Advancing Casing Deformation Detection: A Scalable Real-Time Anomaly Detection Approach Using High Frequency CCL Data

Sensitivity analysis on the interaction between hydraulic and natural fractures based on an explicitly coupled hydro-geomechanical model in PFC2D

Incorporation of sustainability in process control of hydraulic fracturing in unconventional reservoirs

Summary Currently the directional drilling combined with hydraulic fracturing are the most promising and economically feasible mechanisms for shale oil and gas production. There are different methods of fracture distribution estimation resulting from hydraulic fracturing including geochemical ones. Abstract considers in general the stages of geochemical efficiency estimation of hydraulic fracturing in non-conventional reservoirs and shows the possibility of its complex use in determination of HC fluid appurtenance to the bed in development.

We describe a method for the estimation of rock strength and stress between wells using 3D seismic data. The method is demonstrated on the Colorado Shale Formation in Alberta, Canada. The application of the method to these data clearly shows that both rock strength and stress can vary significantly over very short distances. Therefore, it is recommended that this method be used wherever possible to optimize hydraulic fracturing in unconventional reservoirs.

Demand for hydrocarbons is continuing to grow, leading to an increase in the stage count of hydraulic fracturing in unconventional reservoirs. The plug-and-perf system is a typical stimulation method that uses frac plugs for zone isolation. Conventionally, the plugs must be milled out to recover the flow path for hydrocarbons after fracturing is complete. Fully degradable frac plugs would eliminate the need for milling out, and this in turn allows for longer wellbores in the lateral direction, lower costs, and reduced risk in well completion. A key material for fully degradable frac plugs is a sufficiently degradable rubber with good sealing properties for the seal elements of the plugs. This paper presents the fundamental properties of degradable rubbers developed in a comprehensive materials study. The degradation behaviors of the degradable rubbers were investigated under various temperature and fluid media conditions. The mechanical strength was compared with that of conventional nitrile rubber. Nonlinear, three-dimensional multi-body contact analysis and qualification testing were integrated to estimate the sealing performance of seal elements made of the degradable rubbers.

Hydraulic fracturing of unconventional reservoirs has seen a boom in the last century, as a means to fulfill the growing energy demand in the world. The fracturing fluid used in the process plays a substantial role in determining the results. Hence, several research and development efforts have been geared towards developing more sustainable, efficient, and improved fracturing fluids. Herein, we present a dynamic binary complex (DBC) solution, with potential to be useful in the hydraulic fracturing domain. It has a supramolecular structure formed by the self-assembly of low molecular weight viscosifiers (LMWVs) oleic acid and diethylenetriamine into an elongated entangled network under alkaline conditions. With less than 2 wt% constituents dispersed in aqueous solution, a viscous gel that exhibits high viscosities even under shear was formed. Key features include responsiveness to pH and salinity, and a zero-shear viscosity that could be tuned by a factor of ~280 by changing the pH. Furthermore, its viscous properties were more pronounced in the presence of salt. Sand settling tests revealed its potential to hold up sand particles for extended periods of time. In conclusion, this DBC solution system has potential to be utilized as a smart salt-responsive, pH-switchable hydraulic fracturing fluid.

Lithology identification holds a pivotal role in the characterization of subsurface formations. In recent years, the advent of big data and the need for more precise lithology identification have spurred the growing adoption of machine learning algorithms. This paper's primary objective is to leverage unsupervised machine learning techniques for the identification and subsequent removal of anomalies inherent in complex datasets. The Isolation Forest model is the cornerstone of our approach for anomaly detection and elimination. To initiate this process, we employed the K-means algorithm to create clusters, followed by a evaluation using silhouette coefficients. Subsequently, we selected input data for each cluster and conducted exploratory data analysis both prior to and after the removal of outliers. The histograms portraying average anomaly scores for each cluster were thoughtfully presented. For real-time anomaly detection, we harnessed the power of the Isolation Forest model, which facilitated the creation of an Isolation Forest anomalies map by plotting neutron-porosity against bulk density. Our rigorous data analysis employed various statistical techniques, including data statistics, histograms, and cross plots between neutron-porosity and bulk density. This multifaceted approach successfully eradicated anomalies from the dataset, a fact vividly illustrated by the histograms, where anomalies were discernible through their negative scores. The Isolation Forest map conclusively demonstrated the effective removal of outliers from the dataset, underscoring the model's proficiency in identifying and mitigating these anomalies based on their negative scores. The Isolation Forest model has thus exhibited remarkable efficacy in the identification and elimination of data anomalies. Its versatility makes it a valuable asset for the detection and removal of outliers, deviations, or noise from datasets, rendering it particularly well-suited for anomaly detection and outlier mitigation in various analytical scenarios. Notably, the combination of the K-means and Isolation Forest algorithms emerges as a potent and advantageous approach, especially when dealing with extensive datasets and conducting comprehensive analyses.

This article, written by Special Publications Editor Adam Wilson, contains highlights of paper SPE 174118, “Water Management: What We Have Learned and What We Need To Consider for Developing a Shale Play in Argentina,” by J.C. Bonapace, SPE, Halliburton, and F.G. Alric, A. Angeloni, and L. Zangari, Total E&P, prepared for the 2015 SPE Latin American and Caribbean Health, Safety, Environment, and Sustainability Conference, BogotÁ, Colombia, 7–8 July. The paper has not been peer reviewed. Recently, exploration and development of shale plays in Argentina, such as the Vaca Muerta, have begun. To achieve commercial production, this type of reservoir must be stimulated by hydraulic fracturing using large volumes of water. This paper discusses aspects of water logistics necessary during the well-completion phase, fracture-treatment designs applied in Vaca Muerta, and laboratory studies performed on flowback and produced water to help evaluate the potential for water reuse. Introduction Well stimulation using hydraulic fracturing has been used widely for producing oil and gas reservoirs in Argentina since the 1960s. This stimulation technique has been applied in the five hydrocarbon-producing basins shown in Fig. 1, as well as in a variety of formations and types of reservoirs, such as conventional, tight, and, more recently, shale. The majority of shale exploration and development has been in the Vaca Muerta formation, but work has also been assessed in other formations, such as Los Molles, Cacheuta, D-129, and Agrio. Experience gained related to water management in these shale plays during the completion of more than 40 wells (more than 200 hydraulic fractures) by different operators is presented in the paper. Furthermore, laboratory studies were conducted on treated and untreated flowback water, and assessment of its use as fracturing-fluid water is presented. Water Sources and Stimulation Given the economic potential of the Vaca Muerta play, the focus lies on this reservoir. The primary sources of water in the Neuquén basin used to develop these hydrocarbon resources are rivers (Neuquén, Limay, and Colorado), lakes, reservoirs (Cerro Colorado and Pellegrini), or groundwater sources, such as wells with low salinity. These types of wells for water supply need a permit from the regulatory authority, and produced water is not suitable for human consumption or farming.

This article, written by JPT Technology Editor Chris Carpenter, contains highlights of paper SPE 185499, “Fracturing-to-Production Integrated Completion Sensitivities for Horizontal-Well Design in the Vaca Muerta Shale,” by S. Pichon, F. Cafardi, G.D. Cavazzoli, A. Diaz, and M.R. Lederhos, Schlumberger, prepared for the 2017 SPE Latin America and Caribbean Petroleum Engineering Conference, Buenos Aires, 17–19 May. The paper has not been peer reviewed. The boom in organic shale plays has revealed the critical need to size hydraulic-fracture treatments correctly to achieve commercial success. The right balance must be found between the cost of fracturing and the additional production achieved by increasing the formation-to-wellbore contact area. The complete paper examines a range of completion scenarios to evaluate the relationship between hydraulic-fracture design, production, and well profitability by use of numerical simulations to guide completion of horizontal wells in Argentina’s Vaca Muerta Shale. Introduction The Vaca Muerta Shale is the source rock of most of the producing formations in the Neuquén Basin, with high potential as a standalone reservoir. The first well aiming at testing production from the play was drilled and completed in 2010, and, at the end of 2016, the production from the formation involved more than 600 wells. Well-construction practices have moved from creating vertical wells to creating horizontal wells. In any organic shale play, completion has a significant weight in the total well cost and must be sized adequately. Completion design is composed of the volume and number of hydraulic fractures to be created along the lateral, and it must be engineered according to the specific features of each formation. One of the principal features of an organic shale reservoir is the absence of commercial production unless the well is hydraulically fractured. Enhancing the contact area between the formation and the wellbore with hydraulic fractures compensates for the extremely low permeability of these formations. Multiple factors, including geomechanics and stress direction, drive the geometry of the hydraulic fractures. However, it must be noted that most organic shale reservoirs are overpressured. This factor tends to drive the stresses up and reduce their horizontal anisotropy. Besides the hydraulic-fracture geometry, production is also the result of the hydrocarbon volume in place and the interaction of the flow capacities between the reservoir and the created network of conductive fractures. Therefore, the size of this surface of exchange created by the hydraulic fractures has a critical effect on the level and dynamics of the production profile. Finally, economics is the balance between total well cost and production. The completion design affects both production and total well cost, making it a critical parameter. Fracturing-to-Production Integrated Work Flow Work-Flow Requirements. With the primary objective being the combined evaluation of completion design, hydraulic-fracture geometry, production, and economics, the methodology must allow an explicit description, at either the input or output level, of each one of the aforementioned parameters. The fracturing-to-production work flow fits this purpose and is proposed for this study. The work flow has been implemented successfully in the Vaca Muerta and various other shale plays.

Fuzzy anomaly scores for Isolation Forest

ABSTRACT: The bedding interfaces with different cohesions usually exist in unconventional reservoirs. During reservoir stimulation, the slips induced by hydraulic fractures are related to the fracturing effects. In this paper, the rock specimens with cemented and uncemented bedding interfaces were selected to conduct direct shearing experiments, and the slipping behaviors were analyzed using the digital image correlation (DIC) method and acoustic emission (AE) technique. The results show that the slip weakening mode exists in cemented bedding interface during slipping, and the corresponding variation of AE b-value is small. The entire uniform slippage will appear in the uncemented bedding interface during slipping, accompanied by the larger variation of AE b-value. The effects of the interlayer cohesion on the slip weakening zone length, AE magnitude, and the difference between static and kinetic friction were discussed. It is found that the opening feature is not significant during slip weakening, but obvious during cohesionless slipping. And a relationship model was established to describe the opening displacement affected by slipping. This study can help to understand the slip mechanisms during fracturing in unconventional reservoirs. 1. INTRODUCTION Unconventional reservoirs, such as shale, have been the key areas in oil and gas production (Gao et al., 2022). Unlike conventional reservoir rocks, unconventional reservoirs are usually characterized by bedding development. Therefore, investigating the slip of bedding plane in unconventional reservoirs during fracturing is one of the focuses in rock fracture mechanics (Zhao & Gray, 2021). Microseismic monitoring results of in-situ fracturing demonstrate that hydraulic fractures can induce interlayer slip (Rutledge et al., 2016; Tan & Engelder, 2016a). The enhancement of hydraulic conductivity by slip (Zhao et al., 2013; Ye & Ghassemi, 2018) is a crucial factor for promoting shale oil and gas production (Urbancic & Baig, 2016; Wang et al., 2019; Zoback et al., 2012). In field hydraulic fracturing, the slip fractures are usually monitored by microseismic moment tensor analysis (Tan & Engelder, 2016b) and micro-resistivity scanning imaging technology (Zoback & Lund, 2019). Laboratory experiments have also demonstrated that hydraulic fractures can induce interlayer slip at the bedding plane (Chen et al., 2023). Some researchers think that the shear slips of interlaminations during fracturing are part of complex fracture networks (Bunger et al., 2013; Huang et al., 2013; Min et al., 2010; Ye & Ghassemi, 2018).

Anomaly detection in database transactions is critical for safeguarding sensitive information and ensuring the integrity of operations in industries like finance, healthcare, and e-commerce. Existing techniques, including rule-based, machine learning, and deep learning methods, face challenges such as high false positive rates, poor adaptability to evolving patterns, and limited scalability in imbalanced datasets. This research proposes a novel Reinforcement Learning (RL)-based anomaly detection system to address these limitations. The model employs a dynamic reward mechanism and anomaly scoring system to classify transactions accurately while reducing false positives. It leverages the Kaggle Anomaly Detection in Transactions Dataset and a synthetically generated dataset for training and evaluation. Experimental results show that the RL-based model outperforms traditional methods, achieving a precision of 95.2%, recall of 92.4%, and an AUC-ROC score of 97.2%, significantly higher than Autoencoders, Isolation Forest, and Support Vector Machines. The proposed model’s adaptability and robustness make it a scalable solution for real-time anomaly detection, addressing critical gaps in existing techniques. This study advances database security by offering a highly accurate, adaptive, and efficient system for detecting anomalies in complex transactional environments.

BACKGROUND Patient heterogeneity is a key challenge in immunotherapy for IDH-wildtype glioblastoma (GBM), where hypermutated tumors or highly immunosuppressive tumor microenvironments (TME) act as clinical outliers affecting treatment response and trial stratification. We developed Alert-GBM, a radiogenomic AI model designed to flag such outliers based on radiomic signatures from diagnostic imaging. MATERIAL AND METHODS We used multicenter open-access radiogenomic datasets (n = 176) to train unsupervised outlier detection models. Principal Component Analysis (PCA) served as a first-pass filter to harmonize data before applying Isolation Forest (IF) modeling. Three IF models were trained using inter-dataset leave-one-out cross-validation (LOOCV) to simulate real-world performance and were benchmarked against each other. The final model was selected using stratified 10-fold cross-validation (CV). Outliers were validated through visual inspection, statistical profiling, comparison with other outlier detection methods (Local Outlier Factor, One-Class SVM, Mahalanobis distance), and correlation with biological and immune profiles from imaging and omics data. RESULTS The PCA filter identified 3 initial outliers based on MRI metadata. The final IF model, following stratified 10-fold CV, detected 6 outliers across the datasets, with anomaly scores plotted. Flagged cases included large, highly enhancing tumors, minimally enhancing tumors, and post-operative scans. Visualizations using PCA, t-SNE, and UMAP were generated to illustrate separability. False positives and negatives were assessed using immune-based scores, and the distribution of anomaly scores was analyzed with KDE plots. Cross-validation against alternative outlier models confirmed consistency of the flagged cases. CONCLUSION Alert-GBM is a proof-of-concept AI architecture for outlier detection in GBM MRI radiogenomics, capable of flagging cases with atypical immune TME profiles. Integrating such models with radiogenomic immune predictors at the time of diagnosis may support multidisciplinary decision-making and improve patient stratification for immunotherapy trials. Incorporating a human-in-the-loop framework ensures that AI outputs remain clinically interpretable and actionable.

Identifying nonuniform distributions of rock properties and hydraulic fracture trajectories through deep learning in unconventional reservoirs

The rapid growth of network data has increased the complexity of detecting anomalies, which are crucial for ensuring the security and integrity of information systems. This study investigates the use of the Isolation Forest algorithm for anomaly detection in network traffic, utilizing the Luflow Network Intrusion Detection dataset, which contains 590,086 records with 16 features related to network activities. The methodology encompasses data preprocessing (cleaning, normalization, and feature scaling), feature selection (bytes in, bytes out, entropy, and duration), model training, and performance evaluation. The results demonstrate that Isolation Forest can effectively identify anomalies based on feature patterns, isolating suspicious data points without the need for labeled datasets. However, performance metrics, such as accuracy (42.92%), precision (14.37%), recall (2.87%), and F1-score (4.79%), reveal challenges such as high false-positive rates and low sensitivity to true anomalies. These findings highlight the potential of the algorithm for dynamic, high-dimensional datasets but also indicate the need for further improvements through hyperparameter tuning, feature engineering, and alternative approaches. This study contributes to the development of adaptive anomaly detection frameworks for network security and suggests future integration into real-time systems for proactive threat mitigation. The study's findings are particularly relevant for enhancing network security in environments such as corporate and governmental networks, where real-time anomaly detection is crucial.