The information from sparsely logged wellbores is currently under-utilized in reservoir simulation models and their proxies using deep and machine learning (DL/ML).This is particularly problematic for large heterogene...The information from sparsely logged wellbores is currently under-utilized in reservoir simulation models and their proxies using deep and machine learning (DL/ML).This is particularly problematic for large heterogeneous gas/oil reservoirs being considered for repurposing as gas storage reservoirs for CH_(4),CO_(2) or H_(2) and/or enhanced oil recovery technologies.Lack of well-log data leads to inadequate spatial definition of complex models due to the large uncertainties associated with the extrapolation of petrophysical rock types (PRT) calibrated with limited core data across heterogeneous and/or anisotropic reservoirs.Extracting well-log attributes from the few well logs available in many wells and tying PRT predictions based on them to seismic data has the potential to substantially improve the confidence in PRT 3D-mapping across such reservoirs.That process becomes more efficient when coupled with DL/ML models incorporating feature importance and optimized,dual-objective feature selection techniques.展开更多
Tropical forests have large carbon stocks and their conservation is a very important mitigation measure against global warming.However,this carbon pool is the most vulnerable to anthropogenic activities like selective...Tropical forests have large carbon stocks and their conservation is a very important mitigation measure against global warming.However,this carbon pool is the most vulnerable to anthropogenic activities like selective logging and little is known about its recovery.This study aimed to determine the carbon stock recovery after selectively logging using different allometric equations in six 1 ha permanent monitoring plots established in logged and unlogged forest types.Each 1 ha was divided into 25,20×20 m and the DBH of all trees≥2 cm was measured in 2005/2006 and re-measured in 2011/2012.The logged forests had the highest%change in the species richness indicating the impacts of logging.The presence of exploitable commercial trees in both forest types suggests their recruitment after logging.The insignificant difference in the AGB using different allometric equations is an indication that the Pan tropical equation is a good reference for the calculations of AGB in moist tropical forests.The 59.4%recovery rate in forests of 21 YAL indicates that 30 years is not enough for the recovery of the Carbon timber stock as the unlogged forests had a 77.7%.This calls for a review of forest management silvicultural activities for sustainable forest management.展开更多
Karst fractures serve as crucial seepage channels and storage spaces for carbonate natural gas reservoirs,and electrical image logs are vital data for visualizing and characterizing such fractures.However,the conventi...Karst fractures serve as crucial seepage channels and storage spaces for carbonate natural gas reservoirs,and electrical image logs are vital data for visualizing and characterizing such fractures.However,the conventional approach of identifying fractures using electrical image logs predominantly relies on manual processes that are not only time-consuming but also highly subjective.In addition,the heterogeneity and strong dissolution tendency of karst carbonate reservoirs lead to complexity and variety in fracture geometry,which makes it difficult to accurately identify fractures.In this paper,the electrical image logs network(EILnet)da deep-learning-based intelligent semantic segmentation model with a selective attention mechanism and selective feature fusion moduledwas created to enable the intelligent identification and segmentation of different types of fractures through electrical logging images.Data from electrical image logs representing structural and induced fractures were first selected using the sliding window technique before image inpainting and data augmentation were implemented for these images to improve the generalizability of the model.Various image-processing tools,including the bilateral filter,Laplace operator,and Gaussian low-pass filter,were also applied to the electrical logging images to generate a multi-attribute dataset to help the model learn the semantic features of the fractures.The results demonstrated that the EILnet model outperforms mainstream deep-learning semantic segmentation models,such as Fully Convolutional Networks(FCN-8s),U-Net,and SegNet,for both the single-channel dataset and the multi-attribute dataset.The EILnet provided significant advantages for the single-channel dataset,and its mean intersection over union(MIoU)and pixel accuracy(PA)were 81.32%and 89.37%,respectively.In the case of the multi-attribute dataset,the identification capability of all models improved to varying degrees,with the EILnet achieving the highest MIoU and PA of 83.43%and 91.11%,respectively.Further,applying the EILnet model to various blind wells demonstrated its ability to provide reliable fracture identification,thereby indicating its promising potential applications.展开更多
Accurate estimation of mineralogy from geophysical well logs is crucial for characterizing geological formations,particularly in hydrocarbon exploration,CO_(2) sequestration,and geothermal energy development.Current t...Accurate estimation of mineralogy from geophysical well logs is crucial for characterizing geological formations,particularly in hydrocarbon exploration,CO_(2) sequestration,and geothermal energy development.Current techniques,such as multimineral petrophysical analysis,offer details into mineralogical distribution.However,it is inherently time-intensive and demands substantial geological expertise for accurate model evaluation.Furthermore,traditional machine learning techniques often struggle to predict mineralogy accurately and sometimes produce estimations that violate fundamental physical principles.To address this,we present a new approach using Physics-Integrated Neural Networks(PINNs),that combines data-driven learning with domain-specific physical constraints,embedding petrophysical relationships directly into the neural network architecture.This approach enforces that predictions adhere to physical laws.The methodology is applied to the Broom Creek Deep Saline aquifer,a CO_(2) sequestration site in the Williston Basin,to predict the volumes of key mineral constituents—quartz,dolomite,feldspar,anhydrite,illite—along with porosity.Compared to traditional artificial neural networks (ANN),the PINN approach demonstrates higher accuracy and better generalizability,significantly enhancing predictive performance on unseen well datasets.The average mean error across the three blind wells is 0.123 for ANN and 0.042 for PINN,highlighting the superior accuracy of the PINN approach.This method reduces uncertainties in reservoir characterization by improving the reliability of mineralogy and porosity predictions,providing a more robust tool for decision-making in various subsurface geoscience applications.展开更多
We propose an integrated method of data-driven and mechanism models for well logging formation evaluation,explicitly focusing on predicting reservoir parameters,such as porosity and water saturation.Accurately interpr...We propose an integrated method of data-driven and mechanism models for well logging formation evaluation,explicitly focusing on predicting reservoir parameters,such as porosity and water saturation.Accurately interpreting these parameters is crucial for effectively exploring and developing oil and gas.However,with the increasing complexity of geological conditions in this industry,there is a growing demand for improved accuracy in reservoir parameter prediction,leading to higher costs associated with manual interpretation.The conventional logging interpretation methods rely on empirical relationships between logging data and reservoir parameters,which suffer from low interpretation efficiency,intense subjectivity,and suitability for ideal conditions.The application of artificial intelligence in the interpretation of logging data provides a new solution to the problems existing in traditional methods.It is expected to improve the accuracy and efficiency of the interpretation.If large and high-quality datasets exist,data-driven models can reveal relationships of arbitrary complexity.Nevertheless,constructing sufficiently large logging datasets with reliable labels remains challenging,making it difficult to apply data-driven models effectively in logging data interpretation.Furthermore,data-driven models often act as“black boxes”without explaining their predictions or ensuring compliance with primary physical constraints.This paper proposes a machine learning method with strong physical constraints by integrating mechanism and data-driven models.Prior knowledge of logging data interpretation is embedded into machine learning regarding network structure,loss function,and optimization algorithm.We employ the Physically Informed Auto-Encoder(PIAE)to predict porosity and water saturation,which can be trained without labeled reservoir parameters using self-supervised learning techniques.This approach effectively achieves automated interpretation and facilitates generalization across diverse datasets.展开更多
Conventional borehole image log interpretation of linear fractures on volcanic rocks,represented as sinusoids on unwrapped cylinder projections,is relatively straight-forward,however,interpreting non-linear rock struc...Conventional borehole image log interpretation of linear fractures on volcanic rocks,represented as sinusoids on unwrapped cylinder projections,is relatively straight-forward,however,interpreting non-linear rock structures and complex facies geometries can be more challenging.To characterize diverse volcanic paleoenvironments related to the formation of the South American continent,this study presents a new methodology based on image logs,petrography,seismic data,and outcrop analogues.The presented methodology used pseudo-boreholes images generated from outcrop photographs with typical igneous rock features worldwide simulating 2D unwrapped cylinder projections of a 31 cm(12.25 in)diameter well.These synthetic images and standard outcrop photographs were used to define morphological patterns of igneous structures and facies for comparison with wireline borehole image logs from subsurface volcanic and subvolcanic units,providing a“visual scale”for geological evaluation of volcanic facies,significantly enhancing the identification efficiency and reliability of complex geological structures.Our analysis focused on various scales of columnar jointing and pillow lava lobes with additional examples including pahoehoe lava,ignimbrite,hyaloclastite,and various intrusive features in Campos,Santos,and Parnaíba basins in Brazil.This approach increases confidence in the interpretation of subvolcanic,subaerial,and subaqueous deposits.The image log interpretation combined with regional geological knowledge has enabled paleoenvironmental insights into the rift magmatism system related to the breakup of Gondwana with associated implications for hydrocarbon exploration.展开更多
Pharmaceutical pollution is becoming an increasing threat to aquatic environments since inactive compounds do not break down,and the drug products are accumulated in living organisms.The ability of a drug to dissolve ...Pharmaceutical pollution is becoming an increasing threat to aquatic environments since inactive compounds do not break down,and the drug products are accumulated in living organisms.The ability of a drug to dissolve in water(i.e.,LogS)is an important parameter for assessing a drug’s environmental fate,biovailability,and toxicity.LogS is typically measured in a laboratory setting,which can be costly and time-consuming,and does not provide the opportunity to conduct large-scale analyses.This research develops and evaluates machine learning models that can produce LogS estimates and may improve the environmental risk assessments of toxic pharmaceutical pollutants.We used a dataset from the ChEMBL database that contained 8832 molecular compounds.Various data preprocessing and cleaning techniques were applied(i.e.,removing the missing values),we then recorded chemical properties by normalizing and,even,using some feature selection techniques.We evaluated logS with a total of several machine learning and deep learning models,including;linear regression,random forests(RF),support vector machines(SVM),gradient boosting(GBM),and artificial neural networks(ANNs).We assessed model performance using a series of metrics,including root mean square error(RMSE)and mean absolute error(MAE),as well as the coefficient of determination(R^(2)).The findings show that the Least Angle Regression(LAR)model performed the best with an R^(2) value close to 1.0000,confirming high predictive accuracy.The OMP model performed well with good accuracy(R^(2)=0.8727)while remaining computationally cheap,while other models(e.g.,neural networks,random forests)performed well but were too computationally expensive.Finally,to assess the robustness of the results,an error analysis indicated that residuals were evenly distributed around zero,confirming the results from the LAR model.The current research illustrates the potential of AI in anticipating drug solubility,providing support for green pharmaceutical design and environmental risk assessment.Future work should extend predictions to include degradation and toxicity to enhance predictive power and applicability.展开更多
Commercially managed forests are often poor in terms of biodiversity.Saproxylic beetle species could be a useful bioindicating group for the conservation of forest stands.In recent decades,oak stands have been affecte...Commercially managed forests are often poor in terms of biodiversity.Saproxylic beetle species could be a useful bioindicating group for the conservation of forest stands.In recent decades,oak stands have been affected by a wide range of factors that have intensified stand decline.Saproxylic beetle richness was investigated in declining oak stands that have been consequently targeted for clearcutting due to concerns about insect pest outbreaks.The research was conducted at six managed oak forests,where we compared beetle occurrences in declining stands and in healthy stands that did not show any symptoms of decline.Beetles were collected using window traps placed on the basal and mid-trunk sections of trees.A total of 2925 adults belonging to 239 saproxylic beetle species were captured,of which 56 species are on the IUCN Red List.The results show that declining stands were richer in saproxylic species,and that the diversity of beetle species was greater in these stands.Approximately 1.4 times more species were caught within declining stands than in healthy ones(1.6 times for Red List species).Declining stands hosted more pest species(e.g.,cambiophagous and xylophagous species).However,only low numbers of these species were recorded in these stands.In summary,results of this study suggest that decline of managed oak stands is creating a wide spectrum of habitats for many saproxylic species.Thus,salvage logging of declining oak trees can represent a natural trap and reduce local beetle biodiversity,mainly for saproxylic,endangered or low-mobility species that would be attracted by new suitable habitats.展开更多
This study explores the application of machine learning techniques for predicting permeability,porosity,and flow zone indicator(FZI)in carbonate reservoirs using well log data,aiming to overcome the limitations of tra...This study explores the application of machine learning techniques for predicting permeability,porosity,and flow zone indicator(FZI)in carbonate reservoirs using well log data,aiming to overcome the limitations of traditional empirical methods.Six machine learning algorithms are utilized:support vector machine(SVM),backpropagation(BP)neural network,gaussian process regression(GPR),extreme gradient boosting(XGBoost),K-nearest neighbor(KNN),and random forest(RF).The methodology involves classifying pore-permeability types based on the flow index,leveraging logging curves and geological data.Models are trained using seven logging parameters—spectral gamma rays(SGR),uranium-free gamma rays(CGR),photoelectric absorption cross-section index(PE),lithologic density(RHOB),acoustic transit time(DT),neutron porosity(NPHI),and formation true resistivity(RT)—along with corresponding physical property labels.Machine learning models are trained and evaluated to predict carbonate rock properties.The results demonstrate that GPR achieves the highest accuracy in porosity prediction,with a coefficient of determination(R~2)value of 0.7342,while RF proves to be the most accurate for permeability prediction.Despite these improvements,accurately predicting lowpermeability zones in heterogeneous carbonate rocks remains a significant challenge.Application of cross-validation techniques optimized the performance of GPR,resulting in an accuracy index(ACI)value of 0.9699 for porosity prediction.This study provides a novel framework that leverages machine learning techniques to improve the characterization of carbonate reservoirs.展开更多
As computer data grows exponentially,detecting anomalies within system logs has become increasingly important.Current research on log anomaly detection largely depends on log templates derived from log parsing.Word em...As computer data grows exponentially,detecting anomalies within system logs has become increasingly important.Current research on log anomaly detection largely depends on log templates derived from log parsing.Word embedding is utilized to extract information from these templates.However,this method neglects a portion of the content within the logs and confronts the challenge of data imbalance among various log template types after parsing.Currently,specialized research on data imbalance across log template categories remains scarce.A dual-attention-based log anomaly detection model(LogDA),which leveraged data imbalance,was proposed to address these issues in the work.The LogDA model initially utilized a pre-trained model to extract semantic embedding from log templates.Besides,the similarity between embedding was calculated to discern the relationships among the various templates.Then,a Transformer model with a dual-attention mechanism was constructed to capture positional information and global dependencies.Compared to multiple baseline experiments across three public datasets,the proposed approach could improve precision,recall,and F1 scores.展开更多
A cased well model consists of a coaxial tank and casing,which houses coaxially installed transmitting and receiving coils.The transmitting coil is excited by the current produced by the transmitting circuit,and trans...A cased well model consists of a coaxial tank and casing,which houses coaxially installed transmitting and receiving coils.The transmitting coil is excited by the current produced by the transmitting circuit,and transient electromagnetic responses occur in the casing,including direct coupling and casing responses.As the range between the transmitting and receiving coils increases,direct coupling responses decay rapidly,are less than the casing response at 0.3 m,and disappear at 0.7 m.By contrast,a casing response increases rapidly and then declines slowly after reaching a peak and changes little within a specifi c range.The peak decreases slowly with range.The continuous addition of water to the tank causes slight changes in transient electromagnetic responses,so the diff erence which are subtracted from the response without water is used.Moreover,the diff erences at the time of rapid increase in response and the time of rapid decrease in response are large,forming a peak and a trough.Given that the conductivity of water in a full tank changes after the addition of salt,the diff erence in the peak is linear with the increase in the conductivity of water.This result provides an experimental basis for the design of a transient electromagnetic logging instrument that measures the conductivity of formation in cased well.展开更多
Coaly source rocks have attracted considerable attention for their significant hydrocarbon generation potential in recent years. However, limited study is performed on utilizing geochemical data and well log data to e...Coaly source rocks have attracted considerable attention for their significant hydrocarbon generation potential in recent years. However, limited study is performed on utilizing geochemical data and well log data to evaluate coaly hydrocarbon source rocks. In this study, geochemical data and well log data are selected from two key wells to conduct an evaluation of coaly hydrocarbon source rocks of Jurassic Kezilenuer Formation in Kuqa Depression of Tarim Basin. Initially, analysis was focused on geochemical parameters to assess organic matter type, source rock quality, and hydrocarbon generation potential.Lithology types of source rocks include mudstone, carbonaceous mudstone and coal. The predominant organic matter type identified was Type Ⅲ and Type Ⅱ_(2), indicating a favorable hydrocarbon generation potential. Well log data are integrated to predict total organic carbon(TOC) content, and the results indicate that multiple regression method is effective in predicting TOC of carbonaceous mudstone and coal. However, the ΔlgR method exhibited limited predictive capability for mudstone source rock.Additionally, machine learning methods including multilayer perceptron neural network(MLP), random forest(RF), and extreme gradient boosting(XGBoost) techniques are employed to predict TOC of mudstone source rock. The XGBoost performs best in TOC prediction with correlation coefficient(R2) of 0.9517, indicating a close agreement between measured and predicted TOC values. This study provides a reliable prediction method of coaly hydrocarbon source rocks through machine learning methods, and will provide guidance for resource assessment.展开更多
Electromagnetic technology used in logging while drilling(LWD) provides the resistivity distribution around a borehole within a range of several tens of meters.However,a blind zone appears in front of the drill bit wh...Electromagnetic technology used in logging while drilling(LWD) provides the resistivity distribution around a borehole within a range of several tens of meters.However,a blind zone appears in front of the drill bit when operating in high-angle wells,limiting the ability to detect formations ahead of the drill bit.Look-ahead technology addresses this issue and substantially enhances the proactive capability of geological directional drilling.In this study,we examine the detection capabilities of various component combinations of magnetic dipole antenna.Based on the sensitivity of each component to the axial information,a coaxial component is selected as a boundary indicator.We investigate the impact of various factors,such as frequency and transmitter and receiver(TR) distance,under different geological models.This study proposes 5 and 20 kHz as appropriate frequencies,and 10-14 and 12-17 m as suitable TR distance combinations.The accuracy of the numerical calculation results is verified via air-sea testing,confirming the instrument's detection capability.A test model that eliminated the influence of environmental factors and seawater depth is developed.The results have demonstrated that the tool can recognize the interface between layers up to 21.6 m ahead.It provides a validation idea for the design of new instruments as well as the validation of detection capabilities.展开更多
Machine learning algorithms are widely used to interpret well logging data.To enhance the algorithms'robustness,shuffling the well logging data is an unavoidable feature engineering before training models.However,...Machine learning algorithms are widely used to interpret well logging data.To enhance the algorithms'robustness,shuffling the well logging data is an unavoidable feature engineering before training models.However,latent information stored between different well logging types and depth is destroyed during the shuffle.To investigate the influence of latent information,this study implements graph convolution networks(GCNs),long-short temporal memory models,recurrent neural networks,temporal convolution networks,and two artificial neural networks to predict the microbial lithology in the fourth member of the Dengying Formation,Moxi gas field,central Sichuan Basin.Results indicate that the GCN model outperforms other models.The accuracy,F1-score,and area under curve of the GCN model are 0.90,0.90,and 0.95,respectively.Experimental results indicate that the time-series data facilitates lithology prediction and helps determine lithological fluctuations in the vertical direction.All types of logs from the spectral in the GCN model and also facilitates lithology identification.Only on condition combined with latent information,the GCN model reaches excellent microbialite classification resolution at the centimeter scale.Ultimately,the two actual cases show tricks for using GCN models to predict potential microbialite in other formations and areas,proving that the GCN model can be adopted in the industry.展开更多
Well logging technology has accumulated a large amount of historical data through four generations of technological development,which forms the basis of well logging big data and digital assets.However,the value of th...Well logging technology has accumulated a large amount of historical data through four generations of technological development,which forms the basis of well logging big data and digital assets.However,the value of these data has not been well stored,managed and mined.With the development of cloud computing technology,it provides a rare development opportunity for logging big data private cloud.The traditional petrophysical evaluation and interpretation model has encountered great challenges in the face of new evaluation objects.The solution research of logging big data distributed storage,processing and learning functions integrated in logging big data private cloud has not been carried out yet.To establish a distributed logging big-data private cloud platform centered on a unifi ed learning model,which achieves the distributed storage and processing of logging big data and facilitates the learning of novel knowledge patterns via the unifi ed logging learning model integrating physical simulation and data models in a large-scale functional space,thus resolving the geo-engineering evaluation problem of geothermal fi elds.Based on the research idea of“logging big data cloud platform-unifi ed logging learning model-large function space-knowledge learning&discovery-application”,the theoretical foundation of unified learning model,cloud platform architecture,data storage and learning algorithm,arithmetic power allocation and platform monitoring,platform stability,data security,etc.have been carried on analysis.The designed logging big data cloud platform realizes parallel distributed storage and processing of data and learning algorithms.The feasibility of constructing a well logging big data cloud platform based on a unifi ed learning model of physics and data is analyzed in terms of the structure,ecology,management and security of the cloud platform.The case study shows that the logging big data cloud platform has obvious technical advantages over traditional logging evaluation methods in terms of knowledge discovery method,data software and results sharing,accuracy,speed and complexity.展开更多
Theβ-decay properties of^(67-80)As nuclei have been investigated within the framework of the proton-neutron quasi-particle random phase approximation(pn-QRPA)model.The nuclear deformation obtained from the finite ran...Theβ-decay properties of^(67-80)As nuclei have been investigated within the framework of the proton-neutron quasi-particle random phase approximation(pn-QRPA)model.The nuclear deformation obtained from the finite range droplet model is used as an input parameter in the pn-QRPA model for the analysis ofβ-decay properties including Gamow-Teller strength distributions,log ft,β-decay half-lives and stellarβ^(±)decay rates.The predicted log ft values were fairly consistent with the observed data.The computedβ-decay half-lives matched the measured values by a factor of 10.The stellar rates were compared with the shell model outcomes.At high densities and temperatures,theβ^(+)and electron capture rates had a finite contribution.However,theβ^(-)and positron capture rates are only significant at high temperatures and low densities.The pn-QRPA rates outperformed the shell model rates by a factor of 22 or more.展开更多
文摘The information from sparsely logged wellbores is currently under-utilized in reservoir simulation models and their proxies using deep and machine learning (DL/ML).This is particularly problematic for large heterogeneous gas/oil reservoirs being considered for repurposing as gas storage reservoirs for CH_(4),CO_(2) or H_(2) and/or enhanced oil recovery technologies.Lack of well-log data leads to inadequate spatial definition of complex models due to the large uncertainties associated with the extrapolation of petrophysical rock types (PRT) calibrated with limited core data across heterogeneous and/or anisotropic reservoirs.Extracting well-log attributes from the few well logs available in many wells and tying PRT predictions based on them to seismic data has the potential to substantially improve the confidence in PRT 3D-mapping across such reservoirs.That process becomes more efficient when coupled with DL/ML models incorporating feature importance and optimized,dual-objective feature selection techniques.
基金supported by the International Tropical Timber Organisation(ITTO)grantthe equipment grant was provided by IDEA WILD+2 种基金the Carnegie Corporation of New York through the Future Africa Research Leadership(FAR-LeaF)grant of the University of Pretoriasupported the fieldwork and data analyses,the mobility grant and research modernization allowance of the Ministry of Higher Education(MINESUP)Cameroonthe Fako America Scholarship.
文摘Tropical forests have large carbon stocks and their conservation is a very important mitigation measure against global warming.However,this carbon pool is the most vulnerable to anthropogenic activities like selective logging and little is known about its recovery.This study aimed to determine the carbon stock recovery after selectively logging using different allometric equations in six 1 ha permanent monitoring plots established in logged and unlogged forest types.Each 1 ha was divided into 25,20×20 m and the DBH of all trees≥2 cm was measured in 2005/2006 and re-measured in 2011/2012.The logged forests had the highest%change in the species richness indicating the impacts of logging.The presence of exploitable commercial trees in both forest types suggests their recruitment after logging.The insignificant difference in the AGB using different allometric equations is an indication that the Pan tropical equation is a good reference for the calculations of AGB in moist tropical forests.The 59.4%recovery rate in forests of 21 YAL indicates that 30 years is not enough for the recovery of the Carbon timber stock as the unlogged forests had a 77.7%.This calls for a review of forest management silvicultural activities for sustainable forest management.
基金the National Natural Science Foundation of China(42472194,42302153,and 42002144)the Fundamental Research Funds for the Central Univer-sities(22CX06002A).
文摘Karst fractures serve as crucial seepage channels and storage spaces for carbonate natural gas reservoirs,and electrical image logs are vital data for visualizing and characterizing such fractures.However,the conventional approach of identifying fractures using electrical image logs predominantly relies on manual processes that are not only time-consuming but also highly subjective.In addition,the heterogeneity and strong dissolution tendency of karst carbonate reservoirs lead to complexity and variety in fracture geometry,which makes it difficult to accurately identify fractures.In this paper,the electrical image logs network(EILnet)da deep-learning-based intelligent semantic segmentation model with a selective attention mechanism and selective feature fusion moduledwas created to enable the intelligent identification and segmentation of different types of fractures through electrical logging images.Data from electrical image logs representing structural and induced fractures were first selected using the sliding window technique before image inpainting and data augmentation were implemented for these images to improve the generalizability of the model.Various image-processing tools,including the bilateral filter,Laplace operator,and Gaussian low-pass filter,were also applied to the electrical logging images to generate a multi-attribute dataset to help the model learn the semantic features of the fractures.The results demonstrated that the EILnet model outperforms mainstream deep-learning semantic segmentation models,such as Fully Convolutional Networks(FCN-8s),U-Net,and SegNet,for both the single-channel dataset and the multi-attribute dataset.The EILnet provided significant advantages for the single-channel dataset,and its mean intersection over union(MIoU)and pixel accuracy(PA)were 81.32%and 89.37%,respectively.In the case of the multi-attribute dataset,the identification capability of all models improved to varying degrees,with the EILnet achieving the highest MIoU and PA of 83.43%and 91.11%,respectively.Further,applying the EILnet model to various blind wells demonstrated its ability to provide reliable fracture identification,thereby indicating its promising potential applications.
基金the North Dakota Industrial Commission (NDIC) for their financial supportprovided by the University of North Dakota Computational Research Center。
文摘Accurate estimation of mineralogy from geophysical well logs is crucial for characterizing geological formations,particularly in hydrocarbon exploration,CO_(2) sequestration,and geothermal energy development.Current techniques,such as multimineral petrophysical analysis,offer details into mineralogical distribution.However,it is inherently time-intensive and demands substantial geological expertise for accurate model evaluation.Furthermore,traditional machine learning techniques often struggle to predict mineralogy accurately and sometimes produce estimations that violate fundamental physical principles.To address this,we present a new approach using Physics-Integrated Neural Networks(PINNs),that combines data-driven learning with domain-specific physical constraints,embedding petrophysical relationships directly into the neural network architecture.This approach enforces that predictions adhere to physical laws.The methodology is applied to the Broom Creek Deep Saline aquifer,a CO_(2) sequestration site in the Williston Basin,to predict the volumes of key mineral constituents—quartz,dolomite,feldspar,anhydrite,illite—along with porosity.Compared to traditional artificial neural networks (ANN),the PINN approach demonstrates higher accuracy and better generalizability,significantly enhancing predictive performance on unseen well datasets.The average mean error across the three blind wells is 0.123 for ANN and 0.042 for PINN,highlighting the superior accuracy of the PINN approach.This method reduces uncertainties in reservoir characterization by improving the reliability of mineralogy and porosity predictions,providing a more robust tool for decision-making in various subsurface geoscience applications.
基金supported by National Key Research and Development Program (2019YFA0708301)National Natural Science Foundation of China (51974337)+2 种基金the Strategic Cooperation Projects of CNPC and CUPB (ZLZX2020-03)Science and Technology Innovation Fund of CNPC (2021DQ02-0403)Open Fund of Petroleum Exploration and Development Research Institute of CNPC (2022-KFKT-09)
文摘We propose an integrated method of data-driven and mechanism models for well logging formation evaluation,explicitly focusing on predicting reservoir parameters,such as porosity and water saturation.Accurately interpreting these parameters is crucial for effectively exploring and developing oil and gas.However,with the increasing complexity of geological conditions in this industry,there is a growing demand for improved accuracy in reservoir parameter prediction,leading to higher costs associated with manual interpretation.The conventional logging interpretation methods rely on empirical relationships between logging data and reservoir parameters,which suffer from low interpretation efficiency,intense subjectivity,and suitability for ideal conditions.The application of artificial intelligence in the interpretation of logging data provides a new solution to the problems existing in traditional methods.It is expected to improve the accuracy and efficiency of the interpretation.If large and high-quality datasets exist,data-driven models can reveal relationships of arbitrary complexity.Nevertheless,constructing sufficiently large logging datasets with reliable labels remains challenging,making it difficult to apply data-driven models effectively in logging data interpretation.Furthermore,data-driven models often act as“black boxes”without explaining their predictions or ensuring compliance with primary physical constraints.This paper proposes a machine learning method with strong physical constraints by integrating mechanism and data-driven models.Prior knowledge of logging data interpretation is embedded into machine learning regarding network structure,loss function,and optimization algorithm.We employ the Physically Informed Auto-Encoder(PIAE)to predict porosity and water saturation,which can be trained without labeled reservoir parameters using self-supervised learning techniques.This approach effectively achieves automated interpretation and facilitates generalization across diverse datasets.
文摘Conventional borehole image log interpretation of linear fractures on volcanic rocks,represented as sinusoids on unwrapped cylinder projections,is relatively straight-forward,however,interpreting non-linear rock structures and complex facies geometries can be more challenging.To characterize diverse volcanic paleoenvironments related to the formation of the South American continent,this study presents a new methodology based on image logs,petrography,seismic data,and outcrop analogues.The presented methodology used pseudo-boreholes images generated from outcrop photographs with typical igneous rock features worldwide simulating 2D unwrapped cylinder projections of a 31 cm(12.25 in)diameter well.These synthetic images and standard outcrop photographs were used to define morphological patterns of igneous structures and facies for comparison with wireline borehole image logs from subsurface volcanic and subvolcanic units,providing a“visual scale”for geological evaluation of volcanic facies,significantly enhancing the identification efficiency and reliability of complex geological structures.Our analysis focused on various scales of columnar jointing and pillow lava lobes with additional examples including pahoehoe lava,ignimbrite,hyaloclastite,and various intrusive features in Campos,Santos,and Parnaíba basins in Brazil.This approach increases confidence in the interpretation of subvolcanic,subaerial,and subaqueous deposits.The image log interpretation combined with regional geological knowledge has enabled paleoenvironmental insights into the rift magmatism system related to the breakup of Gondwana with associated implications for hydrocarbon exploration.
文摘Pharmaceutical pollution is becoming an increasing threat to aquatic environments since inactive compounds do not break down,and the drug products are accumulated in living organisms.The ability of a drug to dissolve in water(i.e.,LogS)is an important parameter for assessing a drug’s environmental fate,biovailability,and toxicity.LogS is typically measured in a laboratory setting,which can be costly and time-consuming,and does not provide the opportunity to conduct large-scale analyses.This research develops and evaluates machine learning models that can produce LogS estimates and may improve the environmental risk assessments of toxic pharmaceutical pollutants.We used a dataset from the ChEMBL database that contained 8832 molecular compounds.Various data preprocessing and cleaning techniques were applied(i.e.,removing the missing values),we then recorded chemical properties by normalizing and,even,using some feature selection techniques.We evaluated logS with a total of several machine learning and deep learning models,including;linear regression,random forests(RF),support vector machines(SVM),gradient boosting(GBM),and artificial neural networks(ANNs).We assessed model performance using a series of metrics,including root mean square error(RMSE)and mean absolute error(MAE),as well as the coefficient of determination(R^(2)).The findings show that the Least Angle Regression(LAR)model performed the best with an R^(2) value close to 1.0000,confirming high predictive accuracy.The OMP model performed well with good accuracy(R^(2)=0.8727)while remaining computationally cheap,while other models(e.g.,neural networks,random forests)performed well but were too computationally expensive.Finally,to assess the robustness of the results,an error analysis indicated that residuals were evenly distributed around zero,confirming the results from the LAR model.The current research illustrates the potential of AI in anticipating drug solubility,providing support for green pharmaceutical design and environmental risk assessment.Future work should extend predictions to include degradation and toxicity to enhance predictive power and applicability.
基金supported by grant No.QL24020204funded by the Ministry of Agriculture of the Czech Republic and Internal Grant Agency of Faculty of Forestry and Wood Science CZU(reg.no.A_01_22)"EVA 4.0"No.CZ.02.1.01/0.0/0.0/16_019/0000803 financed by OP RDE.
文摘Commercially managed forests are often poor in terms of biodiversity.Saproxylic beetle species could be a useful bioindicating group for the conservation of forest stands.In recent decades,oak stands have been affected by a wide range of factors that have intensified stand decline.Saproxylic beetle richness was investigated in declining oak stands that have been consequently targeted for clearcutting due to concerns about insect pest outbreaks.The research was conducted at six managed oak forests,where we compared beetle occurrences in declining stands and in healthy stands that did not show any symptoms of decline.Beetles were collected using window traps placed on the basal and mid-trunk sections of trees.A total of 2925 adults belonging to 239 saproxylic beetle species were captured,of which 56 species are on the IUCN Red List.The results show that declining stands were richer in saproxylic species,and that the diversity of beetle species was greater in these stands.Approximately 1.4 times more species were caught within declining stands than in healthy ones(1.6 times for Red List species).Declining stands hosted more pest species(e.g.,cambiophagous and xylophagous species).However,only low numbers of these species were recorded in these stands.In summary,results of this study suggest that decline of managed oak stands is creating a wide spectrum of habitats for many saproxylic species.Thus,salvage logging of declining oak trees can represent a natural trap and reduce local beetle biodiversity,mainly for saproxylic,endangered or low-mobility species that would be attracted by new suitable habitats.
基金funded by Fundamental Research Funds for the Central Universities(No.00007851)。
文摘This study explores the application of machine learning techniques for predicting permeability,porosity,and flow zone indicator(FZI)in carbonate reservoirs using well log data,aiming to overcome the limitations of traditional empirical methods.Six machine learning algorithms are utilized:support vector machine(SVM),backpropagation(BP)neural network,gaussian process regression(GPR),extreme gradient boosting(XGBoost),K-nearest neighbor(KNN),and random forest(RF).The methodology involves classifying pore-permeability types based on the flow index,leveraging logging curves and geological data.Models are trained using seven logging parameters—spectral gamma rays(SGR),uranium-free gamma rays(CGR),photoelectric absorption cross-section index(PE),lithologic density(RHOB),acoustic transit time(DT),neutron porosity(NPHI),and formation true resistivity(RT)—along with corresponding physical property labels.Machine learning models are trained and evaluated to predict carbonate rock properties.The results demonstrate that GPR achieves the highest accuracy in porosity prediction,with a coefficient of determination(R~2)value of 0.7342,while RF proves to be the most accurate for permeability prediction.Despite these improvements,accurately predicting lowpermeability zones in heterogeneous carbonate rocks remains a significant challenge.Application of cross-validation techniques optimized the performance of GPR,resulting in an accuracy index(ACI)value of 0.9699 for porosity prediction.This study provides a novel framework that leverages machine learning techniques to improve the characterization of carbonate reservoirs.
基金funded by the Hainan Provincial Natural Science Foundation Project(Grant No.622RC675)the National Natural Science Foundation of China(Grant No.62262019).
文摘As computer data grows exponentially,detecting anomalies within system logs has become increasingly important.Current research on log anomaly detection largely depends on log templates derived from log parsing.Word embedding is utilized to extract information from these templates.However,this method neglects a portion of the content within the logs and confronts the challenge of data imbalance among various log template types after parsing.Currently,specialized research on data imbalance across log template categories remains scarce.A dual-attention-based log anomaly detection model(LogDA),which leveraged data imbalance,was proposed to address these issues in the work.The LogDA model initially utilized a pre-trained model to extract semantic embedding from log templates.Besides,the similarity between embedding was calculated to discern the relationships among the various templates.Then,a Transformer model with a dual-attention mechanism was constructed to capture positional information and global dependencies.Compared to multiple baseline experiments across three public datasets,the proposed approach could improve precision,recall,and F1 scores.
基金supported by the National Natural Science Foundation of China (grant nos. 42074137)。
文摘A cased well model consists of a coaxial tank and casing,which houses coaxially installed transmitting and receiving coils.The transmitting coil is excited by the current produced by the transmitting circuit,and transient electromagnetic responses occur in the casing,including direct coupling and casing responses.As the range between the transmitting and receiving coils increases,direct coupling responses decay rapidly,are less than the casing response at 0.3 m,and disappear at 0.7 m.By contrast,a casing response increases rapidly and then declines slowly after reaching a peak and changes little within a specifi c range.The peak decreases slowly with range.The continuous addition of water to the tank causes slight changes in transient electromagnetic responses,so the diff erence which are subtracted from the response without water is used.Moreover,the diff erences at the time of rapid increase in response and the time of rapid decrease in response are large,forming a peak and a trough.Given that the conductivity of water in a full tank changes after the addition of salt,the diff erence in the peak is linear with the increase in the conductivity of water.This result provides an experimental basis for the design of a transient electromagnetic logging instrument that measures the conductivity of formation in cased well.
基金supported by Science Foundation of China University of Petroleum(Beijing)(No.2462023QNXZ010).
文摘Coaly source rocks have attracted considerable attention for their significant hydrocarbon generation potential in recent years. However, limited study is performed on utilizing geochemical data and well log data to evaluate coaly hydrocarbon source rocks. In this study, geochemical data and well log data are selected from two key wells to conduct an evaluation of coaly hydrocarbon source rocks of Jurassic Kezilenuer Formation in Kuqa Depression of Tarim Basin. Initially, analysis was focused on geochemical parameters to assess organic matter type, source rock quality, and hydrocarbon generation potential.Lithology types of source rocks include mudstone, carbonaceous mudstone and coal. The predominant organic matter type identified was Type Ⅲ and Type Ⅱ_(2), indicating a favorable hydrocarbon generation potential. Well log data are integrated to predict total organic carbon(TOC) content, and the results indicate that multiple regression method is effective in predicting TOC of carbonaceous mudstone and coal. However, the ΔlgR method exhibited limited predictive capability for mudstone source rock.Additionally, machine learning methods including multilayer perceptron neural network(MLP), random forest(RF), and extreme gradient boosting(XGBoost) techniques are employed to predict TOC of mudstone source rock. The XGBoost performs best in TOC prediction with correlation coefficient(R2) of 0.9517, indicating a close agreement between measured and predicted TOC values. This study provides a reliable prediction method of coaly hydrocarbon source rocks through machine learning methods, and will provide guidance for resource assessment.
基金co-funded by the National Key Research and Development Program of China under Grant (2019YFA0708301)the CAS Project for Young Scientists in Basic Research (Grant No.YSBR-082)Research Instrument and Equipment Development Project of Chinese Academy of Sciences (GJJSTD20210008)。
文摘Electromagnetic technology used in logging while drilling(LWD) provides the resistivity distribution around a borehole within a range of several tens of meters.However,a blind zone appears in front of the drill bit when operating in high-angle wells,limiting the ability to detect formations ahead of the drill bit.Look-ahead technology addresses this issue and substantially enhances the proactive capability of geological directional drilling.In this study,we examine the detection capabilities of various component combinations of magnetic dipole antenna.Based on the sensitivity of each component to the axial information,a coaxial component is selected as a boundary indicator.We investigate the impact of various factors,such as frequency and transmitter and receiver(TR) distance,under different geological models.This study proposes 5 and 20 kHz as appropriate frequencies,and 10-14 and 12-17 m as suitable TR distance combinations.The accuracy of the numerical calculation results is verified via air-sea testing,confirming the instrument's detection capability.A test model that eliminated the influence of environmental factors and seawater depth is developed.The results have demonstrated that the tool can recognize the interface between layers up to 21.6 m ahead.It provides a validation idea for the design of new instruments as well as the validation of detection capabilities.
基金supported by National Natural Science Foundation of China(Nos.41872150,U2344209 and U19B6003)the PetroChina Southwest Oil and Gasfield Company(No.2020-54365)。
文摘Machine learning algorithms are widely used to interpret well logging data.To enhance the algorithms'robustness,shuffling the well logging data is an unavoidable feature engineering before training models.However,latent information stored between different well logging types and depth is destroyed during the shuffle.To investigate the influence of latent information,this study implements graph convolution networks(GCNs),long-short temporal memory models,recurrent neural networks,temporal convolution networks,and two artificial neural networks to predict the microbial lithology in the fourth member of the Dengying Formation,Moxi gas field,central Sichuan Basin.Results indicate that the GCN model outperforms other models.The accuracy,F1-score,and area under curve of the GCN model are 0.90,0.90,and 0.95,respectively.Experimental results indicate that the time-series data facilitates lithology prediction and helps determine lithological fluctuations in the vertical direction.All types of logs from the spectral in the GCN model and also facilitates lithology identification.Only on condition combined with latent information,the GCN model reaches excellent microbialite classification resolution at the centimeter scale.Ultimately,the two actual cases show tricks for using GCN models to predict potential microbialite in other formations and areas,proving that the GCN model can be adopted in the industry.
基金supported By Grant (PLN2022-14) of State Key Laboratory of Oil and Gas Reservoir Geology and Exploitation (Southwest Petroleum University)。
文摘Well logging technology has accumulated a large amount of historical data through four generations of technological development,which forms the basis of well logging big data and digital assets.However,the value of these data has not been well stored,managed and mined.With the development of cloud computing technology,it provides a rare development opportunity for logging big data private cloud.The traditional petrophysical evaluation and interpretation model has encountered great challenges in the face of new evaluation objects.The solution research of logging big data distributed storage,processing and learning functions integrated in logging big data private cloud has not been carried out yet.To establish a distributed logging big-data private cloud platform centered on a unifi ed learning model,which achieves the distributed storage and processing of logging big data and facilitates the learning of novel knowledge patterns via the unifi ed logging learning model integrating physical simulation and data models in a large-scale functional space,thus resolving the geo-engineering evaluation problem of geothermal fi elds.Based on the research idea of“logging big data cloud platform-unifi ed logging learning model-large function space-knowledge learning&discovery-application”,the theoretical foundation of unified learning model,cloud platform architecture,data storage and learning algorithm,arithmetic power allocation and platform monitoring,platform stability,data security,etc.have been carried on analysis.The designed logging big data cloud platform realizes parallel distributed storage and processing of data and learning algorithms.The feasibility of constructing a well logging big data cloud platform based on a unifi ed learning model of physics and data is analyzed in terms of the structure,ecology,management and security of the cloud platform.The case study shows that the logging big data cloud platform has obvious technical advantages over traditional logging evaluation methods in terms of knowledge discovery method,data software and results sharing,accuracy,speed and complexity.
基金funded by Taif University,Saudi Arabia,Project No.(TU-DSPP-2024-33)。
文摘Theβ-decay properties of^(67-80)As nuclei have been investigated within the framework of the proton-neutron quasi-particle random phase approximation(pn-QRPA)model.The nuclear deformation obtained from the finite range droplet model is used as an input parameter in the pn-QRPA model for the analysis ofβ-decay properties including Gamow-Teller strength distributions,log ft,β-decay half-lives and stellarβ^(±)decay rates.The predicted log ft values were fairly consistent with the observed data.The computedβ-decay half-lives matched the measured values by a factor of 10.The stellar rates were compared with the shell model outcomes.At high densities and temperatures,theβ^(+)and electron capture rates had a finite contribution.However,theβ^(-)and positron capture rates are only significant at high temperatures and low densities.The pn-QRPA rates outperformed the shell model rates by a factor of 22 or more.
