Digital Twin (DT) technology has rapidly matured from pilot projects to integral components of advanced asset management and process optimization in the oil and gas (O&G) industry. This review provides a structured synthesis of the current state of digital twin frameworks, with a focus on offshore and topside gas-processing systems, such as those found on Floating Production Storage and Offloading (FPSO). Emphasis is placed on high-fidelity process simulations and scalable architectures integrating real-time data with advanced analytics. Drawing on over 85 peer-reviewed sources and industrial frameworks, the paper outlines modular DT architectures, encompassing steady-state and dynamic process simulations (e.g., Aspen HYSYS), reduced-order and hybrid machine learning models, co-simulation environments, and advanced equation-of-state packages (e.g., GERG-2008). Special attention is given to compressor map integration, Equations of State (EOS) selection, ISO/IEC standard compliance, and digital thread continuity. Additionally, the review explores economic and sustainability-driven DT implementations, including flare and methane mitigation, ISO 50001-aligned energy optimization, and lifecycle/decommissioning strategies. It concludes with a technical and economic assessment of DT maturity for gas compression facilities, identifying research gaps in standardization, long-term validation, and cybersecurity integration. The insights provided are intended to support decision-makers, engineers, and researchers in deploying scalable, auditable, and high-impact DT solutions across the O&G value chain.

Identifying new constructions in large cities can be done simply, quickly, and at low cost by applying image processing techniques on time-series remote sensing (RS) images and producing land cover maps. In recent years, object-based (OB) image classification has attracted significant attention as a method for land cover mapping. This method consists of two steps: segmentation and classification. In this research, we will develop a new approach based on image processing techniques to be utilized in the OB classification method for the analysis of urban growth. In this approach, we propose a multi-phase segmentation for the segmentation step and a rule-based method for the classification step. Besides speeding up the process of OB classification, the accuracy of the final preliminary results is another advantage of the proposed approach. Moreover, for collecting RS images, a two-zoom level data collection is adopted using an open source RGB RS database. An important application of analyzing RS images is the detection of non-authorized communities formation around water reservoirs. Therefore, in our preliminary experiments, we selected three different regions around Guarapiranga reservoir in Sao Paulo, Brazil, for collecting our RS images.

Reservoirs are fundamental infrastructures for the management of water resources. Constructions around them can negatively impact their water quality. Such constructions can be detected by segmenting man-made objects around reservoirs in the remote sensing (RS) images. Deep learning (DL) has attracted considerable attention in recent years as a method for segmenting the RS imagery into different land covers/uses and has achieved remarkable success. We develop an approach based on DL and image processing techniques for man-made object segmentation around the reservoirs. In order to segment man-made objects around the reservoirs in an end-to-end procedure, segmenting reservoirs and identifying the region of interest (RoI) around them are essential. In the proposed two-phase workflow, the reservoir is initially segmented using a DL model, and a postprocessing stage is proposed to remove errors, such as floating vegetation in the generated reservoir map. In the second phase, the RoI around the reservoir (RoIaR) is extracted using the proposed image processing techniques. Finally, the man-made objects in the RoIaR are segmented using a DL model. To illustrate the proposed approach, our task of interest is segmenting man-made objects around some of the most important reservoirs in Brazil. Therefore, we trained the proposed workflow using collected Google Earth images of eight reservoirs in Brazil over two different years. The U-Net-based and SegNet-based architectures are trained to segment the reservoirs. To segment man-made objects in the RoIaR, we trained and evaluated four architectures: U-Net, feature pyramid network, LinkNet, and pyramid scene parsing network. Although the collected data are highly diverse (for example, they belong to different states, seasons, resolutions, etc.), we achieved good performances in both phases. The F1-score of phase-1 and phase-2 highest performance models in segmenting test sets are 96.53% and 90.32%, respectively. Furthermore, applying the proposed postprocessing to the output of reservoir segmentation improves the precision in all studied reservoirs except two cases. We validated the prepared workflow with a reservoir dataset outside the training reservoirs. The F1-scores of the phase-1 segmentation stage, postprocessing stage, and phase-2 segmentation stage are 92.54%, 94.68%, and 88.11%, respectively, which show high generalization ability of the prepared workflow.