The digital twin (DT), which involves creating a virtual replica of a physical asset or system, has emerged as a transformative set of tools across various industries. In the oil and gas (O&G) industry, the development of DTs represents a significant evolution in how companies manage complex operations, enhance safety, and optimize decision-making processes. Despite these significant advancements, the underlying tools, technologies, and frameworks for developing DTs in O&G applications remain non-standardized and unfamiliar to many O&G practitioners, highlighting the need for a systematic literature review (SLR) on the topic. Thus, this paper offers an SLR of the existing literature on DT development for O&G from 2018 onwards, utilizing Scopus and Web of Science Core Collection. We provide a comprehensive overview of this field, demonstrate how it is evolving, and highlight standard practices and research opportunities in the area. We perform broad classifications of the 98 studies, categorizing the DTs by their development methodologies, implementation objectives, data acquisition, asset digital development, data integration and preprocessing, data analysis and modeling, evaluation and validation, and deployment tools. We also include a bibliometric analysis of the selected papers, highlighting trends and key contributors. Given the increasing number of new DT developments in O&G and the many new technologies available, we hope to provide guidance on the topic and promote knowledge production and growth concerning the development of DTs for O&G.

In pervasive healthcare monitoring, activity recognition is critical information for adequate management of the patient. Despite the great number of studies on this topic, a contextually relevant parameter that has received less attention is intensity recognition. In the present study, we investigated the potential advantage of coupling activity and intensity, namely, Activity-Intensity, in accelerometer data to improve the description of daily activities of individuals. We further tested two alternatives for supervised classification. In the first alternative, the activity and intensity are inferred together by applying a single classifier algorithm. In the other alternative, the activity and intensity are classified separately. In both cases, the algorithms used for classification are k-Nearest Neighbors (KNN), Support Vector Machine (SVM), and Random Forest (RF). The results showed the viability of the classification with good accuracy for Activity-Intensity recognition. The best approach was KNN implemented in the single classifier alternative, which resulted in 79% of accuracy. Using two classifiers, the result was 97% accuracy for activity recognition (Random Forest), and 80% for intensity recognition (KNN), which resulted in 78% for activity-intensity coupled. These findings have potential applications to improve the contextualized evaluation of movement by health professionals in the form of a decision system with expert rules.

We present an architecture that includes two essential services to compose the supporting infrastructure required by context-aware applications: a Context Service, that provides access to context information, and a Discovery Service. A reference implementation, based on Web Services technology, was used to develop a remote assisted living application, which relies on ambient sensors, placed in each room, to capture context information and on a combo medical appliance to perform blood pressure measurements on the patient, according to a care plan prescribed by a doctor. The collected set of context data may be transmitted to a monitoring centre and also interpreted locally using medical knowledge; the identification of a patient's abnormal condition can activate local actions or send an emergency message to a monitoring centre. This infrastructure can help a doctor to monitor and assist the patient while he or she is performing daily activities and may also help improving the patient's treatment compliance and quality of life.

Summary: This research addresses one of the most critical challenges in oilwell drilling: the early detection of kick anomalies. A kick anomaly is characterized by an undesirable influx of formation fluids into the wellbore, which can lead to severe safety hazards, making its timely identification essential to ensure the safety of all personnel involved and to maintain operational continuity. As kick cases are rare and operational methods often overestimate their occurrence, deep learning anomaly detection techniques are valuable for enhancing efficiency and minimizing false alarms. By using different autoencoder (AE) models, especially with convolutional networks, the aim of this study is not only to improve the accuracy of kick detection but also to anticipate the detection significantly. Based on the analyses of kick anomalies in deepwater offshore wells located in pre-salt Brazilian oil fields, we used real-time drilling data from correlation wells without anomalies to train different AE architectures. The data set comprised 730 hours of historical real-time monitoring records from eight offshore drilling operations across two different oil fields, during which two real kicks were documented. The results indicate that the 1D convolutional neural network AE (1D CNN-AE) outperforms five other well-established AE models reported in the literature for detecting kicks during offshore drilling operations. The 1D CNN-AE model demonstrated high efficacy in the early identification of kick events, achieving a recall rate of 100%. Furthermore, it yielded a 31% reduction in the historical false kick rate (FKR), indicating a substantial improvement in event classification accuracy. In addition to its predictive reliability, the model provided a mean early detection time (EDT) of approximately 100 minutes prior to the corresponding operational reports, reinforcing its potential as a robust tool for real-time decision support in well control operations. This study presents three original contributions: (i) a framework outlining the neural network techniques used in the literature to address the kick detection problem; (ii) a comprehensive investigation and preprocessing of kick event data recorded between 2018 and the first semester of 2025 in specific deepwater offshore wells in Brazil; and (iii) a prototype based on a 1D CNN-AE architecture.

No Brasil, a Análise do Impacto Regulatório (AIR) vem se consolidando nas últimas décadas nas agências reguladoras federais. A metodologia AIR tem como objetivo examinar o processo regulatório, medir os custos e os benefícios gerados, assim como outros efeitos de natureza social, política ou econômica que podem ser causados por uma regulação nova ou já existente. Ao analisar cada opção regulatória, o especialista trata variáveis de natureza qualitativa de difícil mensuração e de elevado grau de incerteza. O trabalho complementa a literatura existente, dado que poucos trabalhos no âmbito da AIR têm empregado metodologias de apoio à decisão que incorporem o conhecimento do especialista de forma independente do problema a ser tratado. Portanto, propõe-se uma abordagem exploratória usando um Sistema Especialista Fuzzy (SEF), o qual, incorporando o conhecimento tácito dos especialistas, contribui para enriquecer o processo de decisão na fase final de comparação das opções regulatórias, permitindo o acesso do tomador de decisão a um histórico de parte dos raciocínios de outros especialistas.

Human Activity Recognition (HAR) plays a crucial role in applications such as health monitoring, physical training, and therapeutic support. Smartphones equipped with embedded sensors provide a convenient platform for these applications. However, running deep learning models continuously can drain device energy autonomy. Despite recent advances, few studies have explored how executing deep learning-based HAR models across different computational environments affects energy consumption, especially when combined with strategies that leverage application-level contextual information. This work develops and evaluates optimized deep learning models, including variants with early exits, in both local and remote execution scenarios. It also incorporates an adaptive sampling strategy that dynamically adjusts sensor reading frequency according to movement intensity (contextual information). Results show that the proposed approach reduces energy consumption and inference time while preserving model accuracy.