Design of an Efficient Satellite Image Analysis Model for Identification of Sustainable Construction Areas via Ground Subsidence Monitoring and Infrastructure Monitoring Operations

To effectively address the pressing issues of urban development and environmental conservation, sustainable construction areas must be identified. In this paper, a proposal for a novel method for segmenting and analyzing satellite images to locate suitable construction sites is based on infrastructure monitoring and ground subsidence monitoring operations. Our method utilizes maximally stable extremal regions with thresholding to accurately classify bodies of water, land areas, bridges, construction zones, forests, and unused land areas. This allows for a comprehensive evaluation of the landscapes. In order to refine our analysis, convolutional neural networks are used to estimate the fertilization levels of the identified areas. To determine whether a structure is suitable by analyzing the characteristics of the surrounding area and calculating the fertility probability levels. By providing a more precise and comprehensive understanding of the surrounding area, this method significantly outperforms existing methods. Extensive experiments were conducted on numerous satellite image datasets to evaluate the performance of our proposed model. With precision and accuracy rates of 99.4% and 98.9%, respectively, and recall rates of 99.2%, the results demonstrate exceptional precision, accuracy, and recall rates. In addition, the model has a remarkable area under the curve score of 98.4%, demonstrating its high discriminatory ability. Importantly, compared to recently proposed models, our method exhibits less delay, enabling rapid decision-making for green building projects. In addition, using Q-learning is a method of reinforcement learning, to incorporate continuous infrastructure monitoring into our model. This integration enables continuous evaluation and improvement of sustainability levels, ensuring the long-term viability of urban areas. It will contribute to reducing environmental impact and enhancing the overall sustainability of urban development by optimizing construction practices iteratively in response to real-time datasets and samples.