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.

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.

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.

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.

Well logging evaluation of fine-grained hydrate-bearing sediment reservoirs: Considering the effect of clay content

Hydrate reservoirs are different from the host reservoirs of all other fossil energy sources because the characteristics of hydrate reservoirs are generally controlled by deep-sea fine-grained sedimentation. In such reservoirs, the reliability of the classical logging evaluation models established for diagenetic reservoirs is questionable. This study used well W8 in the Qiongdongnan Basin to explore the clay content, porosity, saturation, and hydrate-enriched layer identification of a logging-based hydrate reservoir, and it was found that considering the effect of the clay content on the log response is necessary in the logging evaluation of hydrate reservoirs. In the evaluation of clay content, a method based on the optimization inversion method can obtain a more reliable clay content than other methods. Fine-grained sediment reservoirs have a high clay content, and the effect of clay on log responses must be considered when calculating porosity. In addition, combining density logging and neutron porosity logging data can obtain the best porosity calculation results, and the porosity calculation method based on sonic logging predicted that the porosity of the studied reservoir was low. It was very effective to identify hydrate layers based on resistivity, but the clay distribution and pore structure will also affect the relationship between resistivity, porosity and saturation, and it was suggested that the factors effecting the resistivity of different layers should be considered in the saturation evaluation and that a suitable model should be selected. This study also considered the lack of clarity of the relationships among the lithology, physical properties, hydrate-bearing occurrence properties, and log response properties of hydrate reservoirs and the lack of specialized petrophysical models. This research can directly help to improve hydrate logging evaluation.

Logging curves characteristics and response mechanisms of basaltic facies and sub-facies: A case study from eastern sag of Liaohe depression, Northeast China

Based on five types of conventional logging curves including GR,RLLD,CNL,DEN and AC,and 39 core samples from 30 representative boreholes,the logging characteristics and lithofacies and sub-facies of the basaltic rocks were studied.Three basaltic facies and four sub-facies are recognized from the well logs,includ-ing volcanic conduit facies(post intrusive sub-facies),explosive facies,and effusive lava flow facies(tabular flow,compound flow and hyaloclastite sub-facies).The post intrusive,tabular flow and compound flow sub-facies logging curves are mainly controlled by the distribution of vesiculate zones and vesiculate content,which are characterized by four curves with good correlation.Post intrusive sub-facies are characterized by high RLLD,high DEN,with a micro-dentate logging curve pattern,abrupt contact relationships at the top and base.Tabular flow sub-facies are characterized by high RLLD,high DEN,with a bell-shaped log curve pattern,abrupt contact at the base and gradational contact at the top.Compound flow sub-facies are characterized by medium-low RLLD,with a micro-dentate or finger-like logging curve pattern,abrupt contact at the base and gradational contact at the top.Explosive facies and hyaloclastite sub-facies logging curves are mainly controlled by the distribution of the size and sorting of rock particles,which can be recognized by four kinds of logging curves with poor cor-relation.Explosive facies are characterized by low RLLD,medium-low CNL and low DEN,with a micro-dentate logging curve pattern.Hyaloclastite sub-facies are characterized by low RLLD,high CNL,low DEN and high AC,with a micro-dentate logging curve pattern.The present research is beneficial for the prediction of basaltic reser-voirs not only in the Liaohe depression but also in the other volcanic-sedimentary basins.

Total organic carbon content logging prediction based on machine learning:A brief review

The total organic carbon content usually determines the hydrocarbon generation potential of a formation.A higher total organic carbon content often corresponds to a greater possibility of generating large amounts of oil or gas.Hence,accurately calculating the total organic carbon content in a formation is very important.Present research is focused on precisely calculating the total organic carbon content based on machine learning.At present,many machine learning methods,including backpropagation neural networks,support vector regression,random forests,extreme learning machines,and deep learning,are employed to evaluate the total organic carbon content.However,the principles and perspectives of various machine learning algorithms are quite different.This paper reviews the application of various machine learning algorithms to deal with total organic carbon content evaluation problems.Of various machine learning algorithms used for TOC content predication,two algorithms,the backpropagation neural network and support vector regression are the most commonly used,and the backpropagation neural network is sometimes combined with many other algorithms to achieve better results.Additionally,combining multiple algorithms or using deep learning to increase the number of network layers can further improve the total organic carbon content prediction.The prediction by backpropagation neural network may be better than that by support vector regression;nevertheless,using any type of machine learning algorithm improves the total organic carbon content prediction in a given research block.According to some published literature,the determination coefficient(R^(2))can be increased by up to 0.46 after using machine learning.Deep learning algorithms may be the next breakthrough direction that can significantly improve the prediction of the total organic carbon content.Evaluating the total organic carbon content based on machine learning is of great significance.

Response analyses on the drill-string channel for logging while drilling telemetry

Downhole acoustic telemetry(DAT),using a long drill string with periodical structures as the channel,is a prospective technology for improving the transmission rate of logging while drilling(LWD)data.Previous studies only focused on the acoustic property of a free drill string and neglected the coupling between pipes and fluid-filled boreholes.In addition to the drill-string waves,a series of fluid waves are recorded in the DAT channel,which has not been investigated yet.Unpredictable channel characteristics result in lower transmission rates and stability than expected.Therefore,a more realistic channel model is needed considering the fluid-filled borehole.In this paper,we propose a hybrid modeling method to investigate the response characteristics of the DAT channel.By combining the axial wavenumbers and excitation functions of mode waves in radially layered LWD structures,the channel model is approximated to the 1-D propagation,which considers transmission,reflection,and interconversion of the drillstring and fluid waves.The proposed 1-D approximation has been well validated by comparing the 2-D finite-difference modeling.It is revealed that the transmitted and converted fluid waves interfere with the drill-string wave,which characterizes the DAT channel as a particular coherent multi-path channel.When a fluid-filled borehole surrounds the drill string,the channel responses exhibit considerable delay as well as strong frequency selectivity in amplitude and phase.These new findings suggest that the complexity of the channel response has been underestimated in the past,and therefore channel measurements on the ground are unreliable.To address these channel characteristics,we apply a noncoherent demodulation strategy.The transmission rate for synthetic data reaches 15 bps in a 94.5 m long channel,indicating that the acoustic telemetry is promising to break the low-speed limitation of mud-pulse telemetry.

Relational Logging Design Pattern

Observability and traceability of developed software are crucial to its success in software engineering.Observability is the ability to comprehend a system’s internal state from the outside.Monitoring is used to determine what causes system problems and why.Logs are among the most critical technology to guarantee observability and traceability.Logs are frequently used to investigate software events.In current log technologies,software events are processed independently of each other.Consequently,current logging technologies do not reveal relationships.However,system events do not occur independently of one another.With this perspective,our research has produced a new log design pattern that displays the relationships between events.In the design we have developed,the hash mechanism of blockchain technology enables the display of the logs’relationships.The created design pattern was compared to blockchain technology,demonstrating its performance through scenarios.It has been determined that the recommended log design pattern outperforms blockchain technology in terms of time and space for software engineering observability and traceability.In this context,it is anticipated that the log design pattern we provide will strengthen the methods used to monitor software projects and ensure the traceability of relationships.

Characterization of reservoir properties and pore structure based on micro-resistivity imaging logging: Porosity spectrum, permeability spectrum, and equivalent capillary pressure curve

According to the capillary theory,an equivalent capillary model of micro-resistivity imaging logging was built.On this basis,the theoretical models of porosity spectrum(Ф_(i)),permeability spectrum(K_(i))and equivalent capillary pressure curve(pe)were established to reflect the reservoir heterogeneity.To promote the application of the theoretical models,the Archie's equation was introduced to establish a general model for quantitatively characterizing bi,K,and pei.Compared with the existing models,it is shown that:(1)the existing porosity spectrum model is the same as the general equation of gi;(2)the Ki model can display the permeability spectrum as compared with Purcell's permeability model;(3)the per model is constructed on a theoretical basis and avoids the limitations of existing models that are built only based on the component of porosity spectrum,as compared with the empirical model of capillary pressure curve.The application in the Permian Maokou Formation of Well TsX in the Central Sichuan paleo-uplift shows that the Ф_(i),K_(i),and p_(ci) models can be effectively applied to the identification of reservoir types,calculation of reservoir properties and pore structure parameters,and evaluation of reservoir heterogeneity.

Numerical simulation and response analysis of microspherical focused logging in inclined micro-fractured formation

Tight and unconventional reservoirs have become the focus with the progress of petroleum exploration and development.Micro-fractures in these reservoirs can effectively improve reservoir permeability,and well-developed micro-fractures can serve to directly improve productivity.Compared with the centered electrical well logging method,the Micro Spherical Focused Logging(MSFL)is more suitable for microfracture identification due to its high resolution and near borehole wall measuring method.In this study,an anisotropic model is used to depict micro-fractured formation.First,a forward model with microfractured formation,borehole,logging instrument and surrounding rock is established.Subsequently,MSFL responses under different micro-fracture porosity,resistivity,dip angle and borehole radius,are calculated based on the finite element method(FEM).Finally,the MSFL responses under different microfracture parameters are analyzed with the response laws clarified.

Project Level Pavement Evaluation Using FWD,GPR,and Video Logging and Its Application in Pavement Rehabilitation in Indiana

Pavement rehabilitation is a major activity for all highway agencies.Accurate and efficient measurement of the rehabilitated pavement performances becomes more and more important in this procedure.In the last 10 years,significant improvements have been made in pavement nondestructive evaluation.NDT(non-destructive testing)has gained popularity because of its advantage in comparison to laboratory testing.Some of these advantages include minimal or no damage to structure,in-situ full-scale testing,relatively low operational cost,and short test duration.The INDOT(Indiana Department of Transportation)has a project level pavement evaluation program that began several years ago.This project level evaluation program employs FWD(falling weight deflectometer),GPR(ground penetration radar)and video logging.The program provides valuable information about pavement performance characteristics and offers useful tools for developing pavement rehabilitation strategies,specifically overlays and pavement underseals.On the other hand,the state of Indiana had rehabilitated its flexible,rigid or composite pavement almost exclusively with asphalt.This AC(asphalt concrete)overlay can improve the condition of existing pavement and extend the service life of the existing pavement structure.This paper thus describes the experiences of pavement overlay with AC thickness design for the INDOT(Indiana State Department of Transportation)using the AASHTO(American Association of State Highway and Transportation Officials)1993 Guide,the MEPDG(Mechanistic-Empirical Pavement Design Guide).In order to do that,backcalculation program was compared and evaluated to obtain subgrade resilient modulus and k value for pavement rehabilitation using FWD data.Video logging provides IRI(international roughness index)and rut depth for existing pavement condition and GPR provides thickness or pavement bonding conditions in pavement.Emphasis is placed on observations and issues encountered using the current AASHTO 1993 Guide and the MEPDG.

Soil Seed Bank Characteristics in Congolese Rainforests and Implications for Post-Logging Plots Reforestation

The soil seed bank is considered as an important mechanism for the natural regeneration, resilience and conservation of the forests after disturbances. This study evaluates the characteristics of the soil seed bank in two post-logging plots of Loundoungou-Toukoulaka Forest Management Unit: one plot exploited in 2008 and another exploited in 2021. In each study plot, 40 samples were collected per soil layer (0 - 5 cm, 5 - 10 cm, 10 - 15 cm, 15 - 20 cm and 20 - 25 cm depth). The species diversity and abundance of the soil seed bank were estimated after soil samples were brought to germination. The results demonstrated that 347 seedlings belonging to 37 species in the plot exploited in 2008 and 418 seedlings belonging to 27 species in that exploited in 2021 germinated during 20 weeks of monitoring. The total densities of the seedlings identified were respectively 1446 seedlings/m2 and 1742 seedlings/m2. The plot exploited in 2021 presented a higher proportion of herbaceous species (93.78%) compared to that exploited in 2008 (82.71%). Two pioneer species were recorded in the plot exploited in 2008. These are Macaranga barteri (0.29%) in the 0 - 5 cm layer and Musanga cecropioides (2.31%) up to 20 cm deep. On the other hand, in the plot exploited in 2021, Macaranga spinosa (0.96%) in the 0 - 5 cm layer and M. cecropioides (0.96%) up to 20 cm deep were identified. In the plot exploited in 2008, the 20 - 25 cm layer demonstrated important proportions in woody species (9%), these are in particular Rubiaceae sp.4 and Nauclea diderrichii. While that exploited in 2021, presented 19% of woody species, namely the species of Rubiaceae sp.4, Rubiaceae sp.5 and N. diderrichii, greatly exceeding the proportions obtained in the 15 - 20 cm layer of the two plots. Nonetheless, N. diderrichii was the only commercial species recorded with densities of 108 seedlings/m2 and 4 seedlings/m2, respectively in the plot exploited in 2008 and that exploited in 2021. Commercial tree species are poorly represented in the soil seed bank. Consequently, the study suggests that to improve the natural regeneration of the commercial species, silvicultural interventions based on planting techniques in the exploited plots should be more effective in order to sustainably manage these production forests.

Research and experimental testing of a new kind electrokinetic logging tool

We designed a new downhole electrokinetic logging tool based on numericalsimulations and petrophysical experiments. Acoustic and electric receivers cannot be arrangedat the same depth, and the proposed composite electrokinetic logging tool offers a solutionto this problem. The sound field characteristics of the detectors were tested in a water tank inthe laboratory. Then, we calculated the sound pressure of the radiated acoustic field and thetransmitting voltage response of the transmitting transducers; in addition, we analyzed thedirectivity and application of the acoustic transmitting probe based on linear phased array.The results suggest that the sound pressure generated at 1500 mm spacing reaches up to 47.2k Pa and decreases with increasing acoustic source frequency. When the excitation signalsdelay time of adjacent acoustic transmitting subarrays increases, the radiation beam of themain lobe is deflected and its energy gradually increases, which presumably enhances theacoustoelectric conversion efficiency.

Fractal Correction of Well Logging Curves

It is always significant for assessing and evaluation of oil bearing layers, especially for well logging data processing and interpretation of non marine oil beds to get more accurate physical properties in thin and inter thin layers. This paper presents a definition of measures and the measure presents power law relation with the corresponded scale described by fractal theory. Thus, logging curves can be reconstructed according to this power law relation. This method uses the local structure nearby concurrent points to compensate the average effect of logging probes and measurement errors. As an example, deep and medium induced conductivity (IMPH and IDPH) curves in ODP Leg 127 Hole 797C are reconstructed or corrected. Corrected curves are with less adjacent effects through comparison of corrected curves with original one. And also, the power spectra of corrected well logging curve are abounding with more resolution components than the original one. Thus, fractal correction method makes the well logging more resoluble for thin beds.

CCSD Well Logging Engineering Program

This paper introduces briefly the tasks and characteristics of China Continent Science Drilling (CCSD) Well Logging Engineering, the logging methods measured with CCSD, the quality control of original logging information, the logging plan of CCSD, the logging engineering management of CCSD, the logging interpretation and the results and reports made with CCSD.

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.

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.

Acoustic reflection well logging modeling using the frequency-domain finite-element method with a hybrid PML

In this paper, we propose a hybrid PML （H-PML） combining the normal absorption factor of convolutional PML （C-PML） with tangential absorption factor of Mutiaxial PML （M-PML）. The H-PML boundary conditions can better suppress the numerical instability in some extreme models, and the computational speed of finite-element method and the dynamic range are greatly increased using this HPML. We use the finite-element method with a hybrid PML to model the acoustic reflection of the interface when wireline and well logging while drilling （LWD）, in a formation with a reflector outside the borehole. The simulation results suggests that the PS- and SP- reflected waves arrive at the same time when the inclination between the well and the outer interface is zero, and the difference in arrival times increases with increasing dip angle. When there are fractures outside the well, the reflection signal is clearer in the subsequent reflection waves and may be used to identify the fractured zone. The difference between the dominant wavelength and the model scale shows that LWD reflection logging data are of higher resolution and quality than wireline acoustic reflection logging.