This study presents an integrated geospatial framework for advanced monitoring and analysis of oil and gas infrastructure using satellite data, Geographic Information Systems (GIS), three-dimensional (3D) geological modeling, and artificial intelligence methods. The objective is to improve the interpretation of subsurface conditions and support better planning of exploration and infrastructure development in geologically complex areas. The proposed workflow combines satellite-derived digital elevation and multispectral data with geological and lithological information to reconstruct 3D reservoir structures and simulate subsurface fluid migration in heterogeneous permeable and semi-permeable layers. The mathematical basis of the model is Darcy’s law extended to a 3D structured grid, while image interpretation and feature recognition are supported by machine learning tools, including convolutional neural networks. The framework enables visualization of stratigraphic architecture, identification of low-permeability barriers, and detection of zones with restricted flow and abnormal pressure accumulation. The obtained results show that the integration of satellite geodata with digital modeling improves the consistency of geological interpretation, supports preliminary drilling-site screening, strengthens environmental risk awareness, and may help reduce unnecessary exploratory actions. The proposed approach may be useful for digital transformation of oil and gas monitoring workflows and for more sustainable management of subsurface resources.
Shukurova et al. (Tue,) studied this question.