Journal of Applied Geophysics最新文献

{"title":"RSA-Net: generalized weak signal recovery for DAS VSP data in complex noise environments","authors":"Yanwei Li,&nbsp;Yanan Tian,&nbsp;Yue Li,&nbsp;Ning Wu,&nbsp;Yuxing Zhao","doi":"10.1016/j.jappgeo.2025.105914","DOIUrl":"10.1016/j.jappgeo.2025.105914","url":null,"abstract":"<div><div>Distributed acoustic sensing (DAS) technology has emerged as a leading seismic acquisition system, renowned for its high precision and efficient data collection capabilities, which are crucial for exploring deeper and more complex geological structures. The conventional signal processing techniques and the existing denoising methods are insufficient for the purpose of suppressing the various types of noise that are present in complex and diverse noise environments. This ultimately hinders the effective recovery of weak signals. To overcome these challenges, we propose the Reinforced Sparse Attention Network (RSA-Net), a deep learning framework that employs a hierarchical encoder-decoder architecture with dedicated modules for the suppression of noise and the enhancement of weak signal recovery. The network incorporates the Selective Top-k Attention (STA) module, which enables the selective focus on relevant features, and the Adaptive Mixture of Experts (AME) module, which facilitates dynamic adaptation to diverse noise types. These enhancements collectively enhance the network's generalisation capabilities across varying noise conditions. Experiments were conducted using both synthetic and field DAS VSP records, complemented by visualisation experiments that demonstrated RSA-Net's capacity to generalise across a spectrum of noise types. The results of these experiments demonstrate that RSA-Net outperforms conventional and current network-based methodologies and confirms that RSA-Net is an effective method for suppressing noise and recovering weak signals in the presence of a wide range of noise types.</div></div>","PeriodicalId":54882,"journal":{"name":"Journal of Applied Geophysics","volume":"242 ","pages":"Article 105914"},"PeriodicalIF":2.1,"publicationDate":"2025-08-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144906890","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Experimental velocity anisotropy in crystalline basement rocks of the midcontinental USA","authors":"William M. Kibikas ,&nbsp;Ahmad Ghassemi ,&nbsp;Jacob I. Walter ,&nbsp;Brett M. Carpenter","doi":"10.1016/j.jappgeo.2025.105907","DOIUrl":"10.1016/j.jappgeo.2025.105907","url":null,"abstract":"<div><div>Determination of the in-situ stress orientations in the subsurface is key to understanding crustal behavior. For example, in Oklahoma and Kansas a surge in seismic activity occurred between 2010 and 2019 with the vast majority of hypocenters located in the crystalline basement. This prompted significant interest in characterizing the stress state in this region through indirect geophysical methods, such as shear-wave anisotropy, which is a technique used to identify the principal stress directions through identification of seismic anisotropy. The interpretation of apparent anisotropy from regional-scale seismic measurements can be somewhat limited due to assumptions regarding the physical mechanism for the observed S-wave velocity polarizations and the difficulty in separating the intrinsic anisotropy from other factors. In this work we have investigated the intrinsic velocity anisotropy of crystalline basement rocks from Oklahoma and Kansas using direct laboratory velocity measurement techniques. Two sets of tests were conducted to measure the horizontal and vertical velocities of each rock sample. Tests were conducted under hydrostatic conditions so that the intrinsic rock properties would be the dominant factor in the observed velocity anisotropy. Stereologic techniques were used to quantify the microstructural variation and relate it to both the laboratory and field observations. The results indicate that there is a non-trivial degree of velocity anisotropy in both the horizontal and vertical directions, varying for rocks from different locations. Microstructural observations of fractures show that horizontal fractures orientations dominate the samples, coinciding with the strike-slip regime of the region. However, velocity polarization and fracture orientations do not always align well. The results indicate a clear intrinsic anisotropy in the basement rocks of Oklahoma and Kansas and our work highlights the need for a suite of other measurements (i.e. borehole breakouts, stress inversion, or others) to aid in determining the stress orientations, aside from relying solely upon shear-wave polarization to determine subsurface relative stress orientations.</div></div>","PeriodicalId":54882,"journal":{"name":"Journal of Applied Geophysics","volume":"242 ","pages":"Article 105907"},"PeriodicalIF":2.1,"publicationDate":"2025-08-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144889257","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Self-potential signal analysis to recognize sources of primary anomaly in a landslide: a novel approach","authors":"Oziel Souza de Araújo ,&nbsp;Roberto G. Francese ,&nbsp;Stefano Picotti ,&nbsp;Federico Fischanger ,&nbsp;Antonio Bratus ,&nbsp;Massimo Giorgi","doi":"10.1016/j.jappgeo.2025.105912","DOIUrl":"10.1016/j.jappgeo.2025.105912","url":null,"abstract":"<div><div>Self-potential (SP) is a passive geophysical method highly sensitive to subsurface fluid flow, but its application has been traditionally limited by interpretation challenges and instrumentation constraints. In this study, we present a novel methodology for retrieving and processing SP signals during a 3D Electrical Resistivity Tomography (3D-ERT) survey over an active landslide in the Carnic Alps (Italy). Using a non-traditional sparse-gradient array and stainless-steel electrodes connected to new-generation FullWaver georesistivimeters, we demonstrate the feasibility of acquiring stable SP signals without non-polarizing electrodes. The SP data, recorded simultaneously across 23 autonomous units, were processed with custom MATLAB tools to produce time-lapse SP maps and identify groundwater flow patterns. The results highlight the presence of consistent SP anomalies, including “hat-shaped” features indicative of infiltration, and suggest the correlation of SP signals with geological structures and topography. We also applied the 2D Analytical Signal Amplitude (ASA) technique to delineate SP source zones. This approach enhances the utility of SP in landslide monitoring and hydrogeological investigations, particularly as a first-pass qualitative tool when quantitative instrumentation is unavailable. Our findings demonstrate the untapped potential of SP signals typically discarded in resistivity surveys.</div></div>","PeriodicalId":54882,"journal":{"name":"Journal of Applied Geophysics","volume":"242 ","pages":"Article 105912"},"PeriodicalIF":2.1,"publicationDate":"2025-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144903875","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Tracking and classifying objects with DAS data along railway","authors":"Simon Leander Berg Fredriksen ,&nbsp;The Tien Mai ,&nbsp;Kevin Growe ,&nbsp;Jo Eidsvik","doi":"10.1016/j.jappgeo.2025.105900","DOIUrl":"10.1016/j.jappgeo.2025.105900","url":null,"abstract":"<div><div>Using distributed acoustic sensing data from a day of field testing on a fiber-optic cable along a railroad track in Norway, we detect and track cars and trains moving along a segment of the cable where the road runs parallel to the railroad tracks. We develop a method for automatic detection of events using signal processing, thresholding and density-based clustering, and then put data picks into a Kalman filter variant known as joint probabilistic data association filter for multiple object tracking and classification. Statistical model parameters are specified using in-situ labeling data along with the fiber-optic signals. Running the algorithm over time, we automatically track about 100 cars and 20 trains per hour. The velocities of cars coming from a zone with higher speed limit tend to be larger (35 km/h) than that of cars going in the opposite direction (30 km/h).</div></div>","PeriodicalId":54882,"journal":{"name":"Journal of Applied Geophysics","volume":"242 ","pages":"Article 105900"},"PeriodicalIF":2.1,"publicationDate":"2025-08-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144866031","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Enhancing hydrocarbon prospect delineation through artificial intelligence driven integration of seismic attributes and inversion in ‘OS’ field, offshore, Niger Delta","authors":"Ayodele O. Falade ,&nbsp;Olubola Abiola ,&nbsp;John O. Amigun","doi":"10.1016/j.jappgeo.2025.105906","DOIUrl":"10.1016/j.jappgeo.2025.105906","url":null,"abstract":"<div><div>Several studies have employed multi-seismic attributes and seismic inversion to delineate potential hydrocarbon zones on a seismic scale. However, these methods often rely on individual attribute maps and their integration struggle to effectively harness the collective information embedded in their results, leading to hydrocarbon zones being bypassed. To improve precision and reduce uncertainty in integrating these methods, this study introduces an artificial intelligence-driven approach to incorporate results from seismic inversion and multi-attribute analysis for enhanced characterization of hydrocarbon prospects. Key seismic attributes, including instantaneous amplitude, amplitude envelope, and instantaneous frequency, known for their potential as direct hydrocarbon indicators, were employed. Also, post-stack seismic inversion was utilized to derive acoustic impedance, providing a quantitative measure of subsurface properties. To enhance the delineation of hydrocarbon prospects, a computer vision algorithm was designed and implemented using the OpenCV library in Python on the attribute maps to isolate zones corresponding to potential hydrocarbon zones based on their distinctive properties. This process isolated hydrocarbon-prospective zones within each attribute map. These enhanced zones were subsequently integrated using a computer vision algorithm designed to identify areas of overlap, indicating potential hydrocarbon prospects. The resulting integrated map yielded precise and accurate hydrocarbon prospect identification by ensuring alignment with the criteria defined by all employed attributes. The results precisely identify hydrocarbon-bearing zones by reducing uncertainty, demonstrating the effectiveness of integrating seismic attributes and inversion data using artificial intelligence. This innovative approach enhances hydrocarbon prospect evaluation by improving efficiency, accuracy, and precision in extracting and integrating critical information from seismic data. An offshore field (‘OS’) in the Niger Delta Basin was used as the study area.</div></div>","PeriodicalId":54882,"journal":{"name":"Journal of Applied Geophysics","volume":"242 ","pages":"Article 105906"},"PeriodicalIF":2.1,"publicationDate":"2025-08-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144887055","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Study on the multiparameter evolution law and precursors of microearthquakes during the collapse process of slopes with structural surfaces","authors":"Shuo Wang,&nbsp;Yuanhui Li,&nbsp;Shida Xu","doi":"10.1016/j.jappgeo.2025.105903","DOIUrl":"10.1016/j.jappgeo.2025.105903","url":null,"abstract":"<div><div>Under the influence of mining, the rock mass of a slope with a structural plane gradually deteriorates and is prone to collapse, which poses a threat to the safety of personnel and equipment. In this work, the spatial and temporal evolution of multiple microseismic parameters during the collapse of a slope with a structural surface is studied via field monitoring and numerical simulation, and the mining activities and the collapse precursor of the slope are analyzed. The results show that the daily microseismic event rate presents an unusually rapid increase before the slope collapses. The increase in the microseismic event rate 5 days before the collapse is 40 % greater than that 5 to 15 days before the collapse. The cumulative apparent volume increased 2 to 3 days before the collapse, whereas the energy index decreased. An aggregation index of microseismic events is proposed to characterize the density of microseismic events in a slope. The clustering index decreases significantly 2 to 3 days before collapse, and the minimum values are all less than 0.2, indicating that the density of microseismic events in the collapse area increases significantly before collapse. The time when the energy released by a microseismic day is greater than 10⁶ J accounts for 70.8 % of the total time and shows a sudden decreasing trend before the collapse. The numerical simulation revealed that the increase in displacement, stress, and shear strain in the study area suddenly increased 2 to 3 days before the collapse, and the slope rock mass in this area was in an unstable state. Therefore, 2 to 3 days before collapse, the daily microseismic event rate increased while the daily energy decreased, the cumulative apparent volume increased while the energy index suddenly decreased, and the aggregation index rapidly decreased. These three phenomena can be used as precursors of slope collapse. The research results can provide theoretical support for slope stability research and warning of collapse under similar conditions.</div></div>","PeriodicalId":54882,"journal":{"name":"Journal of Applied Geophysics","volume":"242 ","pages":"Article 105903"},"PeriodicalIF":2.1,"publicationDate":"2025-08-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144887056","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Lithology recognition and porosity prediction from well logs based on Convolutional Neural Networks and sliding window","authors":"Yunjuan Wang ,&nbsp;Xixin Wang ,&nbsp;Kaiyu Wang ,&nbsp;Ying Fu","doi":"10.1016/j.jappgeo.2025.105905","DOIUrl":"10.1016/j.jappgeo.2025.105905","url":null,"abstract":"<div><div>Predicting the lithology and porosity of borehole rocks based on wireline logging data holds significant importance. The sampling interval of the logs is relatively small, so the log values within a specific range above and below the target depth contain effective information about the borehole rock at the target depth. This paper proposes a method that combines a deep sliding window with a convolutional neural network. In this approach, multiple logging curves within the sliding window serve as inputs, and the convolutional neural network extracts valuable information from these logging curves. Subsequently, the borehole lithology and porosity at the window center are predicted based on the extracted information. As the window slides vertically, it enables the rapid prediction of lithology and porosity for the entire wellbore. Based on the practical application in an oil field in the east of China, it was determined that the optimal length of the sliding window is 1.125 m. The accuracy rate of the proposed convolutional network model for lithology prediction can exceed 94.4 %, and the accuracy rate for porosity prediction is 94.9 %. The prediction speed is notably fast, making it applicable with precision to lithology or porosity predictions in numerous oil fields and new wells.</div></div>","PeriodicalId":54882,"journal":{"name":"Journal of Applied Geophysics","volume":"242 ","pages":"Article 105905"},"PeriodicalIF":2.1,"publicationDate":"2025-08-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144866030","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Evaluating the performance of an optimized tree-ensemble learning algorithm for predicting sonic logs in the Gandhar CO2 EOR project","authors":"Saqib Zia ,&nbsp;Shubham Dabi ,&nbsp;Nimisha Vedanti","doi":"10.1016/j.jappgeo.2025.105904","DOIUrl":"10.1016/j.jappgeo.2025.105904","url":null,"abstract":"<div><div>Predicting unrecorded well-logs is essential for improving subsurface characterization, particularly for CO₂ storage in geological formations. This study presents a novel and optimized tree-ensemble learning algorithm for predicting compressional (P)-sonic logs in the Gandhar oilfield of India. Specifically, we developed a Gradient Boosting Regressor (GBR) by optimizing hyperparameters using a cross-validated grid search technique to enhance prediction accuracy and uncertainty quantification. Optimal input features (gamma-ray, neutron-porosity, resistivity, and density logs) were selected based on their significant correlation with the target (P-sonic log) measurements and their contribution to minimizing prediction error. The optimized GBR model was trained and tested on wells containing the optimal input features and the target measurements, and then applied to predict unrecorded P-sonic logs in three blind wells. Results showed that the algorithm predicted the overall trend and amplitude of the actual P-sonic log with high prediction accuracy and effectively captured lithological variations. Compared to the empirical methods, GBR demonstrated superior performance with lower mean absolute error and root mean square error. Prediction errors stabilized beyond 20,000 data points, suggesting further improvement depends on more representative lithological data. Prediction intervals highlighted lower uncertainty (higher model confidence) in zones with narrower intervals and abundant training data, particularly in the Hazad sands. Conversely, wider intervals reflected greater uncertainty in underrepresented lithological zones. Predicted logs were successfully utilized to model CO₂-saturated velocities in the Hazad sands. This approach provides a robust, scalable machine learning algorithm with optimized hyperparameters for enhanced well-log prediction and uncertainty quantification, supporting reliable, risk-informed reservoir characterization.</div></div>","PeriodicalId":54882,"journal":{"name":"Journal of Applied Geophysics","volume":"242 ","pages":"Article 105904"},"PeriodicalIF":2.1,"publicationDate":"2025-08-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144996580","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Data-driven lithofacies classification of marine shale based on deep learning approaches","authors":"Yufang Xue ,&nbsp;Bing Luo ,&nbsp;Yalin Chen ,&nbsp;Jun Qin ,&nbsp;Lanpu Chen ,&nbsp;Yuhao Yi","doi":"10.1016/j.jappgeo.2025.105902","DOIUrl":"10.1016/j.jappgeo.2025.105902","url":null,"abstract":"<div><div>Shale lithofacies control hydrocarbon generation potential, reservoir properties, and anisotropy, thereby determining the distribution of shale “sweet spots” and guiding the selection of horizontal well target windows. Consequently, predicting shale lithofacies is crucial for the detailed evaluation, efficient exploration, and development of shale reservoirs. However, predicting lithofacies within the Wujiaping Formation of the Permian in the Hongxing area, eastern Sichuan Basin, presents significant challenges due to complex mineral compositions and strong heterogeneity. In this study, we classified the shale and its interlayers within the reservoir into five lithofacies based on total organic carbon content and mineral assemblages, with MF4 identified as the favorable lithofacies. Additionally, six logging curves (GR, AC, DEN, CNL, CAL, and LLD) were selected as input features to train and test deep learning models for automatic lithofacies prediction. To investigate the applicability of deep learning models for lithofacies identifications using well logs, six models were employed, including CNN, CNN-LSTM, CNN-BiLSTM, CNN-GRU, CNN-BiGRU, and Transformer. Notably, the Transformer model outperformed the others, achieving an <span><math><mi>Accuracy</mi></math></span> of 0.8776 and <span><math><mi>Precision</mi></math></span> of 0.9152 in shale lithofacies identification. Specifically, for the favorable lithofacies MF4, the Transformer model yielded the highest prediction performance, with <span><math><mi>F</mi><mn>1</mn><mo>−</mo><mi>score</mi></math></span> of 0.89. This study demonstrates that deep learning models can effectively identify the shale lithofacies from conventional well logs, providing valuable technical insights for developing practical approaches to identify lithofacies.</div></div>","PeriodicalId":54882,"journal":{"name":"Journal of Applied Geophysics","volume":"242 ","pages":"Article 105902"},"PeriodicalIF":2.1,"publicationDate":"2025-08-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144828549","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Wave-equation surface waves dispersion inversion in vertical transverse isotropic media","authors":"Chengang Zhang,&nbsp;Jing Li,&nbsp;Hui Liu,&nbsp;Lige Bai,&nbsp;Ruizhe Sun,&nbsp;Chang Zhang","doi":"10.1016/j.jappgeo.2025.105899","DOIUrl":"10.1016/j.jappgeo.2025.105899","url":null,"abstract":"<div><div>The wave-equation dispersion inversion (WD) method is a robust approach for reconstructing the S-wave velocity structure, which does not require the assumption of layered media and is independent of source wavelets. However, theoretical analysis demonstrates that surface wave dispersion curves are sensitive to anisotropic parameters. Conventional WD is based on isotropic media, neglecting the anisotropic characteristics of the subsurface structure. To correct and evaluate the anisotropy effect, we present the theory for anisotropic Love wave-equation dispersion inversion (LWD) method based on the vertical transverse isotropic media (VTI-LWD). The synthetic and field data demonstrate that the proposed VTI-LWD significantly improves the accuracy of the S-wave velocity model while simultaneously estimating the anisotropic parameter. This provides more accurate multi-parameter information for near-surface stratigraphic structures.</div></div>","PeriodicalId":54882,"journal":{"name":"Journal of Applied Geophysics","volume":"242 ","pages":"Article 105899"},"PeriodicalIF":2.1,"publicationDate":"2025-08-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144828550","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}