Soil liquefaction is a major contributor to earthquake damage. Evaluating the potential for liquefaction by conventional experimental or empirical methods is both time-intensive and laborious. Utilizing a machine learning model capable of precisely forecasting liquefaction potential might diminish the time, effort, and expenses involved. This research introduces an innovative predictive model created in three phases. Initially, correlation analysis determines essential elements affecting liquefaction. Secondly, predictions are produced using Convolutional Neural Networks (CNN) and Deep Belief Networks (DBN), verified by K-fold cross-validation to guarantee resilience. Third, Ant Colony Optimization (ACO) improves outcomes by increasing convergence efficiency and circumventing local minima. The suggested EC + ACO model substantially surpassed leading approaches, such as SVM-GWO, RF-GWO, and Ensemble Classifier-GA, attaining a very low False Negative Rate (FNR) of 2.00 % when trained on 90 % of the data. A thorough performance evaluation shown that the model achieved a cost value of 1.133 % by the 40th iteration, exceeding the performance of other models such SVMGWO (1.412 %), RF-GWO (1.305 %), and Biogeography Optimized-Based ANFIS (1.7439 %). The model exhibited significant improvements in convergence behavior, with a steady decline in cost values, especially between the 20th and 50th iterations. Additional validation using empirical data from the Tohoku-oki, Great East Japan earthquake substantiated the EC + ACO model's enhanced accuracy and dependability in mirroring observed results. These findings underscore the model's resilience and efficacy, providing a dependable method for forecasting soil liquefaction and mitigating its seismic effects.

This paper proposes a novel data-driven framework for scour detection around offshore wind turbines (OWTs), where damage features are derived from wind and wave-induced acceleration signals collected along the tower. A numerical model of the NREL 5 MW wind turbine, which considers aerodynamic and hydrodynamic loading with soil-structure interaction (SSI) and servodynamics, is developed. The model is used to simulate the acceleration responses along the tower for a healthy structure, and a structure affected by progressive scour. A data segmentation process is initially performed on the collected data, which is followed by a feature selection scheme based on the analysis-of-variance (ANOVA) algorithm, to eliminate irrelevant characteristics from the time domain feature set of responses. The proposed framework consists of two main components: (a) offline training, and (b) real-time classification. The acceleration responses collected from the healthy structure and the structure subjected to three different damage scenarios (different scour depths) and under various load conditions, are used in the offline training mode. The selected feature vector from the feature extraction process is used as input to a Naive Bayes classifier (NBC) algorithm to train the model. In the real-time classification, a prediction of the scour depth affecting the structure is performed using a new dataset simulated from unseen load cases and scour conditions of the OWT. The results show that the model trained in the offline stage can predict the scour depth in the real-time monitoring stage with performance measures over approximately 94%.