Log interpretation of carbonate rocks based on petrophysical facies constraints

The complex pore structure of carbonate reservoirs hinders the correlation between porosity and permeability.In view of the sedimentation,diagenesis,testing,and production characteristics of carbonate reservoirs in the study area,combined with the current trends and advances in well log interpretation techniques for carbonate reservoirs,a log interpretation technology route of“geological information constraint+deep learning”was developed.The principal component analysis(PCA)was employed to establish lithology identification criteria with an accuracy of 91%.The Bayesian stepwise discriminant method was used to construct a sedimentary microfacies identification method with an accuracy of 90.5%.Based on production data,the main lithologies and sedimentary microfacies of effective reservoirs were determined,and 10 petrophysical facies with effective reservoir characteristics were identified.Constrained by petrophysical facies,the mean interpretation error of porosity compared to core analysis results is 2.7%,and the ratio of interpreted permeability to core analysis is within one order of magnitude,averaging 3.6.The research results demonstrate that deep learning algorithms can uncover the correlation in carbonate reservoir well logging data.Integrating geological and production data and selecting appropriate machine learning algorithms can significantly improve the accuracy of well log interpretation for carbonate reservoirs.

Effect of sensor quantity on measurement accuracy of log inner defects by using stress wave

Wood nondestructive testing （NDT） is one of the high efficient methods in utilizing wood. This paper explained the principle of log defect testing by using stress wave, and analyzed the effects of sensor quantity on defect testing results by using stress wave in terms of image fitting degree and error rate. The results showed that for logs with diameter ranging from 20 to 40 cm, at least 12 sensors were needed to meet the requirement which ensure a high testing accuracy of roughly 90% of fitness with 0.1 of error rate. And 10 sensors were recommended to judge the possible locations of defects and 6 sensors were sufficient to decide whether there were defects or not.

Mathematical model and numerical method for spontaneous potential log in heterogeneous formations

This paper introduces a new spontaneous potential log model for the case in which formation resistivity is not piecewise constant. The spontaneous potential satisfies an elliptic boundary value problem with jump conditions on the interfaces. It has beer/ shown that the elliptic interface problem has a unique weak solution. Furthermore, a jump condition capturing finite difference scheme is proposed and applied to solve such elliptic problems. Numerical results show validity and effectiveness of the proposed method.

Permeability Logging:A Breakthrough from 0 to1

On March 3,2024,the prototype permeability logging instrument independently developed in China successfully completed its first downhole test in Ren 91 standard well in PetroChina Huabei Oilfield.In the open hole section at a depth of 3925 metres and at a temperature of 148℃,the device collected high-quality permeability logging data.This marks a key technological breakthrough from 0 to 1 in permeability logging,and lays the foundation for the next step in developing a complete set of permeability logging equipment.

Identification of reservoir types in deep carbonates based on mixedkernel machine learning using geophysical logging data

Identification of reservoir types in deep carbonates has always been a great challenge due to complex logging responses caused by the heterogeneous scale and distribution of storage spaces.Traditional cross-plot analysis and empirical formula methods for identifying reservoir types using geophysical logging data have high uncertainty and low efficiency,which cannot accurately reflect the nonlinear relationship between reservoir types and logging data.Recently,the kernel Fisher discriminant analysis(KFD),a kernel-based machine learning technique,attracts attention in many fields because of its strong nonlinear processing ability.However,the overall performance of KFD model may be limited as a single kernel function cannot simultaneously extrapolate and interpolate well,especially for highly complex data cases.To address this issue,in this study,a mixed kernel Fisher discriminant analysis(MKFD)model was established and applied to identify reservoir types of the deep Sinian carbonates in central Sichuan Basin,China.The MKFD model was trained and tested with 453 datasets from 7 coring wells,utilizing GR,CAL,DEN,AC,CNL and RT logs as input variables.The particle swarm optimization(PSO)was adopted for hyper-parameter optimization of MKFD model.To evaluate the model performance,prediction results of MKFD were compared with those of basic-kernel based KFD,RF and SVM models.Subsequently,the built MKFD model was applied in a blind well test,and a variable importance analysis was conducted.The comparison and blind test results demonstrated that MKFD outperformed traditional KFD,RF and SVM in the identification of reservoir types,which provided higher accuracy and stronger generalization.The MKFD can therefore be a reliable method for identifying reservoir types of deep carbonates.

A log-based method for fine-scale evaluation of lithofacies and its applications to the Gulong shale in the Songliao Basin,Northeast China

The Gulong shale demonstrates high clay content and pronounced thin laminations,with limited vertical variability in log curves,complicating lithofacies classification.To comprehend the distribution and compositional features of lithofacies in the Gulong shale for optimal sweet spot selection and reservoir stimulation,this study introduced a lithofacies classification scheme and a log-based lithofacies evaluation method.Specifically,theΔlgR method was utilized for accurately determining the total organic carbon(TOC)content;a multi-mineral model based on element-to-mineral content conversion coefficients was developed to enhance mineral composition prediction accuracy,and the microresistivity curve variations derived from formation micro-image(FMI)log were used to compute lamination density,offering insights into sedimentary structures.Using this method,integrating TOC content,sedimentary structures,and mineral compositions,the Qingshankou Formation is classified into four lithofacies and 12 sublithofacies,displaying 90.6%accuracy compared to core description outcomes.The classification results reveal that the northern portion of the study area exhibits more prevalent fissile felsic shales,siltstone interlayers,shell limestones,and dolomites.Vertically,the upper section primarily exhibits organic-rich felsic shale and siltstone interlayers,the middle part is characterized by moderate organic quartz-feldspathic shale and siltstone/carbonate interlayers,and the lower section predominantly features organic-rich fissile felsic/clayey felsic shales.Analyzing various sublithofacies in relation to seven petrophysical parameters,oil test production,and fracturing operation conditions indicates that the organic-rich felsic shales in the upper section and the organic-rich/clayey felsic shales in the lower section possess superior physical properties and oil content,contributing to smoother fracturing operation and enhanced production,thus emerging as dominant sublithofacies.Conversely,thin interlayers such as siltstones and limestones,while producing oil,demonstrate higher brittleness and pose great fracturing operation challenges.The methodology and insights in this study will provide a valuable guide for sweet spot identification and horizontal well-based exploitation of the Gulong shale.

Enhancing Log Anomaly Detection with Semantic Embedding and Integrated Neural Network Innovations

System logs,serving as a pivotal data source for performance monitoring and anomaly detection,play an indispensable role in assuring service stability and reliability.Despite this,the majority of existing log-based anomaly detection methodologies predominantly depend on the sequence or quantity attributes of logs,utilizing solely a single Recurrent Neural Network(RNN)and its variant sequence models for detection.These approaches have not thoroughly exploited the semantic information embedded in logs,exhibit limited adaptability to novel logs,and a single model struggles to fully unearth the potential features within the log sequence.Addressing these challenges,this article proposes a hybrid architecture based on amultiscale convolutional neural network,efficient channel attention and mogrifier gated recurrent unit networks(LogCEM),which amalgamates multiple neural network technologies.Capitalizing on the superior performance of robustly optimized BERT approach(RoBERTa)in the realm of natural language processing,we employ RoBERTa to extract the original word vectors from each word in the log template.In conjunction with the enhanced Smooth Inverse Frequency(SIF)algorithm,we generate more precise log sentence vectors,thereby achieving an in-depth representation of log semantics.Subsequently,these log vector sequences are fed into a hybrid neural network,which fuses 1D Multi-Scale Convolutional Neural Network(MSCNN),Efficient Channel Attention Mechanism(ECA),and Mogrifier Gated Recurrent Unit(GRU).This amalgamation enables themodel to concurrently capture the local and global dependencies of the log sequence and autonomously learn the significance of different log sequences,thereby markedly enhancing the efficacy of log anomaly detection.To validate the effectiveness of the LogCEM model,we conducted evaluations on two authoritative open-source datasets.The experimental results demonstrate that LogCEM not only exhibits excellent accuracy and robustness,but also outperforms the current mainstream log anomaly detection methods.

Automatic depth matching method of well log based on deep reinforcement learning

In the traditional well log depth matching tasks,manual adjustments are required,which means significantly labor-intensive for multiple wells,leading to low work efficiency.This paper introduces a multi-agent deep reinforcement learning(MARL)method to automate the depth matching of multi-well logs.This method defines multiple top-down dual sliding windows based on the convolutional neural network(CNN)to extract and capture similar feature sequences on well logs,and it establishes an interaction mechanism between agents and the environment to control the depth matching process.Specifically,the agent selects an action to translate or scale the feature sequence based on the double deep Q-network(DDQN).Through the feedback of the reward signal,it evaluates the effectiveness of each action,aiming to obtain the optimal strategy and improve the accuracy of the matching task.Our experiments show that MARL can automatically perform depth matches for well-logs in multiple wells,and reduce manual intervention.In the application to the oil field,a comparative analysis of dynamic time warping(DTW),deep Q-learning network(DQN),and DDQN methods revealed that the DDQN algorithm,with its dual-network evaluation mechanism,significantly improves performance by identifying and aligning more details in the well log feature sequences,thus achieving higher depth matching accuracy.

A machine learning approach for the prediction of pore pressure using well log data of Hikurangi Tuaheni Zone of IODP Expedition 372,New Zealand

Pore pressure(PP)information plays an important role in analysing the geomechanical properties of the reservoir and hydrocarbon field development.PP prediction is an essential requirement to ensure safe drilling operations and it is a fundamental input for well design,and mud weight estimation for wellbore stability.However,the pore pressure trend prediction in complex geological provinces is challenging particularly at oceanic slope setting,where sedimentation rate is relatively high and PP can be driven by various complex geo-processes.To overcome these difficulties,an advanced machine learning(ML)tool is implemented in combination with empirical methods.The empirical method for PP prediction is comprised of data pre-processing and model establishment stage.Eaton's method and Porosity method have been used for PP calculation of the well U1517A located at Tuaheni Landslide Complex of Hikurangi Subduction zone of IODP expedition 372.Gamma-ray,sonic travel time,bulk density and sonic derived porosity are extracted from well log data for the theoretical framework construction.The normal compaction trend(NCT)curve analysis is used to check the optimum fitting of the low permeable zone data.The statistical analysis is done using the histogram analysis and Pearson correlation coefficient matrix with PP data series to identify potential input combinations for ML-based predictive model development.The dataset is prepared and divided into two parts:Training and Testing.The PP data and well log of borehole U1517A is pre-processed to scale in between[-1,+1]to fit into the input range of the non-linear activation/transfer function of the decision tree regression model.The Decision Tree Regression(DTR)algorithm is built and compared to the model performance to predict the PP and identify the overpressure zone in Hikurangi Tuaheni Zone of IODP Expedition 372.

Integrated Geological and Geophysical Mapping for Groundwater Potential Studies at Ekwegbe-Agu and Environs, Enugu State, Nigeria

The study integrates both the geological and geophysical mapping techniques for groundwater potential studies at Ekwegbe-Agu and the environs, Enugu state, Nigeria for optimal citing of borehole. Located in the Anambra Basin between latitudes 6˚43'N and 6˚47'N and longitudes 7˚28'E and 7˚32'E, it is stratigraphycally underlain by, from bottom to top, the Enugu/Nkporo, Mamu and Ajali Formation respectively, a complex geology that make citing of productive borehole in the area problematic leading to borehole failure and dry holes due to inadequate sampling. The study adopted a field and analytic sampling approach, integrating field geological, electrical resistivity and self-potential methods. The software, SedLog v3.1, InterpexIx1Dv.3, and Surfer v10 were employed for the data integration and interpretation. The result of the geological field and borehole data shows 11 sedimentary facies consisting of sandstone, shales and heterolith of sandstone/shale, with the aquifer zone mostly prevalent in the more porous sand-dominated horizons. Mostly the AK and HK were the dominant curve types. An average of 6 geo-electric layers were delineated across all transects with resistivity values ranging from 25.42 - 105.85 Ωm, 186.38 - 3383.3 Ωm, and 2992 - 6286.4 Ωm in the Enugu, Mamu and Ajali Formations respectively. The resistivity of the main aquifer layer ranges from 1 to 500 Ωm. The aquifer thickness within the study area varies between 95 and 140 m. The western and northwestern part of the study area which is underlain mainly by the Ajali Formation showed the highest groundwater potential in the area and suitable for citing productive boreholes.

Facies logging identification of intermediate-basic volcanic rocks in Huoshiling Formation of Songliao Basin

Volcanic oil and gas reservoirs are generally buried deep,which leads to a high whole-well coring cost,and the degree of development and size of reservoirs are controlled by volcanic facies.Therefore,accurately identifying volcanic facies by logging curves not only provides the basis of volcanic reservoir prediction but also saves costs during exploration.The Songliao Basin is a‘fault-depression superimposed’composite basin with a typical binary filling structure.Abundant types of volcanic lithologies and facies are present in the Lishu fault depression.Volcanic activity is frequent during the sedimentary period of the Huoshiling Formation.Through systematic petrographic identification of the key exploratory well(SN165C)of the Lishu fault-depression,which is a whole-well core,it is found that the Huoshiling Formation in SN165C contains four facies and six subfacies,including the volcanic conduit facies(crypto explosive breccia subfacies),explosive facies(pyroclastic flow and thermal wave base subfacies),effusive facies(upper and lower subfacies),and volcanogenic sedimentary facies(pyroclastic sedimentary subfacies).Combining core,thin section,and logging data,the authors established identification markers and petrographic chart logging phases,and also interpreted the longitudinal variation in volcanic petro-graphic response characteristics to make the charts more applicable to this area's volcanic petrographic interpretation of the Huoshiling Formation.These charts can provide a basis for the further exploration and development of volcanic oil and gas in this area.

Pore size classification and prediction based on distribution of reservoir fluid volumes utilizing well logs and deep learning algorithm in a complex lithology

Pore size analysis plays a pivotal role in unraveling reservoir behavior and its intricate relationship with confined fluids.Traditional methods for predicting pore size distribution(PSD),relying on drilling cores or thin sections,face limitations associated with depth specificity.In this study,we introduce an innovative framework that leverages nuclear magnetic resonance(NMR)log data,encompassing clay-bound water(CBW),bound volume irreducible(BVI),and free fluid volume(FFV),to determine three PSDs(micropores,mesopores,and macropores).Moreover,we establish a robust pore size classification(PSC)system utilizing ternary plots,derived from the PSDs.Within the three studied wells,NMR log data is exclusive to one well(well-A),while conventional well logs are accessible for all three wells(well-A,well-B,and well-C).This distinction enables PSD predictions for the remaining two wells(B and C).To prognosticate NMR outputs(CBW,BVI,FFV)for these wells,a two-step deep learning(DL)algorithm is implemented.Initially,three feature selection algorithms(f-classif,f-regression,and mutual-info-regression)identify the conventional well logs most correlated to NMR outputs in well-A.The three feature selection algorithms utilize statistical computations.These algorithms are utilized to systematically identify and optimize pertinent input features,thereby augmenting model interpretability and predictive efficacy within intricate data-driven endeavors.So,all three feature selection algorithms introduced the number of 4 logs as the most optimal number of inputs to the DL algorithm with different combinations of logs for each of the three desired outputs.Subsequently,the CUDA Deep Neural Network Long Short-Term Memory algorithm(CUDNNLSTM),belonging to the category of DL algorithms and harnessing the computational power of GPUs,is employed for the prediction of CBW,BVI,and FFV logs.This prediction leverages the optimal logs identified in the preceding step.Estimation of NMR outputs was done first in well-A(80%of data as training and 20%as testing).The correlation coefficient(CC)between the actual and estimated data for the three outputs CBW,BVI and FFV are 95%,94%,and 97%,respectively,as well as root mean square error(RMSE)was obtained 0.0081,0.098,and 0.0089,respectively.To assess the effectiveness of the proposed algorithm,we compared it with two traditional methods for log estimation:multiple regression and multi-resolution graph-based clustering methods.The results demonstrate the superior accuracy of our algorithm in comparison to these conventional approaches.This DL-driven approach facilitates PSD prediction grounded in fluid saturation for wells B and C.Ternary plots are then employed for PSCs.Seven distinct PSCs within well-A employing actual NMR logs(CBW,BVI,FFV),in conjunction with an equivalent count within wells B and C utilizing three predicted logs,are harmoniously categorized leading to the identification of seven distinct pore size classification facies(PSCF).this research introduces an advanced approach to pore size classification and prediction,fusing NMR logs with deep learning techniques and extending their application to nearby wells without NMR log.The resulting PSCFs offer valuable insights into generating precise and detailed reservoir 3D models.

Development of Long-Range,Low-Powered and Smart IoT Device for Detecting Illegal Logging in Forests

Forests promote the conservation of biodiversity and also play a crucial role in safeguarding theenvironment against erosion,landslides,and climate change.However,illegal logging remains a significant threatworldwide,necessitating the development of automatic logging detection systems in forests.This paper proposesthe use of long-range,low-powered,and smart Internet of Things(IoT)nodes to enhance forest monitoringcapabilities.The research framework involves developing IoT devices for forest sound classification andtransmitting each node’s status to a gateway at the forest base station,which further sends the obtained datathrough cellular connectivity to a cloud server.The key issues addressed in this work include sensor and boardselection,Machine Learning(ML)model development for audio classification,TinyML implementation on amicrocontroller,choice of communication protocol,gateway selection,and power consumption optimization.Unlike the existing solutions,the developed node prototype uses an array of two microphone sensors forredundancy,and an ensemble network consisting of Long Short-Term Memory(LSTM)and ConvolutionalNeural Network(CNN)models for improved classification accuracy.The model outperforms LSTM and CNNmodels when used independently and also gave 88%accuracy after quantization.Notably,this solutiondemonstrates cost efficiency and high potential for scalability.

Application of Secondary Logging Interpretation—Taking Yan 9 Reservoir in X Area as an Example

Logging data and its interpretation results are one of the most important basic data for understanding reservoirs and oilfield development. Standardized and unified logging interpretation results play a decisive role in fine reservoir description and reservoir development. Aiming at the problem of the conflict between the development effect and the initial interpretation result of Yan 9 reservoir in Hujianshan area of Ordos Basin, by combining the current well production performance, logging, oil test, production test and other data, on the basis of making full use of core, coring, logging, thin section analysis and high pressure mercury injection data, the four characteristics of reservoir are analyzed, a more scientific and reasonable calculation model of reservoir logging parameters is established, and the reserves are recalculated after the second interpretation standard of logging is determined. The research improves the accuracy of logging interpretation and provides an effective basis for subsequent production development and potential horizons.

Transfer learning for well logging formation evaluation using similarity weights

Machine learning has been widely applied in well logging formation evaluation studies.However,several challenges negatively impacted the generalization capabilities of machine learning models in practical imple-mentations,such as the mismatch of data domain between training and testing datasets,imbalances among sample categories,and inadequate representation of data model.These issues have led to substantial insufficient identification for reservoir and significant deviations in subsequent evaluations.To improve the transferability of machine learning models within limited sample sets,this study proposes a weight transfer learning framework based on the similarity of the labels.The similarity weighting method includes both hard weights and soft weights.By evaluating the similarity between test and training sets of logging data,the similarity results are used to estimate the weights of training samples,thereby optimizing the model learning process.We develop a double experts’network and a bidirectional gated neural network based on hierarchical attention and multi-head attention(BiGRU-MHSA)for well logs reconstruction and lithofacies classification tasks.Oil field data results for the shale strata in the Gulong area of the Songliao Basin of China indicate that the double experts’network model performs well in curve reconstruction tasks.However,it may not be effective in lithofacies classification tasks,while BiGRU-MHSA performs well in that area.In the study of constructing large-scale well logging processing and formation interpretation models,it is maybe more beneficial by employing different expert models for combined evaluations.In addition,although the improvement is limited,hard or soft weighting methods is better than unweighted(i.e.,average-weighted)in significantly different adjacent wells.The code and data are open and available for subsequent studies on other lithofacies layers.

Automatic discrimination of sedimentary facies and lithologies in reef-bank reservoirs using borehole image logs

Reef-bank reservoirs are an important target for petroleum exploration in marine carbonates and also an essential supplemental area for oil and gas production in China. Due to the diversity of reservoirs and the extreme heterogeneity of reef-banks, it is very difficult to discriminate the sedimentary facies and lithologies in reef-bank reservoirs using conventional well logs. The borehole image log provides clear identification of sedimentary structures and textures and is an ideal tool for discriminating sedimentary facies and lithologies. After examining a large number of borehole images and cores, we propose nine typical patterns for borehole image interpretation and a method that uses these patterns to discriminate sedimentary facies and lithologies in reeI^bank reservoirs automatically. We also develop software with user-friendly interface. The results of applications in reef-bank reservoirs in the middle Tarim Basin and northeast Sichuan have proved that the proposed method and the corresponding software are quite effective.

Studies on phase and group velocities from acoustic logging

It is still argued whether we measure phase or group velocities using acoustic logging tools. In this paper, three kinds of models are used to investigate this problem by theoretical analyses and numerical simulations. First, we use the plane-wave superposition model containing two plane waves with different velocities and able to change the values of phase velocity and group velocity. The numerical results show that whether phase velocity is higher or lower than group velocity, using the slowness-time coherence （STC） method we can only get phase velocities. Second, according to the results of the dispersion analysis and branch-cut integration, in a rigid boundary borehole model the results of dispersion curves and the waveforms of the first-order mode show that the velocities obtained by the STC method are phase velocities while group velocities obtained by arrival time picking. Finally, dipole logging in a slow formation model is investigated using dispersion analysis and real-axis integration. The results of dispersion curves and full wave trains show similar conclusions as the borehole model with rigid boundary conditions.

Application of the equivalent offset migration method in acoustic log reflection imaging

Borehole acoustic reflection logging can provide high resolution images of nearborehole geological structure. However, the conventional seismic migration and imaging methods are not effective because the reflected waves are interfered with the dominant borehole-guided modes and there are only eight receiving channels per shot available for stacking. In this paper, we apply an equivalent offset migration method based on wave scattering theory to process the acoustic reflection imaging log data from both numerical modeling and recorded field data. The result shows that, compared with the routine post-stack depth migration method, the equivalent offset migration method results in higher stack fold and is more effective for near-borehole structural imaging with low SNR acoustic reflection log data.

Data mining and well logging interpretation: application to a conglomerate reservoir

Data mining is the process of extracting implicit but potentially useful information from incomplete, noisy, and fuzzy data. Data mining offers excellent nonlinear modeling and self-organized learning, and it can play a vital role in the interpretation of well logging data of complex reservoirs. We used data mining to identify the lithologies in a complex reservoir. The reservoir lithologies served as the classification task target and were identified using feature extraction, feature selection, and modeling of data streams. We used independent component analysis to extract information from well curves. We then used the branch-and- bound algorithm to look for the optimal feature subsets and eliminate redundant information. Finally, we used the C5.0 decision-tree algorithm to set up disaggregated models of the well logging curves. The modeling and actual logging data were in good agreement, showing the usefulness of data mining methods in complex reservoirs.

Pore structure effect on reservoir electrical properties and well logging evaluation

The reservoir pore structure controls the reservoir quality and resistivity response of hydrocarbon-bearing zones and thus, critically affects logging interpretation. We use petrophysical data in three types of reservoir with different pore structure characteristics to show that the complexity of pore structure had a significant effect on the effective porosity and permeability regardless of geological factors responsible for the formation of pore structure. Moreover,, the distribution and content of conductive fluids in the reservoir varies dramatically owing to pore structure differences, which also induces resistivity variations in reservoir rocks. Hence, the origin of low-resistivity hydrocarbon-bearing zones, except for those with conductive matrix and mud filtrate invasion, is attributed to the complexity of the pore structures. Consequently, reservoir-specific evaluation models, parameters, and criteria should be chosen for resistivity log interpretation to make a reliable evaluation of reservoir quality and fluids.