Applied Computing and Geosciences最新文献_第4页

Interpretable ore classification using SHAP-enhanced LightGBM: A case study from the Qiaomaishan deposit, China 基于shap增强LightGBM的可解释矿石分类——以乔麦山矿床为例

IF 3.2 Q2 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Applied Computing and Geosciences

Pub Date : 2025-09-26 DOI: 10.1016/j.acags.2025.100295

Mingming Zhang , Xiaoyuan Wang , Cong Chen , Jing Ding , Xinsuo Zhou , Jiangyanyu Qu

Accurate ore classification is essential for geological exploration and mineral resource assessment, particularly in geologically complex settings. This study presents an interpretable classification framework that integrates the Light Gradient Boosting Machine (LightGBM) algorithm with post hoc model interpretation using SHapley Additive exPlanations (SHAP). The framework is applied to geochemical and spatial data from the Qiaomaishan Cu-S polymetallic deposit in Anhui Province, China. A dataset comprising 1588 samples-each containing concentrations of 29 geochemical elements along with 3D spatial coordinates-was used to train and evaluate 5 machine learning models: Support Vector Machine (SVM), Multi-Layer Perceptron (MLP), Random Forest (RF), LightGBM, and CatBoost. Among these, LightGBM achieved the best performance, with an average F1 score of 0.990 across 10 ore and lithological categories. An ablation experiment further confirmed the critical role of spatial coordinates, as removing them led to a notable drop in classification accuracy, particularly for underrepresented ore types. To interpret the LightGBM model, SHAP analysis was used to quantify feature contributions, identifying key geochemical elements such as W, Sr, Ca, and Fe as significant drivers of classification-consistent with the known mineralogical characteristics of the deposit. Moreover, SHAP beeswarm plots provided insights into the direction and magnitude of each feature's influence, enhancing the model's geological interpretability. SHAP-based feature selection further improved classification performance for underrepresented classes, including copper–sulphur–tungsten ore and copper ore. The proposed framework demonstrates strong potential for facilitating automated ore identification and supporting data-driven decision-making in complex geological environments.

准确的矿石分类对地质勘探和矿产资源评价至关重要，特别是在地质复杂的环境中。本研究提出了一个可解释的分类框架，该框架将光梯度增强机（LightGBM）算法与使用SHapley加性解释（SHAP）的事后模型解释相结合。将该框架应用于安徽乔麦山铜硫多金属矿床的地球化学和空间数据。一个包含1588个样本的数据集-每个样本包含29种地球化学元素的浓度以及3D空间坐标-用于训练和评估5种机器学习模型：支持向量机（SVM），多层感知器（MLP），随机森林（RF）， LightGBM和CatBoost。其中，LightGBM表现最佳，10个矿石和岩性类别的F1平均得分为0.990。消融实验进一步证实了空间坐标的关键作用，因为去除它们会导致分类精度显著下降，特别是对于代表性不足的矿石类型。为了解释LightGBM模型，使用SHAP分析来量化特征贡献，确定关键的地球化学元素，如W、Sr、Ca和Fe，作为分类的重要驱动因素，与已知的矿床矿物学特征一致。此外，SHAP蜂群图提供了对每个特征影响的方向和大小的见解，增强了模型的地质可解释性。基于shap的特征选择进一步提高了代表性不足的类别（包括铜硫钨矿和铜矿）的分类性能。所提出的框架在促进复杂地质环境下的自动化矿石识别和支持数据驱动决策方面具有强大的潜力。

{"title":"Interpretable ore classification using SHAP-enhanced LightGBM: A case study from the Qiaomaishan deposit, China","authors":"Mingming Zhang , Xiaoyuan Wang , Cong Chen , Jing Ding , Xinsuo Zhou , Jiangyanyu Qu","doi":"10.1016/j.acags.2025.100295","DOIUrl":"10.1016/j.acags.2025.100295","url":null,"abstract":"<div><div>Accurate ore classification is essential for geological exploration and mineral resource assessment, particularly in geologically complex settings. This study presents an interpretable classification framework that integrates the Light Gradient Boosting Machine (LightGBM) algorithm with post hoc model interpretation using SHapley Additive exPlanations (SHAP). The framework is applied to geochemical and spatial data from the Qiaomaishan Cu-S polymetallic deposit in Anhui Province, China. A dataset comprising 1588 samples-each containing concentrations of 29 geochemical elements along with 3D spatial coordinates-was used to train and evaluate 5 machine learning models: Support Vector Machine (SVM), Multi-Layer Perceptron (MLP), Random Forest (RF), LightGBM, and CatBoost. Among these, LightGBM achieved the best performance, with an average F1 score of 0.990 across 10 ore and lithological categories. An ablation experiment further confirmed the critical role of spatial coordinates, as removing them led to a notable drop in classification accuracy, particularly for underrepresented ore types. To interpret the LightGBM model, SHAP analysis was used to quantify feature contributions, identifying key geochemical elements such as W, Sr, Ca, and Fe as significant drivers of classification-consistent with the known mineralogical characteristics of the deposit. Moreover, SHAP beeswarm plots provided insights into the direction and magnitude of each feature's influence, enhancing the model's geological interpretability. SHAP-based feature selection further improved classification performance for underrepresented classes, including copper–sulphur–tungsten ore and copper ore. The proposed framework demonstrates strong potential for facilitating automated ore identification and supporting data-driven decision-making in complex geological environments.</div></div>","PeriodicalId":33804,"journal":{"name":"Applied Computing and Geosciences","volume":"28 ","pages":"Article 100295"},"PeriodicalIF":3.2,"publicationDate":"2025-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145269354","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Enhancing SAM-based digital rock image segmentation via edge-semantics fusion 利用边缘语义融合增强基于sam的数字岩石图像分割

IF 3.2 Q2 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Applied Computing and Geosciences

Pub Date : 2025-09-20 DOI: 10.1016/j.acags.2025.100292

Ziqiang Wang , Zhiyu Hou , Danping Cao

The Segment Anything Model (SAM) demonstrates strong segmentation capabilities. However, its application to digital rock images faces challenges from subtle transitions between matrix minerals and pore structures, as well as inherent heterogeneity, which result in mis-segmentation and discontinuities that affect petrophysical characterization and numerical modeling of subsurface reservoir properties. To address these challenges, we introduce ESF-SAM (Edge-Semantics Fusion-SAM), a novel approach that enhances SAM's segmentation fidelity by integrating edge and semantic features. Specifically, in ESF-SAM, semantic features from SAM's image encoder are processed through an edge decoder enhanced by progressive dilated convolutions to extract detailed structural boundaries. The resulting edge and original semantic features are adaptively fused through a dual-attention mechanism, where spatial gating attention dynamically balances their contributions across locations, and channel attention recalibrates feature importance to enrich the representation. This spatial–channel attention framework enriches feature representations, enabling targeted fine-tuning within the SAM decoder and thereby preserving global segmentation capability while significantly improving local boundary delineation in two-phase segmentation tasks. Experimental results demonstrate that ESF-SAM improves segmentation detail, leading to more accurate derivation of key rock properties such as elastic modulus and pore geometry parameters, with results that more closely align with labeled data compared to the original SAM. Trained on only a small number of annotated sandstone images, ESF-SAM effectively adapts to the target domain and exhibits strong generalization when applied to carbonate rock images without additional fine-tuning. This work exemplifies how integrating priors into foundation models can substantially enhance their applicability to complex scientific imaging tasks.

分段任意模型（SAM）展示了强大的分段能力。然而，将其应用于数字岩石图像面临着基质矿物和孔隙结构之间的微妙过渡以及固有的非均质性的挑战，这些挑战导致了错误的分割和不连续性，从而影响了岩石物理表征和地下储层性质的数值模拟。为了解决这些挑战，我们引入了ESF-SAM（边缘语义融合-SAM），这是一种通过整合边缘和语义特征来提高SAM分割保真度的新方法。具体而言，在ESF-SAM中，来自SAM图像编码器的语义特征通过渐进式扩展卷积增强的边缘解码器进行处理，以提取详细的结构边界。通过双注意机制自适应融合生成的边缘和原始语义特征，其中空间门控注意动态平衡其在不同位置上的贡献，通道注意重新校准特征的重要性以丰富表征。这种空间通道注意框架丰富了特征表示，使SAM解码器能够进行有针对性的微调，从而在保留全局分割能力的同时显著改善了两阶段分割任务中的局部边界描绘。实验结果表明，与原始的SAM相比，ESF-SAM改善了分割细节，可以更准确地推导出关键的岩石属性，如弹性模量和孔隙几何参数，结果与标记数据更接近。仅在少量带注释的砂岩图像上进行训练，ESF-SAM可以有效地适应目标域，并且在无需额外微调的情况下应用于碳酸盐岩图像时表现出很强的泛化能力。这项工作举例说明了如何将先验整合到基础模型中可以大大提高它们对复杂科学成像任务的适用性。

{"title":"Enhancing SAM-based digital rock image segmentation via edge-semantics fusion","authors":"Ziqiang Wang , Zhiyu Hou , Danping Cao","doi":"10.1016/j.acags.2025.100292","DOIUrl":"10.1016/j.acags.2025.100292","url":null,"abstract":"<div><div>The Segment Anything Model (SAM) demonstrates strong segmentation capabilities. However, its application to digital rock images faces challenges from subtle transitions between matrix minerals and pore structures, as well as inherent heterogeneity, which result in mis-segmentation and discontinuities that affect petrophysical characterization and numerical modeling of subsurface reservoir properties. To address these challenges, we introduce ESF-SAM (Edge-Semantics Fusion-SAM), a novel approach that enhances SAM's segmentation fidelity by integrating edge and semantic features. Specifically, in ESF-SAM, semantic features from SAM's image encoder are processed through an edge decoder enhanced by progressive dilated convolutions to extract detailed structural boundaries. The resulting edge and original semantic features are adaptively fused through a dual-attention mechanism, where spatial gating attention dynamically balances their contributions across locations, and channel attention recalibrates feature importance to enrich the representation. This spatial–channel attention framework enriches feature representations, enabling targeted fine-tuning within the SAM decoder and thereby preserving global segmentation capability while significantly improving local boundary delineation in two-phase segmentation tasks. Experimental results demonstrate that ESF-SAM improves segmentation detail, leading to more accurate derivation of key rock properties such as elastic modulus and pore geometry parameters, with results that more closely align with labeled data compared to the original SAM. Trained on only a small number of annotated sandstone images, ESF-SAM effectively adapts to the target domain and exhibits strong generalization when applied to carbonate rock images without additional fine-tuning. This work exemplifies how integrating priors into foundation models can substantially enhance their applicability to complex scientific imaging tasks.</div></div>","PeriodicalId":33804,"journal":{"name":"Applied Computing and Geosciences","volume":"28 ","pages":"Article 100292"},"PeriodicalIF":3.2,"publicationDate":"2025-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145159762","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Analyzing key controlling factors of shale reservoir heterogeneity in "thin" stratigraphic settings: A deep learning-aided case study of the Wufeng-Longmaxi Formations, Fuyan Syncline, Northern Guizhou “薄”地层条件下页岩储层非均质性控制因素分析——以黔北扶岩向斜五峰组—龙马溪组为例

IF 3.2 Q2 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Applied Computing and Geosciences

Pub Date : 2025-09-20 DOI: 10.1016/j.acags.2025.100293

Ye Tao, Zhidong Bao, Fukang Ma

The Wufeng-Longmaxi Formation shales are key targets for shale gas exploration, but they are often studied as a single stratigraphic unit with limited analysis of internal differences. This study combines traditional geological methods with deep learning to compare the reservoir characteristics of the Wufeng Formation, the first member of the Longmaxi Formation (Long 1), and the second member of the Longmaxi Formation (Long 2), identifying the main controlling factors of differences. We found that: (1) The Wufeng Formation primarily develops siliceous shale lithofacies (S), mixed siliceous shale lithofacies (S-2), and clay siliceous shale lithofacies (S-3). Long 1 develops mixed siliceous shale lithofacies (S-2) and clay siliceous shale lithofacies (S-3), while Long 2 exhibits clay and siliceous mixed shale lithofacies (M-2) and siliceous clay shale lithofacies (CM-1). (2) The YOLO-v8 model demonstrates higher accuracy in shale pore type detection than the YOLO-v10 model, with a maximum mAP of 78.9 %. Using the YOLO-v8 model, it was found that S, S-2, and S-3 lithofacies are dominated by dissolution pores and organic pores with larger specific surface areas and porosities, while CM-1 and M-2 lithofacies are characterized by dissolution pores with smaller specific surface areas and porosities. (3) Based on evaluation indicators such as TOC content, BET surface area, porosity, brittleness index, and gas content, S and S-2 are classified as Class I lithofacies, S-3 as Class II lithofacies, and M-2 and CM-1 as Class III lithofacies. The main controlling factor for the heterogeneity of the shale reservoirs in the study area is lithofacies.

五峰组—龙马溪组页岩是页岩气勘探的重点靶区，但往往将其作为一个单一的地层单元进行研究，对其内部差异分析有限。本研究将传统地质方法与深度学习相结合，对龙马溪组一段（龙一段）与龙马溪组二段（龙二段）五峰组储层特征进行对比，找出差异的主控因素。研究发现：(1)五峰组主要发育硅质页岩岩相(S)、混合硅质页岩岩相（S-2）和粘土硅质页岩岩相（S-3）。龙1发育混合硅质页岩岩相（S-2）和粘土硅质页岩岩相（S-3），龙2发育粘土与硅质混合页岩岩相（M-2）和硅质粘土页岩岩相（CM-1）。(2) YOLO-v8模型对页岩孔隙类型的检测精度高于YOLO-v10模型，最大mAP值为78.9%。利用YOLO-v8模型发现，S、S-2和S-3岩相以溶蚀孔和有机质孔为主，具有较大的比表面积和孔隙度；CM-1和M-2岩相以溶蚀孔为主，比表面积和孔隙度较小。(3)根据TOC含量、BET表面积、孔隙度、脆性指数、含气量等评价指标，将S、S-2划分为ⅰ类岩相，S-3划分为ⅱ类岩相，M-2、CM-1划分为ⅲ类岩相。控制研究区页岩储层非均质性的主要因素是岩相。

{"title":"Analyzing key controlling factors of shale reservoir heterogeneity in \"thin\" stratigraphic settings: A deep learning-aided case study of the Wufeng-Longmaxi Formations, Fuyan Syncline, Northern Guizhou","authors":"Ye Tao, Zhidong Bao, Fukang Ma","doi":"10.1016/j.acags.2025.100293","DOIUrl":"10.1016/j.acags.2025.100293","url":null,"abstract":"<div><div>The Wufeng-Longmaxi Formation shales are key targets for shale gas exploration, but they are often studied as a single stratigraphic unit with limited analysis of internal differences. This study combines traditional geological methods with deep learning to compare the reservoir characteristics of the Wufeng Formation, the first member of the Longmaxi Formation (Long 1), and the second member of the Longmaxi Formation (Long 2), identifying the main controlling factors of differences. We found that: (1) The Wufeng Formation primarily develops siliceous shale lithofacies (S), mixed siliceous shale lithofacies (S-2), and clay siliceous shale lithofacies (S-3). Long 1 develops mixed siliceous shale lithofacies (S-2) and clay siliceous shale lithofacies (S-3), while Long 2 exhibits clay and siliceous mixed shale lithofacies (M-2) and siliceous clay shale lithofacies (CM-1). (2) The YOLO-v8 model demonstrates higher accuracy in shale pore type detection than the YOLO-v10 model, with a maximum mAP of 78.9 %. Using the YOLO-v8 model, it was found that S, S-2, and S-3 lithofacies are dominated by dissolution pores and organic pores with larger specific surface areas and porosities, while CM-1 and M-2 lithofacies are characterized by dissolution pores with smaller specific surface areas and porosities. (3) Based on evaluation indicators such as TOC content, BET surface area, porosity, brittleness index, and gas content, S and S-2 are classified as Class I lithofacies, S-3 as Class II lithofacies, and M-2 and CM-1 as Class III lithofacies. The main controlling factor for the heterogeneity of the shale reservoirs in the study area is lithofacies.</div></div>","PeriodicalId":33804,"journal":{"name":"Applied Computing and Geosciences","volume":"28 ","pages":"Article 100293"},"PeriodicalIF":3.2,"publicationDate":"2025-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145159761","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Using machine learning classifiers together with discrimination diagrams for validation of rock classification labels 利用机器学习分类器和判别图对岩石分类标签进行验证

IF 3.2 Q2 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Applied Computing and Geosciences

Pub Date : 2025-09-19 DOI: 10.1016/j.acags.2025.100288

Malte Mues , Dennis Kraemer , David M. Ernst Styn

Rock classification based on chemical components is a common task in the geochemical domain. Literature recommends the Total Alkali and Silica (TAS) discrimination diagram for classifying igneous volcanic rocks by the sum of Na

_{2}

O and K

_{2}

O in relation to SiO

_{2}

contents. This paper comparatively applies the TAS diagram and machine learning classification techniques to a collection of volcanic rocks from the GEOROC database. The study demonstrates a mismatch between the rock type labeled by experts in the database and rock types assigned by the TAS diagram. Despite this discrepancy, the experiments show that support vector machines are particularly promising for building decision systems for rock classification. Random forests, multi-layer perceptrons and K nearest neighbors are less suitable as rock classifiers in the study.

基于化学成分的岩石分类是地球化学领域的一项常见任务。文献推荐用总碱硅（Total Alkali and Silica， TAS）判别图，通过Na2O和K2O与SiO2含量的总和对火成岩进行分类。本文将TAS图和机器学习分类技术对比应用于GEOROC数据库中的火山岩集合。该研究表明，数据库中专家标记的岩石类型与TAS图分配的岩石类型之间存在不匹配。尽管存在这种差异，但实验表明，支持向量机在构建岩石分类决策系统方面特别有前途。随机森林、多层感知器和K近邻都不适合作为岩石分类器。

引用次数: 0

Automating fault detection in seismic data: integrating image processing with deep learning 地震数据故障自动检测：图像处理与深度学习的集成

IF 3.2 Q2 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Applied Computing and Geosciences

Pub Date : 2025-09-15 DOI: 10.1016/j.acags.2025.100286

Ahmad Ashtari

Fault interpretation in seismic images is crucial for identifying fluid accommodation and flow migration pathways in the oil and gas industry. Several algorithms have been developed to calculate seismic attributes which help identify faults. Despite these advancements, challenges still remain in fault interpretation due to the complexity of fault networks, noise, and quality of seismic data. Hybrid seismic attributes extracted through artificial neural networks can enhance fault interpretation. In the case of neural network-based approaches used for geological feature extraction, picking precise samples for training neural networks is vital. In this study, an innovative method based on the Shi–Tomasi corner detection algorithm has been introduced to automatically pick fault samples on seismic data to be used as input to deep neural networks to predict faults. The method has been tested on two field seismic images that were acquired at different surveys. The field examples indicate that the trained neural networks could give a precise and clear estimation of faults with different azimuths. This proves the proposed sampling method can effectively provide a high-quality training data set for deep neural networks to automatically predict faults from seismic data.

在油气工业中，地震图像中的断层解释对于确定流体容纳和流动运移路径至关重要。已经开发了几种算法来计算地震属性，以帮助识别断层。尽管取得了这些进步，但由于断层网的复杂性、噪声和地震数据的质量，断层解释仍然存在挑战。通过人工神经网络提取混合地震属性，可以提高断层解释的精度。在用于地质特征提取的基于神经网络的方法中，为训练神经网络选择精确的样本是至关重要的。本文提出了一种基于Shi-Tomasi角点检测算法的创新方法，从地震数据中自动提取断层样本，作为深度神经网络的输入，进行断层预测。该方法已在不同勘探获得的两幅现场地震图像上进行了测试。现场算例表明，所训练的神经网络能准确、清晰地估计出不同方位的故障。这证明了该方法可以有效地为深度神经网络从地震数据中自动预测断层提供高质量的训练数据集。

{"title":"Automating fault detection in seismic data: integrating image processing with deep learning","authors":"Ahmad Ashtari","doi":"10.1016/j.acags.2025.100286","DOIUrl":"10.1016/j.acags.2025.100286","url":null,"abstract":"<div><div>Fault interpretation in seismic images is crucial for identifying fluid accommodation and flow migration pathways in the oil and gas industry. Several algorithms have been developed to calculate seismic attributes which help identify faults. Despite these advancements, challenges still remain in fault interpretation due to the complexity of fault networks, noise, and quality of seismic data. Hybrid seismic attributes extracted through artificial neural networks can enhance fault interpretation. In the case of neural network-based approaches used for geological feature extraction, picking precise samples for training neural networks is vital. In this study, an innovative method based on the Shi–Tomasi corner detection algorithm has been introduced to automatically pick fault samples on seismic data to be used as input to deep neural networks to predict faults. The method has been tested on two field seismic images that were acquired at different surveys. The field examples indicate that the trained neural networks could give a precise and clear estimation of faults with different azimuths. This proves the proposed sampling method can effectively provide a high-quality training data set for deep neural networks to automatically predict faults from seismic data.</div></div>","PeriodicalId":33804,"journal":{"name":"Applied Computing and Geosciences","volume":"28 ","pages":"Article 100286"},"PeriodicalIF":3.2,"publicationDate":"2025-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145108300","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Neural network inversion of seismic wave velocities for vadose zone water content profile 含气带含水率剖面地震波速度的神经网络反演

IF 3.2 Q2 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Applied Computing and Geosciences

Pub Date : 2025-09-01 DOI: 10.1016/j.acags.2025.100285

Quentin Didier, Victor Sauvage, Léna Pellorce, Rémi Valois, Slimane Arhab, Arnaud Mesgouez

Accurate estimation of water saturation in the vadose zone is crucial for hydrological and agricultural applications. However, traditional seismic inversion methods often struggle with non-linearity and sensitivity to noise, limiting their generalisation capabilities. To address this challenge, we propose a neural network-based inversion approach that allows the assessment of the vertical distribution of water saturation from compressional (

v_{_{P}}

) and shear (

v_{_{S}}

) wave velocities. Specifically, our architecture is based on a regression model and incorporates an autoencoder layer to improve robustness against noise. As a result, this enhances its ability to invert complete saturation profiles and increases its adaptability to complex hydrological conditions. Furthermore, the model demonstrates strong performance across varying water table depths, with low error metrics and high resilience to input noise with a RMSE of 3.34 × 10⁻² and a R

^{2}

of 0.978 for 5% noise. Our current approach has been trained exclusively on noisy synthetic data. We plan to validate it in the near future against experimental field data we have recorded for an agricultural soil. Overall, this study establishes a foundation for future applications of deep learning in hydrogeophysical inversion and underscores the need for validation with real-world data.

准确估计渗透带含水饱和度对水文和农业应用至关重要。然而，传统的地震反演方法往往存在非线性和噪声敏感性等问题，限制了其泛化能力。为了应对这一挑战，我们提出了一种基于神经网络的反演方法，可以通过纵波速度（vP）和横波速度（vS）来评估含水饱和度的垂直分布。具体来说，我们的架构是基于一个回归模型，并结合了一个自编码器层，以提高对噪声的鲁棒性。因此，这增强了其反演完整饱和度剖面的能力，并提高了其对复杂水文条件的适应性。此外，该模型在不同的地下水位深度上表现出很强的性能，具有较低的误差指标和对输入噪声的高弹性，RMSE为3.34 × 10−2，对于5%的噪声，R2为0.978。我们目前的方法是专门针对有噪声的合成数据进行训练的。我们计划在不久的将来根据我们在农业土壤中记录的试验田数据来验证它。总的来说，这项研究为未来深度学习在水文地球物理反演中的应用奠定了基础，并强调了用现实世界数据验证的必要性。

{"title":"Neural network inversion of seismic wave velocities for vadose zone water content profile","authors":"Quentin Didier, Victor Sauvage, Léna Pellorce, Rémi Valois, Slimane Arhab, Arnaud Mesgouez","doi":"10.1016/j.acags.2025.100285","DOIUrl":"10.1016/j.acags.2025.100285","url":null,"abstract":"<div><div>Accurate estimation of water saturation in the vadose zone is crucial for hydrological and agricultural applications. However, traditional seismic inversion methods often struggle with non-linearity and sensitivity to noise, limiting their generalisation capabilities. To address this challenge, we propose a neural network-based inversion approach that allows the assessment of the vertical distribution of water saturation from compressional (<span><math><msub><mrow><mi>v</mi></mrow><mrow><msub><mrow></mrow><mrow><mi>P</mi></mrow></msub></mrow></msub></math></span>) and shear (<span><math><msub><mrow><mi>v</mi></mrow><mrow><msub><mrow></mrow><mrow><mi>S</mi></mrow></msub></mrow></msub></math></span>) wave velocities. Specifically, our architecture is based on a regression model and incorporates an autoencoder layer to improve robustness against noise. As a result, this enhances its ability to invert complete saturation profiles and increases its adaptability to complex hydrological conditions. Furthermore, the model demonstrates strong performance across varying water table depths, with low error metrics and high resilience to input noise with a RMSE of 3.34 × 10<sup>−2</sup> and a R<span><math><msup><mrow></mrow><mrow><mn>2</mn></mrow></msup></math></span> of 0.978 for 5% noise. Our current approach has been trained exclusively on noisy synthetic data. We plan to validate it in the near future against experimental field data we have recorded for an agricultural soil. Overall, this study establishes a foundation for future applications of deep learning in hydrogeophysical inversion and underscores the need for validation with real-world data.</div></div>","PeriodicalId":33804,"journal":{"name":"Applied Computing and Geosciences","volume":"27 ","pages":"Article 100285"},"PeriodicalIF":3.2,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145044083","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

GPU-accelerated simulation of steady-state flow and particle transport in discrete fracture networks 离散断裂网络中稳态流动和粒子输运的gpu加速模拟

IF 3.2 Q2 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Applied Computing and Geosciences

Pub Date : 2025-09-01 DOI: 10.1016/j.acags.2025.100284

Tingchang Yin , Teng Man , Pei Zhang , Sergio Andres Galindo-Torres

Fracture networks in the subsurface can serve as the primary pathway for fluid flow, allowing for solute transport. This process is critical to various real-world applications, including resource extraction and contaminant migration in fractured rocks. We develop an open-source code called cuDFNsys to simulate flow and transport in discrete fracture networks (DFNs). Our code uses the mixed hybrid finite element method to solve the hydraulic head and velocity fields in DFNs, and the particle tracking method to simulate the movement of solute plumes. The GPU parallelization accelerates the generation of DFNs, identification of intersections between fractures, determination of elementary matrices, and motion of particles. We use several benchmarks to verify the accuracy of flow and transport simulation in cuDFNsys. Dispersion in a DFN is used to demonstrate examples of particle tracking. Performance analyses demonstrate that our code is well-suited for Monte Carlo iterations of DFN simulations, enabling physicists and geoscientists to study critical phenomena and phase transitions in fracture networks using percolation theory.

地下裂缝网络可以作为流体流动的主要通道，允许溶质运输。该过程对于各种实际应用至关重要，包括资源提取和裂缝岩石中的污染物运移。我们开发了一个名为cuDFNsys的开源代码来模拟离散裂缝网络（DFNs）中的流动和传输。我们的代码采用混合混合有限元法求解DFNs中的水头和速度场，采用粒子跟踪法模拟溶质羽流的运动。GPU的并行化加速了dfn的生成、裂缝间交点的识别、初等矩阵的确定和粒子的运动。我们使用几个基准来验证cuDFNsys中流量和传输模拟的准确性。DFN中的色散被用来演示粒子跟踪的例子。性能分析表明，我们的代码非常适合DFN模拟的蒙特卡罗迭代，使物理学家和地球科学家能够使用渗透理论研究裂缝网络中的关键现象和相变。

{"title":"GPU-accelerated simulation of steady-state flow and particle transport in discrete fracture networks","authors":"Tingchang Yin , Teng Man , Pei Zhang , Sergio Andres Galindo-Torres","doi":"10.1016/j.acags.2025.100284","DOIUrl":"10.1016/j.acags.2025.100284","url":null,"abstract":"<div><div>Fracture networks in the subsurface can serve as the primary pathway for fluid flow, allowing for solute transport. This process is critical to various real-world applications, including resource extraction and contaminant migration in fractured rocks. We develop an open-source code called <em>cuDFNsys</em> to simulate flow and transport in discrete fracture networks (DFNs). Our code uses the mixed hybrid finite element method to solve the hydraulic head and velocity fields in DFNs, and the particle tracking method to simulate the movement of solute plumes. The GPU parallelization accelerates the generation of DFNs, identification of intersections between fractures, determination of elementary matrices, and motion of particles. We use several benchmarks to verify the accuracy of flow and transport simulation in <em>cuDFNsys</em>. Dispersion in a DFN is used to demonstrate examples of particle tracking. Performance analyses demonstrate that our code is well-suited for Monte Carlo iterations of DFN simulations, enabling physicists and geoscientists to study critical phenomena and phase transitions in fracture networks using percolation theory.</div></div>","PeriodicalId":33804,"journal":{"name":"Applied Computing and Geosciences","volume":"27 ","pages":"Article 100284"},"PeriodicalIF":3.2,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144988473","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Simwave: A finite difference simulator for acoustic waves propagation 模拟波：一个声波传播的有限差分模拟器

IF 3.2 Q2 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Applied Computing and Geosciences

Pub Date : 2025-09-01 DOI: 10.1016/j.acags.2025.100283

Hermes Senger , Jaime Freire de Souza , João Baptista Dias Moreira , Keith Jared Roberts , Roussian di Ramos Alves Gaioso , Emílio Carlos Nelli Silva , Edson Satoshi Gomi

Simwave is an open-source software package for wave simulations in 2D or 3D domains. It solves the constant and variable density acoustic wave equation with the finite difference method and has support for domain truncation techniques, several boundary conditions, and the modelling of sources and receivers given a user defined acquisition geometry. The architecture of Simwave is designed for applications with geophysical exploration in mind. Its Python front-end enables straightforward integration with many existing Python scientific libraries for the composition of more complex workflows and applications (e.g., migration and inversion problems). Its back-end is implemented in C, enabling performance portability across a range of computing hardware and compilers including both CPUs and GPUs. Simwave also provides non-optimized versions of the algorithms, which can be used as benchmarks for high-performance computing systems, serving as a proxy application for actual production solvers used by the geophysical exploration industry for the identification of Oil and Gas reservoirs.

Simwave是一个开源软件包，用于二维或三维领域的波浪模拟。它用有限差分法求解恒定和变密度声波方程，并支持域截断技术、几种边界条件以及给定用户定义的采集几何形状的源和接收器建模。Simwave的架构是为考虑到地球物理勘探的应用程序而设计的。它的Python前端可以直接与许多现有的Python科学库集成，以组成更复杂的工作流和应用程序（例如，迁移和反转问题）。它的后端是用C语言实现的，这使得它能够在各种计算硬件和编译器（包括cpu和gpu）之间实现性能可移植性。Simwave还提供了算法的非优化版本，可作为高性能计算系统的基准，作为地球物理勘探行业用于识别油气储层的实际生产求解器的代理应用程序。

{"title":"Simwave: A finite difference simulator for acoustic waves propagation","authors":"Hermes Senger , Jaime Freire de Souza , João Baptista Dias Moreira , Keith Jared Roberts , Roussian di Ramos Alves Gaioso , Emílio Carlos Nelli Silva , Edson Satoshi Gomi","doi":"10.1016/j.acags.2025.100283","DOIUrl":"10.1016/j.acags.2025.100283","url":null,"abstract":"<div><div>Simwave is an open-source software package for wave simulations in 2D or 3D domains. It solves the constant and variable density acoustic wave equation with the finite difference method and has support for domain truncation techniques, several boundary conditions, and the modelling of sources and receivers given a user defined acquisition geometry. The architecture of Simwave is designed for applications with geophysical exploration in mind. Its Python front-end enables straightforward integration with many existing Python scientific libraries for the composition of more complex workflows and applications (e.g., migration and inversion problems). Its back-end is implemented in C, enabling performance portability across a range of computing hardware and compilers including both CPUs and GPUs. Simwave also provides non-optimized versions of the algorithms, which can be used as benchmarks for high-performance computing systems, serving as a proxy application for actual production solvers used by the geophysical exploration industry for the identification of Oil and Gas reservoirs.</div></div>","PeriodicalId":33804,"journal":{"name":"Applied Computing and Geosciences","volume":"27 ","pages":"Article 100283"},"PeriodicalIF":3.2,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145026991","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Automatic seismic fault detection and surface construction 自动地震断层检测和地表施工

IF 3.2 Q2 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Applied Computing and Geosciences

Pub Date : 2025-09-01 DOI: 10.1016/j.acags.2025.100287

Xin Liu , Xingyu Zhu , Xupeng He , Yuzhu Wang

This paper proposes an effective approach for automatically building the fault model based on the 3D seismic images via two steps of automatic seismic fault detection and fault surface construction. Automatic seismic fault detection is performed to automatically classify the seismic image into two phases of fault and background using a slightly revised deeplabv3_resnet50 architecture with pretrained parameters provided by PyTorch. The output of the automatic seismic fault detection is a binary image contains fault and background, where one fault may be separated into different fault segments, or several faults are connected with each other which need further distinguish. To reassemble these detected fault segments and construct the fault surface model, four steps are implemented including:1) a morphological workflow is used to separate all connected faults into separated fault segments; 2) the moving least square (MLS) method is used to fit each fault segments as a smooth, one-voxel thickness surface; 3) the weighted principle component analysis (WPCA) method is applied to calculate the normal vector of each surface voxel to judge whether two or more adjacent segments should be combined in one fault surface; 4) MLS method is applied again to fit all surface segments from one fault as an unique fault surface. The final output of the proposed method provides a fault model with well-defined, cleanly separated, labeled fault surfaces that is competent for structure modelling.

本文提出了一种基于三维地震图像自动建立断层模型的有效方法，该方法分为地震断层自动检测和断层表面构造两个步骤。使用PyTorch提供的预训练参数，使用稍微修改的deeplabv3_resnet50架构进行自动地震故障检测，将地震图像自动分类为故障和背景两个阶段。地震断层自动检测的输出是包含断层和背景的二值图像，其中一个断层可能被分割成不同的断层段，或者几个断层相互连接，需要进一步区分。为了对检测到的故障段进行重组并构建故障面模型，实现了四个步骤：1)使用形态学工作流将所有连接的故障分离成独立的故障段；2)采用移动最小二乘（MLS）方法拟合各断层段为光滑的单体素厚度面；3)采用加权主成分分析（WPCA）方法计算每个面素的法向量，判断是否需要在一个断层面上合并两个或多个相邻的断层段；4)再次应用MLS方法拟合一个断层的所有面段作为唯一的断层面。该方法的最终输出提供了一个断层模型，该模型具有定义良好，分离清晰，标记的断层面，可用于构造建模。

{"title":"Automatic seismic fault detection and surface construction","authors":"Xin Liu , Xingyu Zhu , Xupeng He , Yuzhu Wang","doi":"10.1016/j.acags.2025.100287","DOIUrl":"10.1016/j.acags.2025.100287","url":null,"abstract":"<div><div>This paper proposes an effective approach for automatically building the fault model based on the 3D seismic images via two steps of automatic seismic fault detection and fault surface construction. Automatic seismic fault detection is performed to automatically classify the seismic image into two phases of fault and background using a slightly revised deeplabv3_resnet50 architecture with pretrained parameters provided by PyTorch. The output of the automatic seismic fault detection is a binary image contains fault and background, where one fault may be separated into different fault segments, or several faults are connected with each other which need further distinguish. To reassemble these detected fault segments and construct the fault surface model, four steps are implemented including:1) a morphological workflow is used to separate all connected faults into separated fault segments; 2) the moving least square (MLS) method is used to fit each fault segments as a smooth, one-voxel thickness surface; 3) the weighted principle component analysis (WPCA) method is applied to calculate the normal vector of each surface voxel to judge whether two or more adjacent segments should be combined in one fault surface; 4) MLS method is applied again to fit all surface segments from one fault as an unique fault surface. The final output of the proposed method provides a fault model with well-defined, cleanly separated, labeled fault surfaces that is competent for structure modelling.</div></div>","PeriodicalId":33804,"journal":{"name":"Applied Computing and Geosciences","volume":"27 ","pages":"Article 100287"},"PeriodicalIF":3.2,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145044135","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Estimating aboveground biomass using environmental covariates and a machine-learning approach in the Lower Brazos River Basin, Texas, USA 利用环境协变量和机器学习方法估算美国德克萨斯州下布拉索斯河流域的地上生物量

IF 3.2 Q2 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Applied Computing and Geosciences

Pub Date : 2025-09-01 DOI: 10.1016/j.acags.2025.100289

Birhan Getachew Tikuye, Ram Lakhan Ray

Forest ecosystems play a pivotal role in global carbon sequestration, serving as essential carbon sinks for climate change mitigation, while also providing a range of ecosystem services such as seed dispersal, pollination, pest control, and habitat provisioning. This study aimed to estimate aboveground biomass density (AGBD) using environmental covariates and a machine learning approach from the Global Ecosystem Dynamics Investigation Light Detection And Ranging (GEDI-LiDAR) in the Lower Brazos River Watershed, Texas, USA. Specifically, GEDI Level 4A data from the National Aeronautics and Space Administration (NASA) Oak Ridge National Laboratory Distributed Active Archive Center (ORNL DAAC) was integrated with Landsat-9 Operational Land Imagery (OLI) and Shuttle Radar Topographic Mission (SRTM) data to enhance predictive accuracy for AGBD. Spectral indices, including the Normalized Difference Vegetation Index (NDVI) and Enhanced Vegetation Index (EVI), were derived from Landsat 9 to support AGBD prediction. Three machine learning models, such as Multivariate Adaptive Regression Splines (MARS), Random Forest (RF), and eXtreme Gradient Boosting (XGBoost), were deployed, with performance assessed using the coefficient of determination (R²), root mean square error (RMSE), and mean absolute error (MAE). Among the models, XGBoost achieved the highest predictive accuracy (R² = 0.43, RMSE = 31.03, MAE = 22.49). The modelling indicated that longitude, latitude, moisture stress indices (MSI), and digital elevation model (DEM) are among the critical predictors for AGBD. The mean AGBD across the watershed was estimated at 72.3 Mg ha^-1, corresponding to a total biomass of approximately 66.6 million tons. Evergreen forests showed the highest AGBD values at 110 Mg ha^-1, while cultivated lands averaged 33 Mg ha^-1. These findings highlight the effectiveness of integrating environmental covariates with machine learning to estimate AGBD from GEDI LiDAR across diverse ecosystems. This approach provides a robust tool for advancing carbon management and climate change mitigation efforts, while also supporting data-driven conservation planning in both forested and agricultural landscapes.

森林生态系统在全球固碳中发挥着关键作用，是减缓气候变化的基本碳汇，同时还提供一系列生态系统服务，如种子传播、授粉、虫害防治和栖息地供应。本研究旨在利用全球生态系统动态调查光探测和测距（GEDI-LiDAR）的环境协变量和机器学习方法估计美国德克萨斯州下布拉索斯河流域的地上生物量密度（AGBD）。具体来说，来自美国国家航空航天局（NASA）橡树岭国家实验室分布式主动档案中心（ORNL DAAC）的GEDI 4A级数据与Landsat-9作战陆地图像（OLI）和航天飞机雷达地形任务（SRTM）数据集成，以提高AGBD的预测精度。利用Landsat 9反演的归一化植被指数（NDVI）和增强植被指数（EVI）等光谱指数支持AGBD预测。部署了三种机器学习模型，如多元自适应样条回归（MARS）、随机森林（RF）和极端梯度增强（XGBoost），并使用决定系数（R2）、均方根误差（RMSE）和平均绝对误差（MAE）来评估性能。其中，XGBoost的预测准确率最高（R2 = 0.43, RMSE = 31.03, MAE = 22.49）。模拟结果表明，经度、纬度、水分应力指数（MSI）和数字高程模型（DEM）是AGBD的重要预测因子。整个流域的平均AGBD估计为72.3 Mg ha-1，相当于总生物量约为6660万吨。常绿森林的AGBD值最高，为110 Mg ha-1，而耕地平均为33 Mg ha-1。这些发现强调了将环境协变量与机器学习相结合，以估计GEDI激光雷达在不同生态系统中的AGBD的有效性。这一方法为推进碳管理和减缓气候变化工作提供了强有力的工具，同时也支持以数据为导向的森林和农业景观保护规划。

{"title":"Estimating aboveground biomass using environmental covariates and a machine-learning approach in the Lower Brazos River Basin, Texas, USA","authors":"Birhan Getachew Tikuye, Ram Lakhan Ray","doi":"10.1016/j.acags.2025.100289","DOIUrl":"10.1016/j.acags.2025.100289","url":null,"abstract":"<div><div>Forest ecosystems play a pivotal role in global carbon sequestration, serving as essential carbon sinks for climate change mitigation, while also providing a range of ecosystem services such as seed dispersal, pollination, pest control, and habitat provisioning. This study aimed to estimate aboveground biomass density (AGBD) using environmental covariates and a machine learning approach from the Global Ecosystem Dynamics Investigation Light Detection And Ranging (GEDI-LiDAR) in the Lower Brazos River Watershed, Texas, USA. Specifically, GEDI Level 4A data from the National Aeronautics and Space Administration (NASA) Oak Ridge National Laboratory Distributed Active Archive Center (ORNL DAAC) was integrated with Landsat-9 Operational Land Imagery (OLI) and Shuttle Radar Topographic Mission (SRTM) data to enhance predictive accuracy for AGBD. Spectral indices, including the Normalized Difference Vegetation Index (NDVI) and Enhanced Vegetation Index (EVI), were derived from Landsat 9 to support AGBD prediction. Three machine learning models, such as Multivariate Adaptive Regression Splines (MARS), Random Forest (RF), and eXtreme Gradient Boosting (XGBoost), were deployed, with performance assessed using the coefficient of determination (R<sup>2</sup>), root mean square error (RMSE), and mean absolute error (MAE). Among the models, XGBoost achieved the highest predictive accuracy (R<sup>2</sup> = 0.43, RMSE = 31.03, MAE = 22.49). The modelling indicated that longitude, latitude, moisture stress indices (MSI), and digital elevation model (DEM) are among the critical predictors for AGBD. The mean AGBD across the watershed was estimated at 72.3 Mg ha<sup>-1</sup>, corresponding to a total biomass of approximately 66.6 million tons. Evergreen forests showed the highest AGBD values at 110 Mg ha<sup>-1</sup>, while cultivated lands averaged 33 Mg ha<sup>-1</sup>. These findings highlight the effectiveness of integrating environmental covariates with machine learning to estimate AGBD from GEDI LiDAR across diverse ecosystems. This approach provides a robust tool for advancing carbon management and climate change mitigation efforts, while also supporting data-driven conservation planning in both forested and agricultural landscapes.</div></div>","PeriodicalId":33804,"journal":{"name":"Applied Computing and Geosciences","volume":"27 ","pages":"Article 100289"},"PeriodicalIF":3.2,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145104692","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0