Abstract

Remote sensing has become a critical tool in environmental monitoring, offering precise data collection over large areas. However, traditional methods face challenges such as high computational costs and lower accuracy in complex environments. The primary challenge is optimizing data processing to improve accuracy and efficiency in extracting valuable environmental information from remote sensing data. This study proposes a novel approach combining Ant Colony Optimization (ACO) and Region-based Convolutional Neural Networks (RCNN) for enhanced precision in environmental monitoring. ACO, inspired by the foraging behavior of ants, is used to optimize the parameters and feature selection process. RCNN, a deep learning model, is employed to detect and classify environmental features from remote sensing imagery. The integration of ACO with RCNN aims to enhance the model’s performance by selecting the most relevant features and optimal parameters, thereby reducing computational costs and improving accuracy. The proposed method was tested on a dataset of satellite images for land cover classification. The hybrid ACO-RCNN approach achieved a classification accuracy of 93.2%, outperforming traditional methods by 8.7%, and reduced computational time by 25%. These results demonstrate the efficacy of the proposed method in precision environmental monitoring.