Geological Parameters Research Articles

Improving the selection of object-analogues of oil and gas fields in designing reservoir engineering

Relevance. The commissioning of a large number of new fields with limited amount of initial geological and physical data. To fill in the missing data, the selection of object-analogs is carried out. From the correct choice the selected development system will depend. But according to the established practice, the choice of analogues is carried out only by the expert method, based on the search for the geographically closest objects being developed. The effectiveness of the chosen development strategy depends on the selected analogues, which in their turn will minimize the risks of oil companies during the operation of assets. Aim. Development of an algorithm for qualitatively selection of the best object-analogue of the project field, taking into account the verification of the selected analogues. Methods. Evaluation and analysis of the necessary data to define the degree of similarity of reservoir development by the methods of mathematical statistics and machine learning. Results. The authors describe the problem in the selection of objecvt-analogues and the existing approaches to its solution. The paper introduces the prospects and possibilities of applying the accumulated experience in the developing of new assets and provides an algorithm for the selection of analogues based on a qualitative assessment of geological parameters and quantitative assessment of the degree of similarity of geological and physical characteristics of the object. The results obtained show that the method allows you to quickly find analogues from massive databases, and has a high degree of correlation with the variants of deposits agreed upon by the state expertise for the development of hydrocarbon fields. The authors proposed a way of applying the analogy method to predict the missing data.

Intelligent rockburst level prediction model based on swarm intelligence optimization and multi-strategy learner soft voting hybrid ensemble

Rockbursts are highly destructive geological events that pose serious risks to the safety of underground engineering projects, including tunnels, mines, and other subterranean structures. Accurate prediction of rockburst occurrence and intensity is crucial for preventing and mitigating their potentially catastrophic impacts. Such predictions are vital not only for ensuring the safety of workers and infrastructure but also for optimizing construction and operational strategies in underground environments. This research is developing a smart model to predict rockburst levels by combining advanced swarm intelligence with a hybrid ensemble method that uses multiple strategies and classifiers for soft voting. By collecting and analyzing 287 rockburst cases from diverse geological settings around the world, a comprehensive and representative database was constructed. This database was subsequently subjected to in-depth statistical and correlation analyses to identify key patterns and relationships. The data preprocessing method proposed in this study, based on an improved version of the Student t-SNE algorithm, effectively reduced the negative impact of data noise on model performance, enhancing the reliability of predictions. Furthermore, the prediction model developed in this study not only demonstrated exceptional prediction accuracy on the test set but also provided valuable insights into key geological parameters influencing rockbursts through rigorous sensitivity analysis. The proposed hybrid ensemble model greatly improves generalization and interpretability over traditional single models. It offers an efficient, data-driven approach to rockburst prediction, providing a strong scientific foundation for safety management and risk mitigation in underground engineering worldwide.

Study of the Influence of Well Operation Parameters of a Carbonate Reservoir Oil Formation on the Coefficient of Productivity Using Statistical Methods of Analysis

Well productivity index is one of the most important indicators for the development of carbonate reservoirs of oil fields, control and maintenance of high values of which determines the levels of hydrocarbon production. Determination of the complex influence of geological and technological factors on production capabilities of wells remains an actual direction of research in the field of oil producing. The present paper is devoted to improving the efficiency of production wells in a carbonate reservoir oil deposit based on the results of evaluation and consideration of the relationship between the productivity index and geological and field parameters such as reservoir pressure, bottomhole pressure, skin-factor, gas-oil ratio, water cut, using statistical methods of analysis. At the stage of preparation of initial data the materials of hydrodynamic and production-geophysical studies performed on the wells during the whole period of development of oil reservoir of one of the fields of Perm region were involved. The analysis of the obtained data sample with the use of statistical methods allowed us to study the relationships between the specific well productivity index and the considered geological and production parameters. Multivariate statistical models were developed using stepby-step regression analysis, collectively demonstrating the predominant influence of bottomhole pressure, reservoir pressure and water cut on the specific well productivity index based on the frequencies of occurrence of parameters and the order of their inclusion in the model. The study of the dynamics of changes in the accumulated multiple correlation coefficient during the development of statistical models allowed us to identify the ranges (areas) of change in the values of the specific well productivity index, which are characterized by individual correlations with geological and production parameters described by the corresponding mathematical dependencies. The developed models are characterized by high quality, which is confirmed by their statistical evaluations when comparing forecast and factual values of specific well productivity index. The criteria of applicability of models for conditions of carbonate reservoirs of oil fields are formed. The results of the study can be used for justification and regulation of technological modes of well operation, planning programs of optimization measures.

Research on the Parameter Prediction Model for Fully Mechanized Mining Equipment Selection Based on RF-WOA-XGBoost

Fully mechanized mining equipment is core to the coal mining process. The selection process for this type of equipment is complex and heavily relies on experts’ experience for determining equipment parameters. This paper proposes a fully mechanized mining equipment parameter prediction model based on Extreme Gradient Boosting Regression Trees (XGBoost), which is developed based on the mapping relationships among geological parameters, fully mechanized mining face conditions, and the parameters of fully mechanized mining equipment. Feature selection is performed based on the feature importance ranking obtained through the Random Forest (RF) method, thereby reducing the model complexity. Different optimization algorithms are used to optimize the hyperparameters of XGBoost, and the results show that the Whale Optimization Algorithm (WOA) outperforms other algorithms in terms of convergence speed and optimization effectiveness. By comparing different prediction algorithms, it is found that the WOA-XGBoost model achieves higher prediction accuracy on the test set, with an average absolute error of 0.0458, root mean square error of 0.1610, and a coefficient of determination (R2) of 0.9451. Finally, a RF-WOA-XGBoost-based parameter prediction model for fully mechanized mining equipment is established, which is suitable for lightly inclined mining faces. This model reduces input complexity, improves the selection speed, minimizes reliance on experts, and ensures prediction accuracy, providing an effective reference for the parameter selection of fully mechanized mining equipment.

Intelligent characterization of ultra-deep carbonate strike-slip fault zones based on 3DResNeSt-UNet: a case study of the YueMan Block in the Tarim Basin

The strike-slip fault zones (SSFZ) in the ultra-deep carbonate rocks of the Tarim Basin provide crucial space for the migration and accumulation of oil and gas. Traditional 3D seismic interpretation methods have limitations in identifying SSFZ. This study proposes a seismic interpretation method based on the 3DResNeSt-UNet to identify SSFZ more effectively. This network integrates the 3DUNet and ResNeSt modules, using synthetic 3D seismic data and its corresponding label data as inputs for training. The synthetic seismic data incorporates geological knowledge and geological body parameters. Initially, by combining field outcrop observations, logging, and seismic data, the geological patterns of SSFZ are summarized. Guided by these geological patterns and based on the geological body parameters extracted from logging and seismic data, synthetic 3D seismic data and its corresponding label data are generated. The results indicate that the accuracy of the 3DResNeSt-UNet model on the training data exceeds 98%. The trained model achieves good recognition results on the seismic data of the YueMan block. Compared with traditional seismic interpretation results, the model’s recognition accuracy is significantly improved and more aligned with geological understanding. Overall, the 3DResNeSt-UNet provides a new effective method for identifying SSFZ and has great potential for application in similar seismic interpretation scenarios.

Lost circulation intensity characterization in drilling operations: Leveraging machine learning and well log data.

Lost circulation is one of the important challenges in drilling operations and bears financial losses and operational risks. The prime causes of lost circulation are related to several geological parameters, especially in problem-prone formations. Herein, the approach of applying machine learning models to forecast the intensity of lost circulation using well-log data is presented in this work. It concerns a gas field in northern Iran and contains nine well logs with lost circulation incidents categorized into six intensity classes. After rigorous exploratory analysis and preprocessing of the data, seven machine learning methods are applied: Random Forest, Extra Trees, Decision Tree, XGBoost, k-Nearest Neighbors, Support Vector Machine, and Hard Voting. Random Forest, Extra Trees, and Hard Voting are the best-performing methods. These models attained the most robust results on both key performance metrics and, hence, can predict the intensity of lost circulation quite well. Models of Extra Trees and Hard Voting show very high predictive performance values. On the other hand, their limitations in some intensity classes suggest further refinement. In this regard, the ensemble methods are highly effective for managing the multivariate nature of the task. Hard Voting aggregates multiple classifiers, becoming superior to individual models like support vector machines. This paper offers new insight into integrating machine learning to well-log data toward enhancing lost circulation prediction by offering a dependable foundation for real-time drilling decision-making. These results show that the models have the potential to lower operational risks, improve drilling safety, and minimize nonproductive time; hence, they form a quantum leap in lost circulation control.

Enhancing hydraulic fracturing efficiency through machine learning

Hydraulic fracturing (HF) is a technique employed in the oil and gas industry to extract hydrocarbon resources from shale formations and low-permeability rocks. This process involves the creation of new fractures and the extension of existing ones within the rock by injecting a high-pressure fracturing fluid, which enhances the flow of hydrocarbons. To assess the efficiency and safety of HF, various factors such as fracture orientation, geometry, length, distribution, and stimulated reservoir volume are analyzed. In the complex field of HF, the accurate assessment of fracture parameters is crucial for optimizing operational efficiency and ensuring environmental safety. This study investigates the role of machine learning (ML) methodologies in enhancing the precision of these assessments, with a particular focus on fracture width a critical factor in the effectiveness of HF. By utilizing a comprehensive dataset from hydrocarbon fields, in this study, the application of several advanced ML models was investigated, including Artificial Neural Networks (ANNs), Random Forest (RF), and K-Nearest Neighbors (KNNs). These models were specifically employed to predict and assess fracture width based on a variety of geological and operational parameters: geometric factors (γ), Shear Modulus (G), Poisson’s ratio (ν), viscosity of the fracturing fluid (µ in centipoise), crack height (h), fluid efficiency (η), injection time (t), and crack length (x). This study evaluated the performance of ANN, RF, and KNN models, achieving accuracies of 0.978, 0.979, and 0.893, respectively, which underscores their strong predictive modeling capabilities. The results were meticulously documented for each methodology. The RMSE values for ANN, KNN, and RF were 7.552, 15.711, and 6.194, respectively. Notably, the RF approach demonstrated superior performance with an RMSE of 6.194, establishing it as the most accurate method. This study highlights the transformative potential of ML in the pre-stimulation planning phase of HF, enabling enhanced real-time decision-making and operational optimization, which ultimately results in more effective and efficient fracturing operations.

Hydraulic fracturing in deposits of terrigenous reservoirs of Ural-Volga deposits

The work is devoted to improving the processes of developing layers of terrigenous objects of one of the deposits of the Ural-Volga region and improving the technical and economic performance of enterprises of the fuel and energy complex. At the moment, most of the fields in the oil-bearing territory under consideration are characterized by high rates of reserve production, which are accompanied by a significant increase in waterlogging and complications affecting the completeness of resource extraction. However, with the general trend towards the development of reserves in the fields, deposits and areas of the zone with low production are often distinguished, characterized by low permeability and high heterogeneity, including in highly productive development facilities. The authors conducted a review of hydraulic fracturing methods in world and Russian practice. The classification of hydraulic fracturing methods and the features of its implementation are described. In the conditions of the field under consideration, the domestic experience of hydraulic fracturing and modern technologies in the design of hydraulic fracturing are analyzed. The influence of geological, technological factors and features of the development of the research object on the efficiency of hydraulic fracturing has been studied. The regularities of the influence of geological and technological parameters on the efficiency of hydraulic fracturing have been revealed, which can be successfully taken into account when designing operations in various geological and physical conditions of development. Based on the results of combining the results of the study, a number of conclusions were made that reduce the risks of making low-effective management decisions, which, in conditions of the need for operational development of residual oil reserves, is an integral part of the strategy of subsurface users. Keywords: hydraulic fracturing; terrigenous reservoir; colmatation; bottom-hole formation zone; reperforation; waterlogging; fluid flow rate; displacement characteristics.

An experimental approach to estimating the current oil recovery coefficient using a complex of stochastic and numerical computer modeling methods

This paper presents an experimental study devoted to determining the prospects for the integrated application of stochastic and numerical computer modeling methods to solve one of the fundamental problems of field development – assessing current oil recovery based on various parameters that reflect the properties of productive formations and their saturating fluids. The object of the study was the long-term deposits of the Volga–Ural oil and gas province. As part of the initial stage, a discriminant analysis was carried out according to the tectonic-stratigraphic criterion, as a result of which three clusters of homogeneous objects were formed based on seventeen parameters. When interpreting the distribution of deposits in the axes of canonical discriminant functions, the unstable parameter of the total thickness of the reservoir was replaced by one of the variable indicators selected using the digital implementation of the uniform search method and its interpretation using known approaches. In order to reduce the influence factor of the uncertainty zone that arises when considering objects in the axes of canonical discriminant functions, the method of constructing structured grids was used. The reliability and scope of the obtained dependence were established using the Broyden-Fletcher-Goldfarb-Shanno optimization algorithm. The conclusion is made about the possibility of using the developed scientific and methodological approach to forecasting oil recovery at different values of the well grid density. Keywords: oil recovery coefficient; modeling of nonlinear systems; deposits of the Volga-Ural oil and gas province; tectonic and stratigraphic confinement of objects; stochastic and numerical methods of computer analysis and data processing; development of oil fields, geological and field parameters.

Optimization of the development process for complex deposits of the Tyumen suite using flow-diverging systems

Interest in the industrial exploitation of hard-to-recover reserves is growing due to the depletion of the major sources of the country's resource base. These resources are presented by long-developed and multi-layered fields. In most cases oil flow rate from wells in these fields do not exceed five tons daily. This situation affects both extraction costs and the operational performance of the deposits. Currently, under the existing technical and economic conditions, further development of these reserves is becoming unprofitable. This is due to the necessity of planning, designing, and implementing complex geological and technological measures, along with interpreting the extensive data obtained from geophysical surveys.The aim of this study is to optimize oil extraction processes by injecting flow-diverging compositions in the development of complex and low-yield deposits in the West Siberian oil and gas province associated with the Tyumen suite.To achieve this aim, we summarized experiences from the studied field and similar fields with comparable geological conditions. We also studied the history of operations involving flowdiverging systems in various tectonic and stratigraphic units. Additionally, we conducted a basic interpretation of geophysical study results from similar fields to identify analogues for creating isolation screens By analyzing existing geological and field data, we verified criteria to perform processing by flow-diverging compositions in the studied field.Based on the analysis of measures for the implementation of physical and chemical methods to increase oil recovery, we defined a list of recommended basic compositions for initial implementation of this method in the geological conditions under consideration. Taking into account the geological and technological parameters of well operation, we developed a targeted program for injecting flow-diverging compositions. This program will help exploit remaining liquid hydrocarbon reserves and establish primary criteria for selecting candidate wells. We concluded that the results obtained can be replicated in similar fields to optimize the development of low-yield deposits of the Tyumen suite.

Analogs of Precambrian microbial communities formed de novo in Caucasian mineral water aquifers.

The microbiome of deep continental aquifers is considered the most slowly evolving part of the biosphere. The Yessentukskoye Mineral Water Basin (YMWB), located in the pre-Caucasus region, contains three closely spaced but distinct aquifers, the Upper Cretaceous, the Lower Cretaceous, and the Upper Jurassic, which represent unique objects for subsurface biosphere research due to gas-hydrogeochemical and thermal anomalies of the area. We analyzed the geological and hydrogeochemical parameters of the three aquifers and a recharge area of the YMWB and investigated their microbial communities using metagenomic and cultivation-based approaches within a long-term survey. Correlation analysis of the obtained data revealed stable and highly stratified microbial communities inhabiting four distinct ecosystems. Their structure and the metabolic traits of their prokaryotic populations were similar to those presumed to have dominated the Earth's biosphere during several critical periods of its evolutionary history, that is, the Early Archean, the period of banded iron formations accumulation, and the Great Oxidation Event. Among the YMWB strata, the Upper Jurassic aquifer, supersaturated with CO2, influenced by magmatic activity, and highly enriched with thermophilic autotrophic hydrogenotrophic acetogens, turned out to be the first described modern ecosystem based on the primary production by a process predicted to support the Last Universal Common Ancestor (LUCA). The characterization of the YMWB microbial communities reveals a contemporary model environment of the early stages of Earth's development and thus contributes to the understanding of the evolutionary traits in microbial populations that may have played a critical role in the formation of the modern biosphere.IMPORTANCEContinental subsurface environments are estimated to harbor up to one-fifth of the planet's total biomass, representing the most stable and slowly evolving part of the biosphere. Among the deep subsurface inhabitants, the microbial communities of drinking mineral waters remain the least studied. Our interdisciplinary study of the Yessentukskoye Mineral Water Basin shows how hydrochemical and hydrodynamic factors shape different subsurface ecosystems, whose microbial populations influence the composition of mineral waters. A comprehensive analysis reveals the similarity of these ecosystems to those predicted for the early Earth. The deepest of the studied aquifers is the first described modern ecosystem with the most probable primary producer performing hydrogenotrophic acetogenesis. Thus, our results contribute to the understanding of the genesis of modern drinking water resources and expand the knowledge of the evolutionary traits that may have played a critical role in the formation of the Earth's biosphere.

Study on the Influence of Geological Parameters of CO2 Plume Geothermal Systems

At present, there are relatively few studies on the exploitation of geothermal resources in depleted high-temperature gas reservoirs with carbon dioxide (CO2) as the heat-carrying medium. Taking the high-temperature gas reservoir of the Huangliu Formation in the Yingqiong Basin as the research object, we construct an ideal thermal and storage coupling model of a CO2 plume geothermal system using COMSOL6.2 software to conduct a sensitivity analysis of geological parameters in the operation of a CO2 plume geothermal system. The simulation results show that, compared with medium- and low-temperature reservoirs, a high-temperature reservoir exhibits higher fluid temperature in the production well and a higher heat extraction rate owing to a higher initial reservoir temperature but has a shorter system operational lifetime; the influence of the thermal conductivity of a thermal reservoir on the CO2 plume geothermal system is relatively minor, being basically negligible; and the thinner the thermal reservoir is, the faster the fluid temperature in the production well decreases and the shorter the thermal breakthrough time. These findings form a basis for selecting heat extraction areas for CO2 plume geothermal systems and also provide a theoretical reference for future practical CO2 plume geothermal system projects.

Использование комплексной дифференциации и кластеризации геолого-промысловой информации при прогнозировании продуктивности залежей Южно-Татарского свода

The problem of reliable calculation and reasonable interpretation of various productivity coefficient forecasting models is complicated by the presence of hidden patterns between geological and field parameters. The object of the study was the carbonate reservoirs of the deposits of the South Tatar arch, the data on which were obtained as a result of generalization and integration of the results of operating more than 700 wells for various purposes. Twenty geological and physical parameters were identified for the study, using which a discriminant analysis was successfully carried out. Multidimensional regression modeling was carried out for three selected groups of homogeneous objects. The simulation results have shown the efficiency of complex differentiation and clustering of geological and field information, which is based on the hierarchical structuring of parameters, which makes it possible, even with a minimum amount of data at a relevant level, to successfully identify the main trends in the influence of model parameters on the productivity coefficient, expanding the scope of their application to solve a range of basic and indirect problems of rational development of oil fields.

Investigation into the geological radiation levels and evaluation of hazard parameters in soil and rock specimens taken from mining sites across North-Eastern Nigeria

This research quantitatively evaluates the natural radioactivity levels and geological radiation hazard parameters of soil and rock specimens obtained from mining locations in North-Eastern Nigeria, by means of grammar-ray spectroscopy. There have been potential public health risks associated with the use of soil and rock from mining locations in North-Eastern Nigeria, specifically the study areas. A total of twenty-eight samples were systematically gathered from Nahuta and Kashere locations. Through gamma spectrometry employing a NaI (TI) detector, the natural radioactivity levels of 238U, 232Th and 40 K were determined for each and every sample. The findings indicated that the mean activity concentrations of 226Ra, 232Th, and 40 K in Nahuta are 46.13 ± 4.78 Bq/Kg, 34.10 ± 3.02 Bq/Kg and 473.94 ± 5.41 Bq/Kg for the soil samples respectively, and 32.91 ± 0.49 Bq/Kg, 40.70 ± 0.41 Bq/Kg, and 578.18 ± 4.28 Bq/Kg for the rock samples respectively. The corresponding mean activity concentrations of 226Ra, 232Th, and 40 K in kashere are 17.99 ± 4.18 Bq/Kg, 23.73 ± 1.78 Bq/Kg, and 191.65 ± 3.15 Bq/Kg, for the soil samples, and 20.24 ± 3.72 Bq/Kg, 29.09 ± 1.78 Bq/Kg, and 148.36 ± 3.15 Bq/Kg, for the rock samples respectively. An analysis of radiation risk parameters (D, AEDE, Raeq, Hex, Hin, AGDE and ELCR) has been conducted and findings explored. While the samples from the kashere region fall within the international recommended levels, elevated readings of certain radiation health parameters are observed in the Nahuta region, posing serious public health risk due to utilization of the soil and rock from this area in construction activities.

Determining the minimum risk zones and reduction of geological risks in the application of enhanced oil recovery methods

For effective results in the application of both traditional and innovative Enhanced Oil Recovery (EOR) methods, a comprehensive analysis of geological and mining data is essential. Insufficient data or uneven distribution across the oil field often introduces significant challenges and uncertainties in selecting the most suitable EOR techniques and delineating their optimal application areas. These complexities necessitate a systematic approach to manage geological risks and enhance the effectiveness of EOR strategies. To address these challenges, a novel methodology has been developed to identify, assess, and mitigate geological risks associated with the implementation of EOR techniques. This approach encompasses the identification of geological parameters that influence EOR performance, distinguishing both positive and negative factors. Moreover, the boundary values for these parameters have been determined, enabling a more precise evaluation of their impact and enhancing the reliability of the results. The spatial distribution of each parameter across the field has been meticulously mapped, allowing for a detailed assessment of risk zones versus minimum-risk zones. These maps were then integrated to highlight the areas most suitable for EOR applications with minimal geological risks. A key advantage of this methodology is its applicability at all stages of field development, ensuring continuous risk assessment and optimization of recovery strategies. By leveraging this comprehensive approach, oil recovery efforts can be significantly enhanced while minimizing associated risks. This not only improves decision-making processes in oil production but also ensures the reliability and efficiency of selected EOR methods, contributing to more sustainable and productive resource exploitation. Keywords: oil reservoir; geological risk; uncertainty; thermal method; minimum-risk zone.

Prediction Model and Knowledge Discovery for Roof Stress in Mined-Out Areas Integrating 3D Scanning Image Features

The accurate prediction of roof stress in mined-out areas is crucial for ensuring mine safety. However, existing study methods often overlook the increasingly available image data and fail to balance the model predictive capability with interpretability. To address these issues, this study innovatively integrates 3D laser scanning image features into the prediction of roof stress in mined-out areas. Image features are extracted using pre-trained deep-learning models and combined with traditional geological parameters to construct multiple machine-learning models for prediction. The experimental results demonstrate that models incorporating image features significantly outperform traditional models that rely solely on geological parameters in terms of prediction accuracy, interpretability, and complexity, revealing the critical role of image features in stress prediction. Furthermore, the use of SHapley Additive exPlanations (SHAP) to interpret the random forest model uncovers new domain knowledge, such as the relationship between spatial patterns and stress concentration. This study theoretically validates the effectiveness of image data and effectively balances the predictive capability and interpretability of the model, facilitating knowledge discovery in the field. On a practical level, it also provides guidance for mine safety management.

Multidisciplinary evaluation of geological, geotechnical, geomechanical, and hydrogeological parameters for assessing slope stability in the Aures Mountain Quarry

The study delves into characterizing the mechanical parameters of the Tahar Louchene aggregate quarry unit in Ain Touta municipality, Batna province, Algeria. This investigation is crucial to address recurring instabilities commonly encountered in open-cast mines. Our approach adopts a comprehensive methodology integrating geotechnical, geomechanical, and numerical analyses, aiming to provide a thorough assessment of fractured rock mass behavior. Our methodology begins with detailed geological surveys aimed at optimal drilling site selection. Geomechanical analysis follows, focusing on fracturing and evaluating rock mass quality, complemented by geotechnical investigations featuring in-situ testing. To gather representative samples, we extracted eighteen cylindrical cores (102 mm × 204 mm) from various benches using a mechanical coring drill. These cores underwent rigorous physical characterization, geochemical analysis, and mechanical testing. Furthermore, 3D FEM numerical modeling was applied to comprehensively assess rock edge stability. The outcomes of our study unveil the presence of four distinct discontinuity sets within the primary formations, with particular emphasis on fault families of geological significance influencing deposit configuration. These fault structures provide valuable insights into stress history and tectonic evolution that directly impact the stability of the quarry. Moreover, our analysis identified various failure types, notably exacerbated by blasting practices that reduce safety factor values, highlighting the critical need for improved safety protocols. Our approach not only contributes to enhancing mining efficiency and productivity but also prioritizes the safety of equipment and personnel in open-cast mining operations across Algeria.

An Improved Decline Curve Analysis Method via Ensemble Learning for Shale Gas Reservoirs

As a clean unconventional energy source, shale gas reservoirs are increasingly important globally. Accurate prediction methods for shale gas production capacity can bring significant economic benefits by reducing construction and operating costs. Decline curve analysis (DCA) is an efficient method that uses mathematical formulas to describe production trends with minimal reliance on geological or engineering parameters. However, traditional DCA models often fail to capture the complex production dynamics of shale gas wells, especially in complex environments. To overcome these limitations, this study proposes an Improved DCA method that integrates multiple base empirical DCA models through ensemble learning. By combining the strengths of individual models, it offers a more robust and accurate prediction framework. We evaluated this method using data from 22 shale gas wells in region L, China, comparing it to six traditional DCA models, including Arps and the Logistic Growth Model (LGM). The results show that the Improved DCA model achieved superior performance—with an mean absolute error (MAE) of 0.0660, an mean squared error (MSE) of 0.0272, and an R2 value of 0.9882—and exhibited greater stability across various samples and conditions. This method provides a reliable tool for long-term production forecasting and optimization without extensive geological or engineering information.

Natural hydrogen exploration within Western European and the eastern Mediterranean ophiolites and ultramafic complexes

This study investigates the potential for natural hydrogen (H 2 ) production across western continental Europe and the eastern Mediterranean, focusing on ophiolitic and ultramafic massifs. Our approach integrates geophysical, geological and geochemical parameters to identify regions where serpentinization could be a key natural process for H 2 generation. Based on these parameters, we have developed a comprehensive probabilistic model to assess the likelihood of abiotic H 2 production at depth. This model incorporates parameters such as geothermal heat flux, magnetic anomalies and the existence of hyperalkaline springs, each weighted according to their possible influence on serpentinization. This weighting is derived from a case study in Albania, where H 2 degassing has been observed. The model has been applied to several ophiolitic and ultramafic complexes, including the Ordenes (Spain), the Alter-do-Chão (Portugal), the Ronda (Spain), the northwestern Alps, the Apennine (Italy), the Dinarides, the Hellenides (e.g. Vourinos and Pindos ophiolites in Greece), Troodos (Cyprus), Kızıldağ, Bassit, Hatay (Turkey) and Leka (Norway). A ranking has been proposed in terms of the probability of finding H 2 at these locations. Subsequently, in order to underscore the potential need for region-specific adaptations of the model, the model was applied to the well-documented Samail Ophiolite in Oman, where H 2 seepages are observed. While the model provides a framework for H 2 -targeted exploration, it also acknowledges its current limitations, emphasizing the necessity for continuous refinement and validation against new observations. The inherent uncertainties in geological processes call for a dynamic modelling strategy to accurately predict and explore geological H 2 resources.

Few-Shot Learning Method for Continuous Prediction of Rock Mechanical Parameters Based on Logging Data.

The stratigraphic sequence displays pronounced variations in lithological and physical characteristics along the vertical axis. The acquisition of vertically continuous variations in stratigraphic rock mechanical parameters is essential for the detailed characterization of stratigraphy, particularly in reservoir layers. Moreover, mechanical parameters are essential for the establishment of a rock mechanical stratigraphic framework. However, the existing research methods cannot obtain the complete stratum rock mechanics parameters by relying solely on a small number of rock samples. In this study, a method for continuously predicting rock mechanic parameters within geological sequences by using geophysical logging data was proposed. The method aims to solve the problems of sample scarcity and global geological feature extraction in the continuous prediction of rock mechanics parameters. This methodology achieves the continuous extraction of stratigraphic features, generation of samples, and prediction of the mechanical parameters. The research result showed that the stratigraphic feature extractor of the logging autoencoder possesses global stratigraphic perception capabilities. Stratigraphic feature extractors can precisely identify and pinpoint key locations where stratigraphic properties change, such as lithological transitions and abnormal parts within thick rock layers. The fake rock mechanical samples produced by the generator exhibit data characteristics identical to those of the genuine samples. The rock mechanics parameter prediction model with the ability to extract stratigraphic features performs significantly better than traditional models when evaluated on real data sets (the mean square errors for the friction angle and cohesion are 17.2 and 12.65, respectively, mean absolute errors are 2.85 and 2.64, respectively, and R2 values are both 0.91) and produces more reasonable calculation results in the actual prediction task of Longtan Formation rock mechanics parameters compared to traditional models. This study provides an extensive applicable methodological framework to address the issues of insufficient samples and continuous prediction of geological parameters in the field of geology.