Mud volcanoes are geological formations resulting from the expulsion of mud, gases, and fluids from deep underground. Monitoring these formations provides critical insights into subsurface processes and geological hazards. This study focuses on detecting recent mud extrusions in mud volcano environments using high-resolution aerial imagery acquired by unmanned aerial vehicles (UAVs). Using UAV-based surveys instead of satellite imagery, we obtain finer spatial detail suitable for identifying subtle textural and chromatic variations in relatively small sites. A binary image classification pipeline was developed to distinguish recent mud from non-mud areas. Traditional machine learning algorithms, including Support Vector Machine (SVM), Random Forest, and Extreme Gradient Boosting (XGBoost), were compared with deep learning architectures such as Convolutional Neural Networks (CNNs), both leveraging transfer learning and custom models. Traditional algorithms rely on handcrafted features, while CNNs learn hierarchical representations directly from raw data. Feature extraction methods were selected based on their ability to distinguish between the two designated classes effectively. To enhance model robustness and generalization, a designed augmentation pipeline was applied before each training epoch or cross-validation fold. This strategy introduced controlled and random variations to simulate real-world imaging conditions, such as varying viewpoints and lighting, ensuring the models generalization, moreover it also minimized data leakage by presenting distinct image variations throughout training. CNNs achieved the highest accuracy, outperforming traditional algorithms and demonstrating the advantages of combining deep learning with effective data augmentation. These findings underscore the potential of CNNs for accurate and efficient monitoring of dynamic geological environments.