Computers & Geosciences最新文献

{"title":"A novel algorithm and software for efficient global gravimetric forward modeling in the spherical coordinate system","authors":"Wenjin Chen ,&nbsp;Xiaoyu Tang ,&nbsp;Robert Tenzer","doi":"10.1016/j.cageo.2025.105985","DOIUrl":"10.1016/j.cageo.2025.105985","url":null,"abstract":"<div><div>We present a novel algorithm and complementary software for the global gravimetric forward modeling that accommodates masses with complex shapes and density distributions defined in the frame of spherical coordinates. Traditional gravimetric forward modeling techniques often face significant challenges when dealing with irregularly shaped bodies and complex density variations, leading to high computational costs and long processing times. To address these practical limitations, we introduce an innovative algorithm that divides the 3-D mass-density body into spherical concentric rings with equal intervals in the radial direction, while discretizing the latitudinal and longitudinal directions into a grid with equal intervals. After discretization, we assume that each spherical volumetric mass ring has a laterally varying density and constant upper and lower bounds. Based on this approach, the gravitational field at any point outside the Earth is evaluated as the sum of the gravitational contributions generated by each concentric ring. This discretization allows applying the Fast Fourier Transform (FFT) technique to drastically improve computational efficiency of the spherical harmonic analysis and synthesis. Numerical results are validated against corresponding solutions obtained using the tesseroid method in the spatial domain. The comparison of results reassures a high accuracy of proposed method, with relative differences between results obtained from both methods less than 1 % and 4 % for the gravitational attraction and gradient respectively, while significantly improving the numerical efficiency. When modelling the gravitational field quantities of very complex structures by means of their geometry and density distribution, such as the Earth's crustal density structure, the numerical efficiency improved several orders of magnitude.</div></div>","PeriodicalId":55221,"journal":{"name":"Computers & Geosciences","volume":"204 ","pages":"Article 105985"},"PeriodicalIF":4.2,"publicationDate":"2025-06-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144291287","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 innovative adaptive mineral segmentation method via augmentation and fusion of single and orthogonal polarized images: AMS-p/xpl","authors":"W. Ma ,&nbsp;P. Lin ,&nbsp;S. Li ,&nbsp;Z.H. Xu","doi":"10.1016/j.cageo.2025.105987","DOIUrl":"10.1016/j.cageo.2025.105987","url":null,"abstract":"<div><div>An adaptive mineral segmentation method is proposed to address the challenges of traditional thin section identification, which is typically expert-dependent, highly subjective, and time-consuming. The method is based on the augmentation and fusion of single polarized (PPL) and orthogonal polarized (XPL) images using an enhanced Deeplabv3-based segmentation model. The Depth Separable Convolution (DSC) is introduced to strengthen edge and texture features from PPL images, and a ColorBoost module is designed to enhance color information from XPL images. An adaptive feature fusion mechanism is employed to integrate complementary polarized features and dynamically adjust their contribution weights. The results demonstrate that the proposed model achieved the highest segmentation performance on the test set, with a mean intersection over union (<em>mIoU</em>) of 89.0 % and an accuracy of 96.7 %. Compared to widely used semantic segmentation networks such as FCN, it demonstrates a notable improvement in <em>mIoU</em>, with a maximum gain of 32.9 %. Additionally, through the integration of feature augmentation and an adaptive fusion mechanism, the model outperforms the baseline DeepLabv3 by 5 % in <em>mIoU.</em> The proposed method provides a more efficient and automated solution for thin section mineral identification, reducing reliance on expert knowledge and improving applicability in practical and non-specialist settings.</div></div>","PeriodicalId":55221,"journal":{"name":"Computers & Geosciences","volume":"204 ","pages":"Article 105987"},"PeriodicalIF":4.2,"publicationDate":"2025-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144262984","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":"A gradient-optimized least-squares reverse time migration based on the safe type-I anderson acceleration","authors":"Yingming Qu ,&nbsp;Chongpeng Huang","doi":"10.1016/j.cageo.2025.105984","DOIUrl":"10.1016/j.cageo.2025.105984","url":null,"abstract":"<div><div>Least-squares reverse time migration (LSRTM) can generate preferable images for complex media, but faces substantial computational challenges in field data applications, especially in 3D cases. Many optimization algorithms have been proposed to alleviate this problem, such as the limited-memory Broyden-Fletcher-Goldfarb-Shanno (LBFGS) method, the restarted generalized minimal residual method, and Anderson acceleration (AA). AA is a popular gradient optimization algorithm that has been widely used in many fields due to its ability to greatly accelerate the convergence of fixed-point iterations and considerably reduce the computational cost. According to Broyden's method, AA is divided into type-I AA (AA-I) and type-II AA (AA-II), with most implementations favoring AA-II due to residual oscillation issues observed in AA-I during data residual minimization. To address the residual vibration issue of AA-I and expedite the convergence of LSRTM, we apply a safe AA-I method to LSRTM, incorporating Powell-type regularization, re-start checking, and safe guarding steps. The Powell-type regularization guarantees the non-singularity of AA-I, while the re-start checking preserves its strong linear independence, both contributing to the stability of AA-I. The safe guarding steps examine the data residual reduction and accelerate the convergence. Our analysis reveals that the optimal step length for the safe AA-I method is approximately 5 times or 10 times the initial steepest descent (SD) iteration. We also derive an exponential scaling law for the safe AA-I step length. In addition, the safe AA-I has faster data residual convergence speed, less computational cost, and higher quality images than SD, conjugate gradient (CG), AA-II, and LBFGS. The safe AA-I is approximately twice as efficient as the LBFGS. Field validation through land seismic data processing shows that LSRTM based on the safe AA-I delivers enhanced structural resolution with sharper imaging events and improved stratigraphic continuity relative to LBFGS-based implementations.</div></div>","PeriodicalId":55221,"journal":{"name":"Computers & Geosciences","volume":"204 ","pages":"Article 105984"},"PeriodicalIF":4.2,"publicationDate":"2025-06-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144262986","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":"Lithological mapping using Spatially Constrained Bayesian Network (SCB-Net): A deep learning model for generating field-data-constrained predictions with uncertainty evaluation using remote sensing data","authors":"Victor Silva dos Santos ,&nbsp;Erwan Gloaguen ,&nbsp;Shiva Tirdad","doi":"10.1016/j.cageo.2025.105964","DOIUrl":"10.1016/j.cageo.2025.105964","url":null,"abstract":"<div><div>Geological maps are an important source of information for the Earth sciences. These maps are created using numerical or conceptual models that use geological observations to extrapolate data. Geostatistical techniques have traditionally been used to generate reliable predictions that take into account the spatial patterns inherent in the data. However, as the number of auxiliary variables increases, these methods become more labor-intensive. Additionally, traditional machine learning methods often struggle to capture spatial context and extract valuable non-linear information from geoscientific datasets. To address these challenges, we developed the Spatially Constrained Bayesian Network (SCB-Net)—an architecture designed to effectively integrate auxiliary variables while generating spatially constrained predictions. SCB-Net employs a late-fusion strategy, processing auxiliary data and ground-truth information through two parallel encoding paths. Additionally, it leverages Monte Carlo dropout as a Bayesian approximation to quantify model uncertainty. The SCB-Net has been tested on two real-world datasets from northern Quebec, Canada, demonstrating its effectiveness in generating field-data-constrained lithological maps while providing uncertainty estimates for unsampled locations. Our method outperformed the Attention U-Net – a widely used model in image segmentation – by at least 4.7% in accuracy across all tested datasets.</div></div>","PeriodicalId":55221,"journal":{"name":"Computers & Geosciences","volume":"204 ","pages":"Article 105964"},"PeriodicalIF":4.2,"publicationDate":"2025-05-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144222039","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":"AI-based geological subsurface reconstruction using sparse convolutional autoencoders","authors":"Rodrigo Uribe-Ventura ,&nbsp;Yoan Barriga-Berrios ,&nbsp;Jorge Barriga-Gamarra ,&nbsp;Patrice Baby ,&nbsp;Willem Viveen","doi":"10.1016/j.cageo.2025.105981","DOIUrl":"10.1016/j.cageo.2025.105981","url":null,"abstract":"<div><div>Subsurface reconstruction is critical for geological modeling and resource exploration. Conventional spatial interpolation methods are limited by stationarity and spatial isotropy assumptions, while advanced geostatistical techniques require specialized datasets. Deep learning approaches often need large datasets, which is impractical for geoscientific applications. This study presents an AI-based methodology using a sparse convolutional autoencoder for robust subsurface modeling under data constraints and integrating secondary data sources such as Vertical Electrical Sounding (VES) data. A four-stage testing framework was implemented: (1) emulating conventional interpolation for baseline performance; (2) reconstructing subsurface geometries from synthetic data; (3) incorporating geophysical constraints through VES forward modeling; and (4) validating the methodology using a real-world case study from the Huancayo tectonic basin in the Peruvian Andes, using 41 VES measurements across two cross-sections (12 and 14 km long). Results demonstrate that the proposed model effectively emulates kriging interpolation (mean squared error: 1.5 <span><math><mrow><mo>×</mo></mrow></math></span> 10<span><math><mrow><mo>−</mo><mn>3</mn></mrow></math></span> to 1.2 <span><math><mrow><mo>×</mo></mrow></math></span> 10<span><math><mrow><mo>−</mo><mn>3</mn></mrow></math></span> with 100–800 training examples) through transfer learning from an inverse-distance, pre-trained model. In subsurface reconstruction, the model outperforms kriging (37.4–61.7 % improvement across 1–15 % sampling densities) through its ability to adapt to non-stationary conditions. When incorporating synthetic VES data, the model effectively reconstructed subsurface geometries with error reduction from 4.1 <span><math><mrow><mo>×</mo></mrow></math></span> 10<span><math><mrow><mo>−</mo><mn>1</mn></mrow></math></span> to 9.1 <span><math><mrow><mo>×</mo></mrow></math></span> 10<span><math><mrow><mo>−</mo><mn>3</mn></mrow></math></span> as stations increased from 1 to 40, demonstrating diminishing returns beyond this point. Application to the Huancayo basin case study validated the model's practical applicability by successfully identifying previously unmapped features including the contact between basement and sedimentary infill, folds and faults. The methodology demonstrates the AI's capability to enhance geological understanding in complex tectonic settings, revealing subtle features and refining existing assumptions about subsurface architecture.</div></div>","PeriodicalId":55221,"journal":{"name":"Computers & Geosciences","volume":"204 ","pages":"Article 105981"},"PeriodicalIF":4.2,"publicationDate":"2025-05-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144178633","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":"Quadrangular adaptive mesh for elastic wave simulation in smooth anisotropic media","authors":"Marius Rapenne ,&nbsp;Paul Cupillard ,&nbsp;Guillaume Caumon ,&nbsp;Corentin Gouache","doi":"10.1016/j.cageo.2025.105946","DOIUrl":"10.1016/j.cageo.2025.105946","url":null,"abstract":"<div><div>Smooth anisotropic media are often met when implementing effective medium theory, full waveform inversion or seismic imaging. However, computational overburden is often a recurring problem when working with high frequencies or when quantifying uncertainties. In this context, adaptive meshes constitute, in principle, an attractive representation to maximize simulation accuracy while minimizing the computational cost. However, such meshes are difficult to create in the context of smooth anisotropic media as the optimal local size of the elements is not clearly defined. In this work, we present a two-step algorithm to efficiently mesh these media for spectral element method (SEM) simulation in the 2D elastic case. Our algorithm yields quadrangular only meshes which adapt the size of the element to the local and directional S-wave velocity. It relies on a quadtree division introduced by Maréchal (2009) to divide the mesh until the size of each element edge is adapted to the local minimum wavelength that will be propagated. Then, a Laplacian smoothing is applied to further optimize the size of the elements, increasing the global time step and makes the SEM simulation faster while keeping a good accuracy and even improving it in some cases. An application of our method on a 2D section of the homogenized Groningen area shows that simulation time can be reduced by a factor up to 7.</div></div>","PeriodicalId":55221,"journal":{"name":"Computers & Geosciences","volume":"203 ","pages":"Article 105946"},"PeriodicalIF":4.2,"publicationDate":"2025-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144148034","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":"Rock thin section image classification in low data scenarios using few-shot learning","authors":"Maofa Wang ,&nbsp;Wenheng Guo ,&nbsp;Fengshan Yang ,&nbsp;Bingchen Yan ,&nbsp;Yanlin Xu ,&nbsp;Jun Jiang ,&nbsp;Jingjing Huang","doi":"10.1016/j.cageo.2025.105962","DOIUrl":"10.1016/j.cageo.2025.105962","url":null,"abstract":"<div><div>Microscopic rock thin section image recognition is crucial in rock mineral analysis. Typically, deep learning models are used to automate expert knowledge, but the scarcity of samples in certain categories limits the available training data, affecting the performance of traditional deep learning models. This paper proposes a novel few-shot learning model to address the challenge of classifying rock thin section images under limited sample conditions. Based on advanced few-shot learning processes involving pre-training and meta-training, we first introduce a Cross Attention Feature Fusion (CAFF) module. This module generates new features by combining plane polarized light images (PPL) and cross-polarized light images (XPL) of rock thin sections under a microscope, integrating these with the original features through autonomous learning to obtain more comprehensive features. Secondly, we propose a Feature Selection (FS) module based on the prototypical network (ProtoNet). This module enhances the model’s classification capability by extracting key feature dimensions from two perspectives: intra-class representativeness and inter-class distinctiveness. Finally, using the pre-trained ResNet50 and Swim-Transformer on ImageNet-1000k as the backbone network, simulation experiments were conducted on the Nanjing University Rock Thin Section Teaching Dataset. Under the 5-Way 5-Shot few-shot learning task standard, the proposed ProtoNet-CAFF-FS model achieved an average classification accuracy of 96.70% and 99.16%, outperforming traditional modeling methods and demonstrating the effectiveness of the newly added modules.</div></div>","PeriodicalId":55221,"journal":{"name":"Computers & Geosciences","volume":"203 ","pages":"Article 105962"},"PeriodicalIF":4.2,"publicationDate":"2025-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144131119","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":"A GPU algorithm for identifying the longest flow paths in catchments","authors":"Bartłomiej Kotyra","doi":"10.1016/j.cageo.2025.105961","DOIUrl":"10.1016/j.cageo.2025.105961","url":null,"abstract":"<div><div>The longest flow path is one of the key features of a catchment, commonly considered in hydrological analysis and modeling. Recent literature highlights that identifying the longest flow paths using existing software tools is time-consuming. Over the last few years, attempts have been made to develop more computationally efficient algorithms for this particular task. This paper extends previously published research and presents a new GPU algorithm designed for fast identification of the longest flow paths using DEM-derived flow directions. Performance measurements show significantly shorter execution times compared to other existing algorithms for the same task. Additionally, this algorithm is able to efficiently process multiple catchments in the same run, offering further performance improvements.</div></div>","PeriodicalId":55221,"journal":{"name":"Computers & Geosciences","volume":"203 ","pages":"Article 105961"},"PeriodicalIF":4.2,"publicationDate":"2025-05-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144123278","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":"Smoke or cloud: Real-time satellite image segmentation in a wildfire data integration application","authors":"Sequoia Andrade ,&nbsp;Nastaran Shafiei ,&nbsp;Peter Mehlitz","doi":"10.1016/j.cageo.2025.105960","DOIUrl":"10.1016/j.cageo.2025.105960","url":null,"abstract":"<div><div>Advanced satellite data is increasingly used for wildfire detection and monitoring, yet near real-time hotspot data products from the GOES-R series often have low confidence due to aerosol contamination. Since aerosol contamination impacts the confidence of the GOES-R hot spot detection algorithm, regardless of contamination from fire-indicating smoke or false positive-indicating clouds, differentiating smoke from cloud has the potential to improve the accuracy of real-time hot spot detection. The primary contribution of this paper is a multi-class smoke and cloud segmentation model that classifies smoke, cloud, and neither pixels from GOES-R true color images in a real-time application. When selecting the final model, we perform an experiment to examine the impact self-supervised learning has on different model architectures. The final model is a U-Net model pre-trained on over 10,000 images using Barlow Twins self-supervised learning and fine-tuned using supervised learning, which exhibits comparable performance to the larger and slower ResUnet model. Our model improves upon existing satellite-based smoke segmentation, with 85% accuracy and 68% mean intersection-over-union on the test set. The model is deployed in an Open Data Integration for wildfire management (ODIN) application, allowing for real-time smoke and cloud detection to improve situational awareness regarding smoke location. From real-time image import to smoke-cloud segmentation display in the browser, the total run time is approximately 74 s, with 52 s total from the segmentation model pipeline.</div></div>","PeriodicalId":55221,"journal":{"name":"Computers & Geosciences","volume":"204 ","pages":"Article 105960"},"PeriodicalIF":4.2,"publicationDate":"2025-05-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144166157","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":"FourCastLSTM: A precipitation nowcasting model integrating global and local spatiotemporal features","authors":"Chuangwei Xu ,&nbsp;Jie Liu ,&nbsp;Shiyuan Han ,&nbsp;Xiaoqi Duan ,&nbsp;Lei Xiang ,&nbsp;Tong Zhang","doi":"10.1016/j.cageo.2025.105966","DOIUrl":"10.1016/j.cageo.2025.105966","url":null,"abstract":"<div><div>Accurate precipitation nowcasting is crucial for transportation, agriculture, urban planning, and tourism, and it is highly beneficial in disaster prevention, resource allocation, and service optimization. Existing precipitation nowcasting methods often integrate convolution neural networks and recurrent neural networks or employ vision transformers to capture spatiotemporal correlations. However, convolutional operators struggle to capture global information, and vision transformers based global modeling may overemphasize heavy rainfall while neglecting moderate and light precipitation. In this study, Fourier nowCasting LSTM (FourCastLSTM) is introduced to effectively capture and fusion spatiotemporal global and local features of precipitation, enhancing prediction accuracy for different precipitation intensities. A Fourier nowCasting LSTM Cell (FourCastCell), which combine the Adaptive Fourier Neural Operator (AFNO) with a simplified LSTM, is proposed to reinforce the representation of global spatiotemporal precipitation patterns by replacing traditional convolutional layers with AFNO. An Image Detail Enhancement module (IDE) is adopted to strengthen local precipitation detail features by integrating difference convolutional neural network. Finally, the adaptive feature fusion module embedded in the IDE, can dynamically adjust the integration weights of global and local features based on the specific spatiotemporal features of precipitation events, ensuring a balanced fusion of features with different intensities. Experiments on synthetic datasets (MovingMNIST++) and real-world datasets (RadarCIKM) demonstrate that the proposed FourCastLSTM outperforms state-of-the-art approaches by 15.6 % and 9.6 % in B-MAE and B-MSE metrics, respectively.</div></div>","PeriodicalId":55221,"journal":{"name":"Computers & Geosciences","volume":"204 ","pages":"Article 105966"},"PeriodicalIF":4.2,"publicationDate":"2025-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144338655","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}