Computers & Geosciences最新文献

{"title":"Shear wave velocity prediction based on bayesian-optimized multi-head attention mechanism and CNN-BiLSTM","authors":"Wenzhi Lan ,&nbsp;Yunhe Tao ,&nbsp;Bin Liang ,&nbsp;Rui Zhu ,&nbsp;Yazhai Wei ,&nbsp;Bo Shen","doi":"10.1016/j.cageo.2024.105787","DOIUrl":"10.1016/j.cageo.2024.105787","url":null,"abstract":"<div><div>Shear wave velocity (VS) is one of the fundamental geophysical parameters essential for pre-stack seismic inversion, rock mechanics evaluation, and in-situ stress assessment. However, due to the high cost of acquiring VS log data, it is impossible to carry out this logging project in all wells. Thus, it is extremely necessary to develop an efficient and reliable VS prediction method. Deep learning methods have distinct advantages in data inversion, but different neural network have their own characteristics. A single-structured neural network has inevitable limitations in VS prediction, making it challenging to effectively capture the nonlinear mapping relationships of multiple parameters. Therefore, an integrated VS prediction model was proposed based on analyzing the applicability of classical neural networks. This new model, denoted as Bo-MA-CNN-BiLSTM, combines a Bayesian-optimized and multi-head attention mechanism (Bo-MA) with a convolutional neural network (CNN) and a bidirectional long short-term memory network (BiLSTM). It can effectively capture spatio-temporal data reflecting geophysical characteristics from log data, and the integration of the multi-head attention mechanism enhances the rational allocation of weights for log data. Bayesian optimization is utilized to determine the values of hyperparameters, overcoming the subjectivity and empiricism associated with manual selection. Actual data processing demonstrates that the new model achieves higher accuracy in predicting VS than applying CNN, LSTM, BiLSTM, and CNN-LSTM individually. The application results of well log data not involved in training indicate that, compared to other classical models, this new model exhibits optimal evaluation metrics. Especially for strongly heterogeneous formations, the predicted results demonstrate significant superiority, verifying the generalization ability and robustness of the proposed model.</div></div>","PeriodicalId":55221,"journal":{"name":"Computers & Geosciences","volume":"195 ","pages":"Article 105787"},"PeriodicalIF":4.2,"publicationDate":"2024-11-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142747274","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":"Multivariate simulation using a locally varying coregionalization model","authors":"Álvaro I. Riquelme,&nbsp;Julian M. Ortiz","doi":"10.1016/j.cageo.2024.105781","DOIUrl":"10.1016/j.cageo.2024.105781","url":null,"abstract":"<div><div>Understanding the response of materials in downstream processes of mining operations relies heavily on proper multivariate spatial modeling of relevant properties of such materials. Ore recovery and the behavior of tailings and waste are examples where capturing the mineralogical composition is a key component: in the first case, to ensure reliable revenues, and in the second one, to avoid environmental risks involved in their disposal. However, multivariate spatial modeling can be difficult when variables exhibit intricate relationships, such as non-linear correlation, heteroscedastic behavior, or spatial trends. This work demonstrates that the complex multivariate behavior among variables can be reproduced by disaggregating the global non-linear behavior through the spatial domain and looking instead at the local correlations between Gaussianized variables. Local linear dependencies are first inferred from a local neighborhood and then interpolated through the domain using Riemannian geometry tools that allow us to handle correlation matrices and their spatial interpolation. By employing a non-stationary modification of the linear model of coregionalization, it is possible to independently simulate variables and then combine them as a linear mixture that locally varies according to the inferred correlation, reproducing the global multivariate behavior seen on input variables. A real case study is presented, showing the reproduction of the reference multivariate distributions, as well as direct and cross semi-variograms.</div></div>","PeriodicalId":55221,"journal":{"name":"Computers & Geosciences","volume":"195 ","pages":"Article 105781"},"PeriodicalIF":4.2,"publicationDate":"2024-11-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142722650","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":"Optimized AI-MPM: Application of PSO for tuning the hyperparameters of SVM and RF algorithms","authors":"Mehrdad Daviran ,&nbsp;Abbas Maghsoudi ,&nbsp;Reza Ghezelbash","doi":"10.1016/j.cageo.2024.105785","DOIUrl":"10.1016/j.cageo.2024.105785","url":null,"abstract":"<div><div>Modern computational techniques, particularly Support Vector Machines (SVM) and Random Forest (RF) models, are revolutionizing predictive mineral prospectivity mapping. These advanced systems excel at identifying prime resource locations but require meticulous fine-tuning of their internal settings to achieve peak performance. Careful calibration of these configurations during the learning phase significantly enhances their ability to detect promising deposits. The main goal of this study is to introduce a hybrid model called PSO -SVM and PSO-RF, which aim to combine particle swarm optimization (PSO) with SVM (with RBF kernel) and RF models. This hybrid model automatically adjusts the optimized hyperparameters of SVM and RF, resulting in highly accurate predictions and a wide range of applicability. The PSO algorithm has been applied to fine-tune two main parameters (<em>C</em> and <em>λ</em>) for SVM-RBF and three main parameters (<em>N</em>_<em>T</em>, <em>N</em>_<em>S</em>, and <em>d</em>) for RF, creating efficient models for both. The proposed hybrid model as well as the traditional versions of SVM and RF models, were tested using a geo-spatial dataset related to Cu mineralization in Kerman belt, SE Iran. Forecasting algorithms were developed by integrating diverse datasets: multi-element concentrations from stream samples, bedrock and fault line maps, indicators of hot fluid interaction, aeromagnetic survey results, coordinates of previously identified copper-rich igneous intrusions, and verified ore body positions as reference points. The models' performance was evaluated using four validation methods: Multi-round data partitioning (K-fold), error classification tables (confusion matrix), true-positive vs. false-positive graphical analysis ((ROC) curve), and P-A plot were used to assess algorithms and models performance. Tests revealed that the PSO-SVM surpassed all competitors. Impressively, this fine-tuned classifier identified prime target zones in merely one-seventh of the region (14%), yet these areas encompassed nearly all verified resource sites (97%).</div></div>","PeriodicalId":55221,"journal":{"name":"Computers & Geosciences","volume":"195 ","pages":"Article 105785"},"PeriodicalIF":4.2,"publicationDate":"2024-11-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142707103","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":"Automatic variogram calculation and modeling","authors":"Luis Davila Saavedra ,&nbsp;Clayton V. Deutsch","doi":"10.1016/j.cageo.2024.105774","DOIUrl":"10.1016/j.cageo.2024.105774","url":null,"abstract":"<div><div>The variogram is one of the most used tools in geostatistics. It represents a key step for the results of estimation and simulation. This paper presents a methodology of the experimental variogram points calculation and subsequent modeling, including some practical considerations. The proposed methodology infers the variogram parameters directly from the dataset to require minimum user input. Autovar is a program that implements the described methodology, giving an initial variogram model for disseminated and tabular deposits.</div></div>","PeriodicalId":55221,"journal":{"name":"Computers & Geosciences","volume":"195 ","pages":"Article 105774"},"PeriodicalIF":4.2,"publicationDate":"2024-11-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142707098","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":"SaltFormer: A hybrid CNN-Transformer network for automatic salt dome detection","authors":"Yang Li ,&nbsp;Suping Peng ,&nbsp;Dengke He","doi":"10.1016/j.cageo.2024.105772","DOIUrl":"10.1016/j.cageo.2024.105772","url":null,"abstract":"<div><div>Salt dome interpretation of seismic data is a crucial task in the exploration and development of oil and gas. Conventional techniques, such as multi-attribute analysis, are laborious, time-consuming, and susceptible to subjective biases in their results. To achieve a more automated and precise identification of salt dome, we developed a hybrid network for salt dome detection. In order to optimally exploit both local and global features, a hierarchical Vision Transformer is employed as an encoder for feature extraction. Concurrently, the concurrent spatial and channel squeeze &amp; excitation attention module is utilized to improve detection accuracy in the decoder. Furthermore, we leveraged the complementarity of information between multiple tasks to enhance the model’s generalization performance. Using the competition data from the Kaggle platform provided by TGS-NOPEC Geophysics Company, automatic segmentation of salt domes was completed with a detection accuracy of 85.20%. A series of experiments were conducted using state-of-the-art models and the SaltFormer model, which was found to have higher detection accuracy compared to other networks. Finally, the test conducted with seismic field data from the Netherlands offshore F3 block in the North Sea demonstrate that the novel method is highly effective in detecting salt domes in seismic data.</div></div>","PeriodicalId":55221,"journal":{"name":"Computers & Geosciences","volume":"195 ","pages":"Article 105772"},"PeriodicalIF":4.2,"publicationDate":"2024-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142707100","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":"MagTFs: A tool for estimating multiple magnetic transfer functions to constrain Earth’s electrical conductivity structure","authors":"Zhengyong Ren ,&nbsp;Zijun Zuo ,&nbsp;Hongbo Yao ,&nbsp;Chaojian Chen ,&nbsp;Linan Xu ,&nbsp;Jingtian Tang ,&nbsp;Keke Zhang","doi":"10.1016/j.cageo.2024.105769","DOIUrl":"10.1016/j.cageo.2024.105769","url":null,"abstract":"<div><div>Time-varying magnetic signals measured by geomagnetic observatories and satellites carry information about the Earth’s deep electrical conductivity structure and external current sources in the ionosphere and magnetosphere. Estimating magnetic transfer functions (TFs), which reflect the Earth’s internal conductivity structure, is a primary task in interpreting geomagnetic data from observatories and satellites. However, available TFs estimation tools either focus on a single source (ionosphere currents or magnetosphere currents) or are not publicly accessible. Therefore, we developed a flexible TFs estimation tool, named MagTFs, to achieve robust and precise estimation of magnetic TFs from the time series of magnetic field data acquired through land or satellite-based observations. This tool can handle magnetic data originating from time-varying currents in both the ionosphere and magnetosphere. We tested its performance on four kinds of data sets, and the good agreements with published results underscore the tool’s maturity and versatility in accurately estimating multi-source TFs. As a contribution to the scientific community, we have released MagTFs as an open-source tool, facilitating broader utilization and collaborative advancements.</div></div>","PeriodicalId":55221,"journal":{"name":"Computers & Geosciences","volume":"195 ","pages":"Article 105769"},"PeriodicalIF":4.2,"publicationDate":"2024-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142707101","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":"An identification for channel mislabel of strong motion records based on Siamese neural network","authors":"Baofeng Zhou ,&nbsp;Bo Liu ,&nbsp;Xiaomin Wang ,&nbsp;Yefei Ren ,&nbsp;Maosheng Gong","doi":"10.1016/j.cageo.2024.105780","DOIUrl":"10.1016/j.cageo.2024.105780","url":null,"abstract":"<div><div>Strong motion records are first-hand data for studying the seismic response of sites or engineering structures, and their objectivity is crucial for the credibility of the results in earthquake engineering and engineering seismology. However, domestic and international earthquake data may be mislabeled between horizontal and vertical channels. This issue is typically addressed by manually comparing the similarity between the three components of strong motion records, which is inherently subjective and inefficient in identification. To achieve the intelligent recognition of massive records, this study used 14,983 sets of ground motion records with significant differences between horizontal and vertical components from the NGA-West2 database. A Siamese neural network preliminarily distinguished the similarity between the acceleration waveform and the three components of the Fourier amplitude spectrum (FAS) of ground motion records. Combined with manual identification, an efficient and accurate method for identifying vertical components in ground motion records was proposed, and applied to verify the channel directions of the strong motion records in Strong Motion Network in China. It was found that 308 sets of records from 170 stations were suspected of mislabeling vertical and horizontal components. This advancement significantly enhances the objectivity of strong motion records. This proposed method holds potential for remote maintenance of strong motion stations, verifying the channels of strong motion instruments, and mitigating the negative impact of channel confusion on research results.</div></div>","PeriodicalId":55221,"journal":{"name":"Computers & Geosciences","volume":"195 ","pages":"Article 105780"},"PeriodicalIF":4.2,"publicationDate":"2024-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142707136","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":"ReUNet: Efficient deep learning for precise ore segmentation in mineral processing","authors":"Chanjuan Wang ,&nbsp;Huilan Luo ,&nbsp;Jiyuan Wang ,&nbsp;Daniel Groom","doi":"10.1016/j.cageo.2024.105773","DOIUrl":"10.1016/j.cageo.2024.105773","url":null,"abstract":"<div><div>Efficient ore segmentation plays a pivotal role in advancing mineral processing technologies. With the rise of computer vision, deep learning models like UNet have increasingly outperformed traditional methods in automatic segmentation tasks. Despite these advancements, the substantial computational demands of such models have hindered their widespread adoption in practical production environments. To overcome this limitation, we developed ReUNet, a lightweight and efficient model tailored for mineral image segmentation. ReUNet optimizes computational efficiency by selectively focusing on critical spatial and channel information, boasting only 1.7 million parameters and 24.88 GFLOPS. It delivers superior segmentation performance across three public datasets (CuV1, FeMV1, and Pellets) and achieves the most accurate average particle size estimation, closely matching the true values. Our findings underscore ReUNet’s potential as a highly effective tool for mineral image analysis, offering both precision and efficiency in processing mineral images.</div></div>","PeriodicalId":55221,"journal":{"name":"Computers & Geosciences","volume":"195 ","pages":"Article 105773"},"PeriodicalIF":4.2,"publicationDate":"2024-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142707099","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":"Spectral whitening based seismic data preprocessing technique to improve the quality of surface wave's velocity spectra","authors":"Tarun Naskar ,&nbsp;Mrinal Bhaumik ,&nbsp;Sayan Mukherjee ,&nbsp;Sai Vivek Adari","doi":"10.1016/j.cageo.2024.105784","DOIUrl":"10.1016/j.cageo.2024.105784","url":null,"abstract":"<div><div>A high-quality surface wave velocity spectrum, also known as a dispersion image, is paramount for any MASW survey to accurately predict subsurface earth properties. The presence of diversified noise during field acquisition and dissimilar attenuation due to mechanical and radial damping makes it challenging for any wavefield transformation technique to produce a detailed and precise velocity spectrum. Standard surface wave data preprocessing techniques, such as trace normalization and bandpass filtering, along with postprocessing techniques like frequency-wise amplitude normalization, fail to address all these issues appropriately. In this paper, we present a spectral whitening-based data preprocessing technique that can adequately eradicate most of the shortcomings associated with different wavefield transformation techniques. Instead of normalizing each trace, it normalizes the amplitude of every frequency present in the seismogram. The spectral whitening can regain the relative amplitude losses due to both radial and mechanical damping, thus improving the signal-to-noise ratio. Along with diversified field data including Love and Rayleigh wave surveys, a synthetic dataset is used to demonstrate the efficacy of the proposed technique. Furthermore, field noise is added to random traces to test the ability of the proposed technique to filter asymmetric noise. Overall, the spectral whitening procedure significantly improves the quality of the velocity spectrum and produces a sharper dispersion image with well-separated modes. The work presented here enhances our ability to interpret surface wave velocity spectra precisely and helps explore accurate properties of the subsurface earth. It can help avoid the need for repeated field tests in cases of extremely noisy data, thereby significantly reducing costs and saving time.</div></div>","PeriodicalId":55221,"journal":{"name":"Computers & Geosciences","volume":"195 ","pages":"Article 105784"},"PeriodicalIF":4.2,"publicationDate":"2024-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142707092","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":"Heterogeneous layer effects on mining-induced dynamic ruptures","authors":"Yatao Li","doi":"10.1016/j.cageo.2024.105776","DOIUrl":"10.1016/j.cageo.2024.105776","url":null,"abstract":"<div><div>The risk of dynamic disasters increases with the trend toward deeper mining, highlighting an urgent need to better understand induced seismicity. To address this need, we developed custom code to implement the open-source software PyLith in the study of induced seismicity for the first time. We examined the effects of heterogeneous geological conditions on dynamic ruptures induced by deep mining operations. Our focus was on the dynamic ruptures and their effects on the nearby working face, analyzing parameters such as peak slip rates and rupture velocities. Our results show that rupture duration ranges from 255 ms to 676 ms and peak slip rates vary between 1.3 m/s and 5.0 m/s, with rupture velocities decreasing from 1.29 km/s to 0.17 km/s as the critical slip distance (<em>D</em>_c) increases. The relationship between peak slip rate and rupture velocity is consistent with Bizzarri's (2012) findings. A linear relationship between the times of peak slip rate (T_pv) and breakdown time (T_b) was observed, with a ratio of 1.0. In examining the induced seismic waves at the working face, we found that heterogeneous models exhibited more irregular slip distributions and higher peak particle acceleration (PPA) and peak particle velocity (PPV) compared to homogeneous models, indicating amplified seismic responses due to material heterogeneity. The study also identified potential risks to the working face's structural integrity, with more pronounced effects observed in hanging wall mining compared to footwall mining. These findings underscore the importance of considering geological heterogeneity in seismic hazard assessments and support the development of more accurate predictive models for mining-induced seismic events. It is important to note that our comparison of heterogeneous and homogeneous modeling is based on the assumption of identical initial traction, focusing on the effects of heterogeneous layers.</div></div>","PeriodicalId":55221,"journal":{"name":"Computers & Geosciences","volume":"195 ","pages":"Article 105776"},"PeriodicalIF":4.2,"publicationDate":"2024-11-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142707137","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}