Among these contributors, approximately half of the inflow is attributed to the Zarrineh River and the Simineh River. Remarkably, Lake Urmia lacks a natural outlet, with its water loss occurring solely through evaporation processes. This study employed a comprehensive methodology integrating ground surveys, remote sensing analyses, and meticulous documentation of historical landslides within the basin as primary information sources. Through this investigative approach, we preciselyidentified and geolocated a total of 512 historical landslide occurrences across the Urmia Lake drainage basin, leveraging GPS technology for precision. Thisarticle introduces a suite of hybrid machine learning predictive models, such as support-vector machine (SVM), random forest (RF), decision trees (DT), logistic regression (LR), fuzzy logic (FL), and the technique for order of preference by similarity to the ideal solution (TOPSIS). These models were strategically deployed to assess landslide susceptibility within the region. The outcomes of the landslide susceptibility assessment reveal that the main high susceptible zones for landslide occurrence are concentrated in the northwestern, northern, northeastern, and some southern and southeastern areas of the region. Moreover, when considering the implementation of predictions using different algorithms, it became evident that SVM exhibited superior performance regardingboth accuracy (0.89) and precision (0.89), followed by RF, with and accuracy of 0.83 and a precision of 0.83. However, it is noteworthy that TOPSIS yielded the lowest accuracy value among the algorithms assessed.

Artificial intelligence (AI) applications have introduced transformative possibilities within geohazard analysis, particularly concerning the assessment of rock slope instabilities. This study delves into the amalgamation of AI and empirical techniques to attain highly precise outcomes in the evaluation of slope stability. Specifically, our primary objective is to propose innovative and efficient methods by investigating the integration of AI within the well-regarded Q_slope system, renowned for its efficacy in analyzing rock slope stability. Given the complexities inherent in rock characteristics, particularly in coastal regions, the Q_slope system necessitates adjustments and harmonization with other geomechanical methodologies. Uncertainties prevalent in rock engineering, compounded by water-related factors, warrant meticulous consideration during all calculations. To address these complexities, we present a novel approach through the infusion of fuzzy set theory into the Q_slope classification, leveraging fuzziness to effectively quantify and accommodate uncertainties. Our approach employs a sophisticated fuzzy algorithm encompassing six inputs, three outputs, and 756 fuzzy rules, thereby enabling a robust assessment of rock slope stability in coastal regions. The implementation of this method capitalizes on the high-level programming language Python, enhancing computational efficiency. To validate the potency of our AI-based approach, we conducted preliminary tests on slope instabilities within coastal zones, indicating a promising initial direction. The results underwent thorough evaluation, affirming the precision and dependability of the proposed method. However, it is crucial to emphasize that this work represents a first attempt to apply AI to the evaluation of rock slope stability. Our findings underscore a high degree of concurrence and expeditious stability assessment, vital for timely and effective hazard mitigation. Nonetheless, we acknowledge that the reliability of this innovative method must be established through broader applications across diverse scenarios. The proposed AI-based approach’s effectiveness is validated through a preliminary survey on a slope instability case within a coastal region, and its potential merits must be substantiated through broader validation efforts.

Landslide susceptibility assessment (LSA) is fundamental for managing landslide geological disasters. This study presents a deep learning approach (DNN-MSFM) designed to enhance LSA modeling, particularly addressing limitations caused by the unbalanced distribution of data samples in applied datasets. DNN-MSFM approach combines a deep neural network (DNN) and a mean squared false misclassification loss function (MSFM) to handle unbalanced samples from the algorithmic perspective. The model's performance was evaluated on an unbalanced dataset containing mapping units' records of 293 landslide samples and 653 non-landslide samples from the Baota District, China. Its effectiveness was assessed through statistical metrics and compared against DNN and Support Vector Machine (SVM) basic models. The results demonstrated a significant performance enhancement from the DNN-MSFM (OverallAccuracy = 0.889 and area under the receiver operating characteristic curve (AUC) = 0.84), indicating its effectiveness in learning the underlying landslide susceptibility features and demonstrating its ability to provide improved predictions even in areas with unbalanced landslide samples. Moreover, the study emphasizes the importance of considering balanced loss functions in training DNN under various imbalance degrees and contributes to expanding the applicability of DNN in LSA modeling. Also, this study builds a foundation for further enhancements of deep learning methods for geological disaster assessments.