{"title":"A first arrival picking method of microseismic signals based on semi-supervised learning using FreeMatch and MS-Picking","authors":"Guanqun Sheng , Zhuka Zhang , Xingong Tang , Kai Xie","doi":"10.1016/j.cageo.2024.105844","DOIUrl":"10.1016/j.cageo.2024.105844","url":null,"abstract":"<div><div>The small magnitude and low signal-to-noise ratio (SNR) of these signals make picking the arrivals challenging. Recent advancements in deep learning-based methods for picking the first arrivals of microseismic signals have effectively addressed traditional methods' inefficiency and inaccuracy problems. However, these methods often require a large amount of training data, and the substantial size and labeling effort significantly hinder further development of deep learning-based first-arrival picking methods. In recent years, semi-supervised methods have dealt with the small-sample problem. This approach establishes a semi-supervised learning framework, automatically labeling microseismic signals after sample augmentation, which can significantly reduce the time required for sample labeling. Still, in the microseismic domain, microseismic data face issues of low SNR and poor quality of pseudo-labels, which affects the performance of semi-supervised learning methods. Therefore, this study proposes a semi-supervised method that uses FreeMatch and MS-Picking, called Semi-MS-Picking, to improve the accuracy and efficiency of microseismic arrival picking under small sample labeling conditions. The first-arrival picking experiments are conducted under low-SNR conditions using synthetic signals and real microseismic records. The experimental results showed that the proposed Semi-MS-Picking method can outperform the FixMatch, Π Model, Pseudo Label, and AdaMatch methods, achieving a picking accuracy of 73% TOP-1 accuracy, while the other semi-supervised methods do not exceed the 50% TOP-1 accuracy. The proposed method can surpass typical deep learning-based first-arrival picking methods for microseismic signals, demonstrating good performance in intelligent microseismic data processing.</div></div>","PeriodicalId":55221,"journal":{"name":"Computers & Geosciences","volume":"196 ","pages":"Article 105844"},"PeriodicalIF":4.2,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143093105","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Neural operator-based proxy for reservoir simulations considering varying well settings, locations, and permeability fields","authors":"Daniel Badawi, Eduardo Gildin","doi":"10.1016/j.cageo.2024.105826","DOIUrl":"10.1016/j.cageo.2024.105826","url":null,"abstract":"<div><div>Simulating Darcy flows in porous media is fundamental to understand the future flow behavior of fluids in hydrocarbon and carbon storage reservoirs. Geological models of reservoirs are often associated with high uncertainly leading to many numerical simulations for history matching and production optimization. Machine learning models trained with simulation data can provide a faster alternative to traditional simulators. In this paper we present a single Fourier Neural Operator (FNO) surrogate that outperforms traditional reservoir simulators by the ability to predict pressures and saturations on varying permeability fields, well locations, well controls, and well count. The mean relative error of pressure and saturation predictions is less than 1%. This is achieved by employing a simple yet very effective data augmentation technique that reduces the simulation training dataset size by 75% and reduces overfitting. Also, constructing the input tensor in a binary fashion enables predictions on unseen well locations, well controls, and well count.</div></div>","PeriodicalId":55221,"journal":{"name":"Computers & Geosciences","volume":"196 ","pages":"Article 105826"},"PeriodicalIF":4.2,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143093108","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Kevin Buchin , Maike Buchin , Joachim Gudmundsson , Jorren Hendriks , Erfan Hosseini Sereshgi , Rodrigo I. Silveira , Jorrick Sleijster , Frank Staals , Carola Wenk
{"title":"Roadster: Improved algorithms for subtrajectory clustering and map construction","authors":"Kevin Buchin , Maike Buchin , Joachim Gudmundsson , Jorren Hendriks , Erfan Hosseini Sereshgi , Rodrigo I. Silveira , Jorrick Sleijster , Frank Staals , Carola Wenk","doi":"10.1016/j.cageo.2024.105845","DOIUrl":"10.1016/j.cageo.2024.105845","url":null,"abstract":"<div><div>The challenge of map construction involves creating a representation of a travel network using data from the paths traveled by entities within the network. Although numerous algorithms for constructing maps can effectively piece together the overall layout of a network, accurately capturing smaller details like the positions of intersections and turns tends to be more difficult. This difficulty is especially pronounced when the data is noisy or collected at irregular intervals. In this paper we present <span>Roadster</span>, a map construction system that combines efficient cluster computation and a sophisticated method to construct a map from a set of such clusters. First, edges are extracted by producing a number of subtrajectory clusters, of varying widths, which naturally correspond to paths in the network. Second, representative paths are extracted from the candidate clusters. The geometry of each representative path is improved in a process involving several stages, that leads to map edges. The rich information obtained from the clustering process is also used to compute map vertices, and to finally connect them using map edges. An experimental evaluation of <span>Roadster</span>, using vehicle and hiking GPS data, shows that the system can produce maps of higher quality than previous methods.</div></div>","PeriodicalId":55221,"journal":{"name":"Computers & Geosciences","volume":"196 ","pages":"Article 105845"},"PeriodicalIF":4.2,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143093690","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"A novel algorithm and software for 3D density gravity inversion","authors":"Wenjin Chen , Xiaolong Tan , Yang Liu","doi":"10.1016/j.cageo.2024.105839","DOIUrl":"10.1016/j.cageo.2024.105839","url":null,"abstract":"<div><div>In this study, we present a novel algorithm for three-dimensional density gravity inversion in the spectral domain. By applying the Fast Fourier Transform (FFT) to the observation equation and introducing an auxiliary function, we establish a general functional relationship between gravity anomalies and density. To address the ill-posed nature of the three-dimensional density inversion problem, we propose a new auxiliary function with two multiplicative factors: one to adjust density variation with depth and another to reflect the solution characteristics. Additionally, we have developed a user-friendly software interface using the scientific computing language Matlab. Both synthetic and field data are used to validate the proposed algorithm and software. Noise tests are conducted to demonstrate the efficacy and robustness of the proposed method. A comparative analysis with the smoothing and focusing methods is also performed. The results show that the proposed method outperforms the smoothing method and achieves higher resolution, although it is smoother than the focusing inversion results. Furthermore, we compare the computational times of the three methods, and the results indicate that the proposed method is the most efficient.</div></div>","PeriodicalId":55221,"journal":{"name":"Computers & Geosciences","volume":"196 ","pages":"Article 105839"},"PeriodicalIF":4.2,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143093818","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Shanghua Zhang, Hang Wang, Lele Zhang, Xiangyun Hu
{"title":"Seismic random noise suppression by structure-oriented BM3D","authors":"Shanghua Zhang, Hang Wang, Lele Zhang, Xiangyun Hu","doi":"10.1016/j.cageo.2025.105859","DOIUrl":"10.1016/j.cageo.2025.105859","url":null,"abstract":"<div><div>Random noise affects the precision of seismic imaging and interpretation, thus denoising is a significant step in data processing. Block matching and 3D collaborative filtering (BM3D) is an effective block-based noise suppression algorithm. However, when it is applied to the data with complex structures, the similarity between data blocks will decrease significantly, thereby damaging some structural details and leading to energy leakage. To address this issue, we propose a structure-oriented BM3D (SBM3D) denoising method. Initially, plane wave destruction (PWD) is employed to estimate the local slope of the seismic data. Using the obtained slope information, the events are flattened, significantly enhancing the similarity between data blocks. To minimize the flattening error, segmented flattening of the data is performed. Subsequently, BM3D is applied to the flattened data for denoising. Finally, the events are restored to their original shape through inverse flattening to obtain the ultimate denoised result. Through this method, the leaking signal energy from removed noise can be reduced. In addition, we adopt a parallel computing method to improve the computational efficiency. Synthetic and field data testing results show that this improved method can effectively reduce signal damage while ensuring the denoising effect.</div></div>","PeriodicalId":55221,"journal":{"name":"Computers & Geosciences","volume":"196 ","pages":"Article 105859"},"PeriodicalIF":4.2,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143093828","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Eccentricity curve estimation from geological data using sinusoidal modeling","authors":"Miroslav Zivanovic , Matthias Sinnesael","doi":"10.1016/j.cageo.2025.105866","DOIUrl":"10.1016/j.cageo.2025.105866","url":null,"abstract":"<div><div>The estimation of eccentricity curves from geological data is important as it can be used as a basis for the construction of geological timescales, or making inferences of past orbital evolutions of the Solar System. Such estimation can be challenging for multiple reasons like age-depth distortions, non-linear responses to insolation and various other sources of perturbation. We present a novel approach to estimating the eccentricity waveform from geological time series by targeted modifications to the Astronomical Component Estimation model (ACEv.1). We show that analyzing individual precession components is highly beneficial in understanding the impact of perturbation on the estimator. It turns out that individual precession components are fairly stationary in noise-free environments. Although the presence of perturbation modifies the morphology of the corresponding waveforms, the root-mean-square of individual waveforms remains approximately unchanged. This finding allows for a simple adjustment of individual precession components, that renders them almost noise-free. Such an approach provides a high-fidelity precession waveform, from which we can estimate the eccentricity. Furthermore, we provide a benchmark study on both synthetic and real geological data, which assess the performance of the proposed method against three state-of-the-art methods from the literature. The modified ACEv.1 model – here named ACEv.2 – outperforms the reference methods in terms of goodness-of-fit to the known eccentricity solutions in the case of a known age-depth model and precession frequencies. Cyclostratigraphic studies often lack comparisons to other methods; therefore, we believe this study could enhance users' understanding of how the reference methods handle perturbations in geological signals.</div></div>","PeriodicalId":55221,"journal":{"name":"Computers & Geosciences","volume":"196 ","pages":"Article 105866"},"PeriodicalIF":4.2,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143093830","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Dual-scattering elastic least-squares reverse time migration","authors":"Mingqian Wang , Huixing Zhang , Bingshou He","doi":"10.1016/j.cageo.2025.105854","DOIUrl":"10.1016/j.cageo.2025.105854","url":null,"abstract":"<div><div>Elastic least-squares reverse time migration (ELSRTM) can enhance imaging resolution and interpret multicomponent seismic data. However, traditional ELSRTM only considers primary scattered waves and cannot accommodate secondary scattered waves in the observed records. This limitation leads to inadequate imaging of steeply dipping and complex structures, where secondary scattered waves are present. To address this issue, we propose dual-scattering elastic least-squares reverse time migration (DS-ELSRTM). We construct the objective function of DS-ELSRTM under the second-order Born approximation and derive its gradient, forming a corresponding computational algorithm and implementation steps. Additionally, we introduce improved DS-ELSRTM strategies to address the weak amplitude matching of secondary scattered waves and the non-stationary gradient issue that arises during the nonlinear process of DS-ELSRTM. By comparing the imaging results of DS-ELSRTM and conventional ELSRTM in numerical experiments with the vertical fault model and Marmousi model, it is demonstrated that the DS-ELSRTM method has advantages in imaging steeply dipping structures and complex geological structures. DS-ELSRTM can produce higher-precision images than conventional ELSRTM.</div></div>","PeriodicalId":55221,"journal":{"name":"Computers & Geosciences","volume":"196 ","pages":"Article 105854"},"PeriodicalIF":4.2,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143093100","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Fu Zuo , Xinmin Ge , Lanchang Xing , Bohan Wu , Yiren Fan , Jackson Jervis Junior , Bin Wang
{"title":"An improved method to accelerate the acquisition efficiency of the T1-T2 spectrum based on the IR-BSSFP-CPMG pulse sequence∗","authors":"Fu Zuo , Xinmin Ge , Lanchang Xing , Bohan Wu , Yiren Fan , Jackson Jervis Junior , Bin Wang","doi":"10.1016/j.cageo.2024.105792","DOIUrl":"10.1016/j.cageo.2024.105792","url":null,"abstract":"<div><div>The correlation map of the longitudinal relaxation time (T<sub>1</sub>) and the transverse relaxation time (T<sub>2</sub>) offers valuable information of different proton contributions and is served as a significant data for identifying, quantifying and characterizing complex relaxation components in unconventional reservoirs. However, the acquisition speed and spectral resolution for existing pulse sequences cannot be guaranteed simultaneously. We designed an improved pulse sequence which integrates the inversion recovery-balanced steady-state free precession (IR-BSSFP) sequence and the Carr-Purcell-Meiboom-Gill (CPMG) sequence, allowing for the measurement of two-dimensional T<sub>1</sub>-T<sub>2</sub> spectrums. The IR-BSSFP sequence adopts a low refocusing angle and reduced flip angle pulse transmission power, eliminating the need for complete polarization. Moreover, the parameters of the improved pulse sequence such as the value and the number of the flip angle, the repetition time are discussed by numerical simulations. The result showed that the new pulse sequence achieves high-precision measurement performance, and the T<sub>1</sub>-T<sub>2</sub> spectrum can be achieved within a few seconds.</div></div>","PeriodicalId":55221,"journal":{"name":"Computers & Geosciences","volume":"196 ","pages":"Article 105792"},"PeriodicalIF":4.2,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143093167","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Introducing PyFaultSlip: A free and open-source tool for the assessment of induced fault slip hazards from deep fluid injection","authors":"Sean G. Polun , Tandis S. Bidgoli","doi":"10.1016/j.cageo.2024.105813","DOIUrl":"10.1016/j.cageo.2024.105813","url":null,"abstract":"<div><div>Induced fault slip is a significant hazard incurred by deep fluid injection operations and is inferred to be the source of recent elevated seismicity in the U.S. midcontinent. Deep fluid injection is commonly used for disposal of wastewater associated with oil and gas development and other industrial activities, enhanced oil recovery (EOR), and carbon capture and storage (CCS). However, easy-to-use tools to investigate hazards associated with disposal are lacking. Here, we present <strong><em>pyFaultSlip</em></strong>, a modular, free, and open-source tool written in Python to assess the likelihood of induced fault slip, using both 2D and 3D mapped geometries. We adopt two different approaches to assessing fault slip tendency, a ‘deterministic’ model that does not consider input uncertainty, and a ‘probabilistic’ model that uses a Monte Carlo approach to assess uncertainty. We show examples using 2D and 3D fault data in Oklahoma and Kansas. This tool is geared towards providing straightforward results that can directly communicate the likelihood of induced slip occurring on specific faults to researchers, operators, regulators, and other stakeholders of deep fluid injection projects.</div></div>","PeriodicalId":55221,"journal":{"name":"Computers & Geosciences","volume":"196 ","pages":"Article 105813"},"PeriodicalIF":4.2,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143093169","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"ETASbootstrap 0.2.0: A flexible R package for computing bootstrap confidence intervals for parameters in the space–time epidemic-type aftershock sequence model, with four case studies","authors":"R. Peng , P. Dutilleul , C. Genest","doi":"10.1016/j.cageo.2024.105817","DOIUrl":"10.1016/j.cageo.2024.105817","url":null,"abstract":"<div><div>The space–time epidemic-type aftershock sequence (ETAS) model is a widely used tool for stochastic declustering of earthquake data catalogs and short-term aftershock forecasting. However, confidence intervals derived from asymptotic standard errors (ASEs) of parameter estimates based on maximum-likelihood theory can sometimes be misleading and it was recently suggested to use bootstrap confidence intervals instead (<span><span>Dutilleul et al., 2024</span></span>). The ETASbootstrap package was developed to facilitate the use of the bootstrap resampling procedure and its associated confidence intervals for a direct comparison with asymptotic ones. In this paper, the statistical underpinnings of the package are first presented, including the space–time ETAS model with its multiple parameters, the importance of edge effects, and the bootstrapping algorithm. Then, three earthquake data catalogs (Japan, Italy, Iran) are used as input to ETASbootstrap 0.2.0, which is more flexible regarding the shape of spatial windows than the original version. In all cases, a discrepancy was observed between bootstrap and asymptotic confidence intervals for some of the space–time ETAS model parameters. It was possible to relate this discrepancy to the presence of outliers and a resulting lack of normality, which compromised the asymptotic approximation of the variability of the maximum-likelihood estimates (ML estimates). The results suggest that the two types of confidence intervals should be used in practice, especially for earthquake data catalogs of moderate size.</div></div>","PeriodicalId":55221,"journal":{"name":"Computers & Geosciences","volume":"196 ","pages":"Article 105817"},"PeriodicalIF":4.2,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143093172","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}