Summary In the mud logging process, manual lithology identification of drill cuttings not only relies heavily on experienced engineering geologists but is also labor-intensive and prone to subjective bias. Meanwhile, automatic lithology identification faces several challenges, including small object sizes, fragmented morphology, and high-density distribution of samples. Existing mainstream object detection frameworks still fall short in effectively modeling global contextual information and performing adaptive feature calibration for drill cuttings. To address these issues, we propose YoMa-DL, a novel drill cuttings lithology detection framework. First, an enhanced state-space-based Vision Mamba (V-Mamba) sequence modeling module is incorporated into the you only look once (YOLOv11) backbone, which integrates local spatial block (LSBlock), 2D selective scan (SS2D), and depthwise gated block (DGBlock) components to reinforce the representation of global contextual features essential for drill cuttings lithology discrimination. Then, a lightweight adaptive multiattention (AMAtt) mechanism specifically designed for this model is introduced both in the backbone and before each detection head to finely calibrate the extracted global spatial features, enabling the model to more accurately focus on key textures and morphological structures of drill cuttings. We validate YoMa-DL on a drill cuttings image data set collected at an oilfield mud logging center, demonstrating a 5.8-point gain in mean average precision (mAP)50:95 over the YOLOv11 baseline and outperforming multiple state-of-the-art detection methods across precision, recall, mAP50, and mAP50:95. Ablation studies further demonstrate that both V-Mamba and AMAtt contribute significantly to performance improvement and exhibit strong synergy. This approach integrates state-space modeling with YOLO-based spatial detection, providing an effective automated solution for drill cuttings lithology identification in mud logging.

ABSTRACT A sequence stratigraphic analysis was conducted in the Srikail Gas Field, situated within the Tripura Uplift in the east-central Bengal Basin, near the Surma Sub-Basin. This study aimed to understand the sedimentary infill behaviour and the distribution of producing and non-producing sands by interpreting Mud Log and Wireline Log Data. Deltaic sands of the Miocene Surma Group were analysed, defining surfaces and systems tracts using Maximum Flooding Surfaces (MFS) as sequence boundaries. Four MFS and five third-order sequences (a to e) were identified. The stratigraphic relationship between this scheme and traditional Surma Group stratigraphy revealed that the Bhuban Formation corresponds to sequences a and b, while the Bokabil Formation correlates with sequences c to e. Producing sands A, B, and C were found in the transition from early to late Lowstand Systems Tract (LST), whereas non-producing sands, including the prominent D sand, were located in the Transgressive Systems Tract (TST). The sequence stratigraphic framework of the Surma Group succession offers valuable guidance for hydrocarbon exploration in the Bengal Basin, particularly in and around the Srikail field, with significant implications for both conventional and unconventional reservoirs.

A stacking ensemble approach for pore pressure prediction in real-time during drilling based on mud log data

ABSTRACT The application of mud logging in formation evaluation is significant because it reduces operational risks through the monitoring of gas composition and other drilling parameters. While widely used, systematic validation of mud logging data against wireline and fluid sampling data for formation and pressure assessment remains limited in the Niger Delta Basin. This study advances current practices in the region by investigating the reliability of mud logging data for formation characterisation and pore pressure prediction. Three wells (X, Y, and Z) were investigated for gas ratio analysis using the Pixler Model – based on hydrocarbon ratios (C1-C5) – and pore pressure prediction using the drilling exponent (D-exponent) model. Results show that two of the three wells had formation pressure predictions that closely matched wireline pressure data. However, approximately 37.5% inconsistencies appeared in the gas ratio results. Reservoir X3 (Well X) had a gas peak of 371,600 ppm, while Reservoir Z2 (Well Z) had 369,600 ppm, yet the gas ratio plots failed to distinguish hydrocarbon-bearing from non-hydrocarbon zones. Therefore, it was inferred that while mud logging may be effective in pressure evaluation, it is limited in formation characterisation, especially in complex lithologies and low-gas reservoirs.

_ This article, written by JPT Technology Editor Chris Carpenter, contains highlights of paper SPE 222299, “Unlocking the Potential of Mud Logs and LWD in the Gulf of Thailand Using Machine Learning,” by Sethawut Palviriyachote, Siddharth Misra, SPE, and Sandro Moelyono, SPE, Texas A&M University, et al. The paper has not been peer reviewed. _ The subject gas field in the Gulf of Thailand (GOT) stands as one of the largest natural gas reserves in Thailand, with over 30 years of development history and more than 1,000 penetrated wells. Use of machine learning (ML) for log synthesis can help reduce expenses and operational risks associated with traditional well-logging methods, including service fees, rig time, and potential retrieval challenges. This study aims to use ML techniques to predict well logs by analyzing mud-log and logging-while-drilling (LWD) data. Introduction Drilling in the GOT faces challenges involving high temperatures, pressures, and complex geological structures, demanding robust logging techniques and careful interpretation to ensure successful outcomes. Many wells feature incomplete well-log data, which complicates development planning. With the advent of ML technologies, however, a transformative approach to predict crucial well logs is presented. The potential cost savings from reducing well-log fees and rig time in one of the fields could amount to $1 million per month. Data-Driven Methodology This section outlines the process of developing ML models for predicting three key targets from openhole logs: bulk density (RHOB), neutron porosity (NPHI), and compressional sonic travel time (DTC). The first two of the five steps of the methodology are detailed in this synopsis. 1. Data Collection. The initial step involves gathering a comprehensive data set of well logs, including LWD, mud-log and openhole-log data. This data set should be scrutinized for completeness, correctness, and relevance to ensure that it provides a solid foundation for subsequent analysis. 2. Data Preprocessing. In this stage, the data is prepared for developing predictive models. First, anomalies that may distort the analysis are identified and removed. Next, new features are engineered, or existing ones are modified to enhance predictive performance. Finally, numerical features are normalized and scaled to ensure generalizable, unbiased predictive performance. 3. Model Selection and Training. This phase involves choosing appropriate regression and ML techniques and then tuning their hyperparameters to obtain highly generalizable prediction models. Key tasks include defining hyperparameters to be tuned and their tuning ranges that ultimately control model generalization. The authors tune random forest, gradient boosting, neural networks, and support vector regression techniques. The overall objective in this study is to process mud logs and LWD logs to predict RHOB, NPHI, and DTC. 4. Model Evaluation. Once the model is trained, its performance is evaluated on test data to determine its effectiveness. Metrics such as R-squared, mean absolute error(MAE), and mean absolute percentage error (MAPE) are calculated to gauge generalization performance. 5. Deployment. The final step involves integrating the trained and tested model into a real-world deployment environment to evaluate the applicability of the predictive model.

Real-time and precise monitoring of drill string vibration states is crucial for ensuring the safe and efficient drilling of complex oil and gas wells. However, limited by the high cost and poor timeliness of downhole measurement data acquisition, existing methods predominantly rely on single-source parameters, making it difficult to precisely monitor vibration modes. A novel architecture for real-time drill string vibration monitoring via surface-downhole parameter fusion was designed. First, a downhole three-axial acceleration prediction model was established based on the gated recurrent unit (GRU) to provide real-time downhole data for the model. Second, the variational modal decomposition (VMD) method is introduced to extract the multicomponent frequency domain features of downhole vibration signals. Third, a hybrid network architecture with the GRU and Informer models in parallel is designed to capture and fuse the multidimensional and multiscale features of the surface-downhole information. Finally, a Mixture of Experts (MoE) architecture is introduced to synthesize the coupled correlations between vibrations to improve the computational efficiency and accuracy of the model. The results demonstrate that GRU-Informer with MoE outperforms current models, achieving an accuracy of 0.912 and a precision of 0.820. Compared to the models with separate inputs of surface mud logging and downhole vibration data, the model's accuracy was improved by 15.59% and 11.08%, respectively. Comparative studies validate the contributions of VMD, GRU-Informer structure, and MoE, emphasizing the critical role of the designed framework in improving the model adaptability and performance. This work provides significant theoretical support for mitigating drilling risks and enhancing operational efficiency.

_ The relentless march of computational intelligence continues to redefine the paradigms of petroleum engineering, offering sophisticated solutions to long- standing challenges in subsurface characterization and operational optimization. A compelling triptych of recent research illuminates this trajectory, showcasing the burgeoning capacity of machine learning (ML) to unlock substantial efficiencies and enhance decision-making across the exploration and production lifecycle. Paper SPE 222299 presents a framework for synthesizing crucial openhole well logs by ingeniously leveraging readily available mud-log and logging-while-drilling data within the complex geological context of the Gulf of Thailand. The authors demonstrate that robust algorithms, particularly random forest and gradient-boosting regressors, can achieve remarkable predictive accuracy. This offers a pragmatic solution to populate data-deficient legacy wells, crucial for informed reservoir management, and promises tangible fiscal benefits by curtailing the necessity for costly conventional logging. Paper SPE 35892 introduces a physics-informed ML framework to elevate permeability prediction in notoriously heterogeneous carbonate reservoirs. By integrating physics-based constraints—specifically, modeling the discrepancy between core and nuclear-magnetic-resonance-derived permeability—this research enhances the predictive power of tree-ensemble algorithms. Physics-informed models transcend purely data-driven methodologies, offering more-robust and generalizable frameworks by embedding domain-specific physical understanding directly into the learning process, thereby bridging the gap between empirical observation and fundamental reservoir physics. Further exemplifying ML’s strategic value, paper SPE 224365 details an intelligent system for optimizing depth selection in formation pressure testing (FPT). An artificial neural network trained on an extensive suite of well logs demonstrates a remarkable 94% specificity in identifying depth intervals likely to yield invalid pressure data. This capability is paramount in minimizing resource expenditure on unproductive tests, particularly in complex reservoir settings. The model provides a data-driven, consistent alternative to traditional, often subjective, FPT planning, underscoring the value of ML in derisking and streamlining critical field operations. Collectively, these contributions signal a mature phase in the application of ML within the oil and gas sector. No longer confined to academic exploration, these techniques are providing robust, field-deployable solutions that enhance subsurface interpretation, improve operational foresight, and potentially drive economic benefits. The continued success of such endeavors will undoubtedly rely on the synergistic fusion of domain expertise, high-quality data, and the ever-evolving sophistication of ML algorithms. Summarized Papers in This August 2025 Issue SPE 222299 - Machine Learning Unlocks Potential of Mud Logs, LWD in the Gulf of Thailand by Sethawut Palviriyachote, Texas A&M University, et al. OTC 35892 - Machine-Learning Approach Optimizes Formation-Pressure Testing in Complex Reservoirs by Ahmed K. Khassaf, Basrah University of Oil and Gas, et al. SPE 224365 - Physics-Informed Machine Learning Enhances Permeability Prediction in Carbonate Reservoirs by Mohammad K. Aljishi, University of Oklahoma, et al. Recommended Additional Reading at OnePetro: www.onepetro.org. SPE 224566 - Applying Machine Learning in Highly Laminated Formation To Differentiate Pay and Nonpay Zones and Resolve Rt for Fit-for-Purpose Azimuthal Resistivity Tool Selection by Armando Vianna, Baker Hughes SPE 223396 - Early Signs of Gas Recognition Based on Machine-Learning Analysis of Passive Acoustics by Y. Maslennikova, TGT Diagnostics, et al.

The difficulty of accurately predicting abnormally high-pressure formation pressure is one of the critical challenges in the field of petroleum engineering. Due to the low accuracy of formation pressure prediction and the narrow drilling safety density window, accidents such as leakage and blowout occur frequently. To address this issue, improving the accuracy of pore pressure predictions is essential. The well logging and mud logging data were combined to analyze the correlation between various parameters. Analysis using the Spearman correlation coefficient revealed that pore pressure exhibits varying correlation relationships with different parameters. Pore pressure is closely related to factors such as depth, weight of hanging, and mud weight. Pore pressure has a medium to high correlation with the rate of penetration, weight on bit, torque, slurry pump pressure, acoustic time difference, density, and volume of clay. Pore pressure has a medium to low correlation with the rotation per minute. Based on machine learning algorithms and a large amount of known data, a machine learning formation pressure model with integrated well logging and mud logging data (IWM) was established. The prediction results of traditional models and IWM models were compared using neighboring wells as the prediction targets. The results indicate that the backpropagation neural network model based on a genetic algorithm and IWM (IWM-GABP) achieves the highest prediction accuracy, with an average prediction accuracy greater than 96%. When predicting formation pressure, it is advisable to use the back propagation neural network model based on IWM or the IWM-GABP model, rather than the radial basis function neural network model based on IWM. The IWM model significantly reduces the prediction error of formation pore pressure, achieving an average improvement of 8.32% enhancement in prediction accuracy compared to traditional data models. The research method effectively improves the accuracy of formation pressure prediction and provides support for efficient on-site development.

Pemboran merupakan kegiatan yang memiliki tingkat resiko dan biaya yang tinggi dimana dibutuhkan perencanaan yang matang untuk memperoleh keberhasilan pada kegiatan ini. Salah satu hal yang paling penting dalam kegiatan pemboran ini adalah penentuan tekanan pori yang menjadi fundamental mencegah terjadi nya masalah dalam pemboran seperti underpressure & overpressure yang mana sangat vital dalam mempengaruhi keselamatan dan efisiensi operasi pengeboran. Penelitian ini bertujuan untuk mengetahui pada kedalaman berapa overpressure dan underpresure terjadi dengan menggunakan data wireline log, data tes tekanan, data mud log dan final well report. Metode Eaton digunakan untuk menentukan nilai tekanan pori dengan menggunakan data wireline logging seperti data log sonik, densitas dan resistivitas. Berdasarkan hasil penelitian ini didapati peningkatan nilai tekanan pori yang lebih besar dari tekanan normal hidrostatis pada kedalaman 1580, 8 m – 1740,4 m dan 2097 m – 2605 m yang diakibatkan oleh formasi yang didominasi oleh batuan lempung yang bersifat impermeable sehingga meningkatkan tekanan pori bawah permukaan atau disebut juga sebagai overpressure. Selain itu terjadi penurunan nilai tekanan pori yang lebih kecil dari tekanan normal hidrostatis pada kedalaman 1778,4 – 2052 m yang diindikasikan sebagai underpressure. Penyebab hal ini diakibatkan oleh formasi yag didominasi oleh batuan lempung dan pengaruh salinitas dan perubahan dari flow regime akibat pengaruh tektonik.

China is rich in coalbed methane (CBM) resources, and the key to realizing the scale and efficiency of CBM development is to build “engineering tools” for exploration and development continuously. Accurate calculation of rock components and precise identification of lithology and macroscopic coal lithotypes of coal-bearing measures are the basis for the evaluation of CBM geological engineering. This paper proposes a method to identify the lithology and macroscopic coal lithotypes of coal-bearing measures based on elemental mud logging. Firstly, a coal seam demarcation line is constructed based on the elemental mud logging to divide the coal and non-coal seams. Secondly, the content of each component in the coal and non-coal seams is calculated. Finally, based on the results of the calculations, a method for recognizing the lithology of non-coal seams and macroscopic coal lithotypes of coal seams is constructed based on the combination of the S (sulfur) element innovatively. The calculation error of mineral and proximate analysis components is less than 10%, and the average accuracy of lithology and macroscopic coal lithotype identification is as high as 87%. The results can provide important technical guidance for the geological evaluation of coal-bearing measures and the selection of target seams.

Well logging data can be used to determine lithology and for stratigraphic divi-sion and correlation. Well logging technology primarily utilizes the geological and physical properties of rock formations, such as electrical conductivity, elec-trochemical properties, acoustic properties, and radioactivity, to measure their parameters. Spontaneous potential logging utilizes changes in the spontaneous potential curve to classify lithology; natural gamma logging employs gamma curves for lithology classification and stratigraphic correlation to determine shale content; density logging can accurately calculate porosity and distinguish the nature of various fluids in the reservoir; and acoustic logging can be used to delineate the boundary between sandstone and mudstone and to identify gas zones. Essentially, various well logging methods can only indirectly and condi-tionally reflect certain aspects of the geological characteristics of rock for-mations. To accurately and comprehensively understand the subsurface geolog-ical features and to discover and evaluate hydrocarbon reservoirs, it is neces-sary to combine multiple well logging methods and pay attention to drilling, mud logging, and other data. Utilizing well logging curve data not only allows for accurate stratigraphic lithology classification but also more vividly repre-sents the depositional environment. By analyzing the shape of the well logging curves and various logging values, it is possible to determine the geometric morphology, lithology, lithofacies, sedimentary structures, ancient water flow and transport directions, and geochemical characteristics of the depositional facies.

The drilling fluid cooling system is a key technology for reducing wellbore temperatures, improving the working environment of downhole equipment, and ensuring safe and efficient drilling in high-temperature wells. Based on the existing drilling fluid cooling system, this article designs and develops a closed drilling fluid cooling system according to the working environment and cooling requirements of the GH-02 dry hot rock trial production well in the Gonghe Basin, Qinghai Province. The system mainly includes a cascade cooling module, a convective heat exchange module, and a monitoring and control module. Based on the formation conditions and drilling design of the GH-02 well, a transient temperature prediction model for wellbore circulation is established to provide a basis for the design of the cooling system. Under the conditions of a drilling fluid displacement of 30 L/s and a bottomhole circulation temperature not exceeding 105 °C, the maximum allowable inlet temperature of the drilling fluid is 55.6 °C, and the outlet temperature of the drilling fluid is 69.2 °C. The heat exchange of the drilling fluid circulation is not less than 1785 kW. Considering the heat transfer efficiency and reserve coefficient, the heat transfer area of the spiral plate heat exchanger calculated using the average temperature difference method is not less than 75 m2. By applying this drilling fluid cooling system in the 3055 m~4013 m section of well GH-02, the inlet temperature is controlled at 45 °C~55 °C, and the measured bottomhole circulation temperature remains below 105 °C. After adopting the drilling fluid cooling system, the performance of the drilling fluid is stable during the drilling process, downhole tools such as the drill bits, screws, and MWD work normally, and the failure rate of the mud pump and logging instruments is significantly reduced. The drilling fluid cooling system effectively maintains the safe and efficient operation of the drilling system, which has been promoted and applied in shale oil wells in Dagang Oilfield.

Real-time identification of fluid characterization is important to execute and/or modify the proposed well program and provide a better understanding of the application of gas ratio analysis. In this study, reservoir fluids were characterized during drilling by analyzing light gases released as a result of formation rocks being penetrated. Drilling mud is used to carry reservoir gas during this process. The required data included the values of liberated gas molecules from the main reservoir section extracted by gas chromatograph (GC) during drilling, that data was collected from five wells (A, B, C, D, and E) in the X oilfield. The gas measurements included the gases from Methane (C1) to Pentane (C5) measured in real-time by the gas chromatograph in the mudlogging units. The ratios of C1-C5 gases were used to determine the values of wetness ratio (Wh), and hydrocarbon balance (Bh) in the 3rd and 4th pay reservoirs. Results showed good indications of fluid type compared to the actual well test and were capable of distinguishing between heavy and light hydrocarbons in the reservoir section. A joint interpretation of electric logs and mudlogging gas data leads to an enhanced understanding of well results, which in turn can be used to optimize future logging and well testing.

Valid projection of Well productivity is essential for carrying out appropriate criteria and to avoid increasing the cost of exploration and development. A combination of various reservoir evaluation procedures can be beneficial to estimate Well productivity according to different data, including seismic, mud logging, well logging, well-testing, formation test data, etc. In this study, the productivity index was extracted based on well logging and well-testing by Interactive Petrophysics and Saphir™ to comprehend reservoir productivity behavior and be a valuable guide for planning future drilling processes. The results indicated that the correlation between the J-predicted and productivity index (PI) results from the well-logs interpretation is power law in the northern part of the field and linear in the south. The average porosity values in the southern part of the Buzurgan field are lower than in the north and the average water saturation and permeability in the south are slightly higher than in the north. On the other hand, the Multiple Linear Regression (MLR) analysis for PI identifier and PI by well-logging and Well-testing shows that the southern part of the field has a better PI than the north. The MB21 was the best unit in the Mishrif reservoir in the field. Likewise, the oil reserve in the south of the field is higher than in the north due to the Net-to-Gross and bulk volume results, especially in zone 5, representing the MB21 unit. In addition, the water saturation model shows that the oil–water contact (OWC) is at a depth of − 3877 m in the south part and 3885 m in the north. By examining the Well performance using the Ecrin program, the Productivity Index of layer MB21 is equal to 6.3 in the south and 5.9 in the north. Finally, the volume of the Oil initially in place (STOIIP) for the Mishrif Formation is estimated to be approximately 4138.7 million barrels.

The Tarakan Basin is one of the basins that has been producing hydrocarbons since 1901, with nine active oil fields to this day. The exploration of oil and gas in the Tarakan Basin has been ongoing for a considerable amount of time and can be considered as the oldest exploration in Indonesia that continues due to its estimated economically viable reserves based on its geological conditions. Research on the evaluation of reservoir characteristics in the Tarakan Sub-Basin with a Pliocene age interval aims to determine the subsurface lithology and fluid conditions qualitatively and the quantitative characteristics of the reservoir rocks. This study utilizes quantitative petrophysical analysis using a deterministic method with primary data consisting of wireline log data, as well as secondary data including core data, mud logs, biostratigraphy data, drill stem test data, and sidewall core data. Based on the analysis results, the petrophysical properties of the target reservoir in the study area include an average shale volume (VSH) of 16.65% - 29.31%, average effective porosity (PHIE) of 11.80% - 27.09%, which falls into the categories of fair to excellent quality, hydrocarbon saturation ranging from 7.68% - 43.03%, an average permeability value (PERM) of 10.03 mD - 613.29 mD, falling into the categories of good to very good, and a net pay thickness ranging from 4 feet to 16.7 feet, with a total thickness of 67.4 feet containing oil and gas fluids.

Measurement from open-hole well logging has been a significant variability in the oil and gas business as it offers mud logging and measurement while drilling in conventional and wireline logs. Measurement is the base in formation evaluation, proving to be crucial information in applications from simple assessment of individual drilling wells to more general reservoir characterization. Improvements that the open-hole well-logging technology has experienced over time have overruled the challenges related to the accuracy or the efficiency demanded by the requirements of precise and reliable reservoir evaluation. Some of the significant technological progress resulted in better capabilities for measuring the key properties of a reservoir and, thereby, offering scopes for even better decisions about exploration and production. It depicts several examples of such development that describe their real-world application in a holistic view of the modern technological landscape. This paper also reveals ideas about what trends are surfacing and shaping open-hole wells, logging into a future that will see them become a constant process within the industry of continuous change and innovation in methods used to evaluate the subsurface.

Heterogeneous multi-task learning approach for rock strength prediction in real-time during drilling based on mud log data

Abstract In the implementation process of traditional horizontal wells, the degree of data sharing and collaboration among multiple specialties such as drilling, directional drilling, and mud logging are low, which cannot fully meet the construction needs of horizontal wells under complex conditions, resulting in low reservoir penetration rate and long drilling cycles of horizontal wells. Accordingly, An integrated geology & engineering mud logging geo-steering mode is constructed consisting of “geo-steering+directional drilling+drilling risk assessment+mud logging technology+remote informatization”, With geo-steering as the core, geological and engineering perspectives and comprehensive analysis have been taken into account, and intelligent analysis models have been developed to enhance analytical and decision-making capabilities. An integrated geology & engineering remote geo-steering platform has been developed to promote information sharing, intelligent analysis, and collaborative decision-making among different locations, times, and professionals. In the process of horizontal well construction, the application of this comprehensive geo-steering mode promotes the comprehensive application and analysis ability of downhole drilling data and mud logging data, with the principle of improving reservoir penetration rate, while considering the feasibility and safety of engineering trajectory, effectively reducing the construction risk of horizontal wells, and achieving the dual goals of geology and engineering. It provides strong technical support for improving the drilling efficiency and development effect of horizontal wells, and provides technical reference for the application of drilling technology in complex horizontal wells.

Real-time lithology identification from drilling data with self & cross attention model and wavelet transform

Abstract The M block in Algeria is located in the southern Sahara platform, with oil and gas reservoirs mainly composed of river-glacial marine facies, fluvial and shallow marine fine sandstones. The pore structure is complex, and the difference in resistivity logging between gas layers and water layers is not significant, resulting in difficulties in identifying and evaluating hydrocarbon zone and the occurrence of reservoir omission. Based on geological, mud logging, core experimental data, logging, formation water analysis and testing data together, the formation mechanism of low resistivity hydrocarbon zone and the response characteristics of logging curves were generalised. The research suggests that the main factors causing low resistivity in this area are strong heterogeneity, high formation water salinity, high shale content, etc. On this basis, in response to the difficulty of identifying low resistivity gas layers, three methods of assessment were constructed: resistivity reduction rate factor method, porosity curve differentiation technique method and double porosity overlap method, which can quickly identify low resistivity gas layers. The oil testing results have verified that this method significantly improves the interpretation accuracy, with a 17.2% increase in accuracy and good results. The test results show that the method can greatly improve the interpretation accuracy with current accuracy 89.1% and the method turns out to be effective. Based on the above methods, the distribution law of low resistivity oil and gas layers in the study area has been clarified, and favorable zones have been discovered, providing strong technical support for increasing reserves and production in the area.