Artificial Intelligence in Geosciences最新文献_第8页

Automatic classification of Carbonatic thin sections by computer vision techniques and one-vs-all models 基于计算机视觉技术和一对一模型的碳酸盐岩薄片自动分类

Artificial Intelligence in Geosciences

Pub Date : 2025-06-01 Epub Date: 2025-06-02 DOI: 10.1016/j.aiig.2025.100117

Elisangela L. Faria , Rayan Barbosa , Juliana M. Coelho , Thais F. Matos , Bernardo C.C. Santos , J.L. Gonzalez , Clécio R. Bom , Márcio P. de Albuquerque , P.J. Russano , Marcelo P. de Albuquerque

Convolutional neural networks have been widely used for analyzing image data in industry, especially in the oil and gas area. Brazil has an extensive hydrocarbon reserve on its coast and has also benefited from these neural network models. Image data from petrographic thin section can be essential to provide information about reservoir quality, highlighting important features such as carbonate lithology. However, the automatic identification of lithology in reservoir rocks is still a significant challenge, mainly due to the heterogeneity that is part of the lithologies of the Brazilian pre-salt. Within this context, this work presents an approach using one-class or specialist models to identify four classes of lithology present in reservoir rocks in the Brazilian pre-salt. The proposed methodology had the challenge of dealing with a small number of images for training the neural networks, in addition to the complexity involved in the analyzed data. An auto-machine learning tool called AutoKeras was used to define the hyperparameters of the implemented models. The results found were satisfactory and presented an accuracy greater than 70% for image samples belonging to other wells not seen during the model building, which increases the applicability of the implemented model. Finally, a comparison was made between the proposed methodology and multiple-class models, demonstrating the superiority of one-class models.

卷积神经网络已广泛应用于工业领域，特别是油气领域的图像数据分析。巴西在其沿海地区拥有丰富的碳氢化合物储量，也受益于这些神经网络模型。来自岩石薄片的图像数据对于提供储层质量信息至关重要，突出了碳酸盐岩岩性等重要特征。然而，储层岩性的自动识别仍然是一个重大挑战，这主要是由于巴西盐下地层岩性的非均质性。在此背景下，本工作提出了一种使用一类或专业模型来识别巴西盐下储层岩石中存在的四类岩性的方法。除了分析数据的复杂性外，所提出的方法还面临着处理少量图像以训练神经网络的挑战。使用名为AutoKeras的自动机器学习工具来定义实现模型的超参数。结果令人满意，对于模型构建过程中未看到的其他井的图像样本，其精度大于70%，提高了所实现模型的适用性。最后，将该方法与多类模型进行了比较，证明了单类模型的优越性。

{"title":"Automatic classification of Carbonatic thin sections by computer vision techniques and one-vs-all models","authors":"Elisangela L. Faria , Rayan Barbosa , Juliana M. Coelho , Thais F. Matos , Bernardo C.C. Santos , J.L. Gonzalez , Clécio R. Bom , Márcio P. de Albuquerque , P.J. Russano , Marcelo P. de Albuquerque","doi":"10.1016/j.aiig.2025.100117","DOIUrl":"10.1016/j.aiig.2025.100117","url":null,"abstract":"<div><div>Convolutional neural networks have been widely used for analyzing image data in industry, especially in the oil and gas area. Brazil has an extensive hydrocarbon reserve on its coast and has also benefited from these neural network models. Image data from petrographic thin section can be essential to provide information about reservoir quality, highlighting important features such as carbonate lithology. However, the automatic identification of lithology in reservoir rocks is still a significant challenge, mainly due to the heterogeneity that is part of the lithologies of the Brazilian pre-salt. Within this context, this work presents an approach using one-class or specialist models to identify four classes of lithology present in reservoir rocks in the Brazilian pre-salt. The proposed methodology had the challenge of dealing with a small number of images for training the neural networks, in addition to the complexity involved in the analyzed data. An auto-machine learning tool called AutoKeras was used to define the hyperparameters of the implemented models. The results found were satisfactory and presented an accuracy greater than 70% for image samples belonging to other wells not seen during the model building, which increases the applicability of the implemented model. Finally, a comparison was made between the proposed methodology and multiple-class models, demonstrating the superiority of one-class models.</div></div>","PeriodicalId":100124,"journal":{"name":"Artificial Intelligence in Geosciences","volume":"6 1","pages":"Article 100117"},"PeriodicalIF":0.0,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144261331","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

Identification of interlayer and connectivity analysis based on machine learning and production data: A case study from M oilfield 基于机器学习和生产数据的层间识别和连通性分析：以M油田为例

Artificial Intelligence in Geosciences

Pub Date : 2025-06-01 Epub Date: 2025-05-09 DOI: 10.1016/j.aiig.2025.100119

Xiaoshuai Wu , Yuanliang Zhao , Jianpeng Zhao , Shichen Shuai , Bing Yu , Junqing Rong , Hui Chen

Interlayer is an important factor affecting the distribution of remaining oil. Accurate identification of interlayer distribution is of great significance in guiding oilfield production and development. However, the traditional method of identifying interlayers has some limitations: (1) Due to the existence of overlaps in the cross plot for different categories of interlayers, it is difficult to establish a determined model to classify the type of interlayer; (2) Traditional identification methods only use two or three logging curves to identify the types of interlayers, making it difficult to fully utilize the information of the logging curves, the recognition accuracy will be greatly reduced; (3) For a large number of complex logging data, interlayer identification is time-consuming and labor-intensive. Based on the existing well area data such as logging data and core data, this paper uses machine learning method to quantitatively identify the interlayers in the single well layer of CⅢ sandstone group in the M oilfield. Through the comparison of various classifiers, it is found that the decision tree method has the best applicability and the highest accuracy in the study area. Based on single well identification of interlayers, the continuity of well interval interlayers in the study area is analyzed according to the horizontal well. Finally, the influence of the continuity of interlayers on the distribution of remaining oil is verified by the spatial distribution characteristics of interlayers combined with the production situation of the M oilfield.

层间是影响剩余油分布的重要因素。准确识别层间分布对指导油田生产和开发具有重要意义。然而，传统的中间层识别方法存在一定的局限性：(1)由于不同类别的中间层在交叉图中存在重叠，难以建立确定的模型对中间层类型进行分类；(2)传统识别方法仅利用2条或3条测井曲线识别夹层类型，难以充分利用测井曲线信息，识别精度将大大降低；(3)对于大量复杂的测井资料，层间识别费时费力。本文基于M油田CⅢ砂岩群单井层间的测井、岩心等现有井区资料，采用机器学习方法对CⅢ砂岩群单井层间进行定量识别。通过对各种分类器的比较，发现决策树方法在研究区域具有最好的适用性和最高的准确率。在单井层间识别的基础上，根据水平井分析了研究区井段层间的连续性。最后，结合M油田的生产情况，通过层间空间分布特征验证了层间连续性对剩余油分布的影响。

{"title":"Identification of interlayer and connectivity analysis based on machine learning and production data: A case study from M oilfield","authors":"Xiaoshuai Wu , Yuanliang Zhao , Jianpeng Zhao , Shichen Shuai , Bing Yu , Junqing Rong , Hui Chen","doi":"10.1016/j.aiig.2025.100119","DOIUrl":"10.1016/j.aiig.2025.100119","url":null,"abstract":"<div><div>Interlayer is an important factor affecting the distribution of remaining oil. Accurate identification of interlayer distribution is of great significance in guiding oilfield production and development. However, the traditional method of identifying interlayers has some limitations: (1) Due to the existence of overlaps in the cross plot for different categories of interlayers, it is difficult to establish a determined model to classify the type of interlayer; (2) Traditional identification methods only use two or three logging curves to identify the types of interlayers, making it difficult to fully utilize the information of the logging curves, the recognition accuracy will be greatly reduced; (3) For a large number of complex logging data, interlayer identification is time-consuming and labor-intensive. Based on the existing well area data such as logging data and core data, this paper uses machine learning method to quantitatively identify the interlayers in the single well layer of CⅢ sandstone group in the M oilfield. Through the comparison of various classifiers, it is found that the decision tree method has the best applicability and the highest accuracy in the study area. Based on single well identification of interlayers, the continuity of well interval interlayers in the study area is analyzed according to the horizontal well. Finally, the influence of the continuity of interlayers on the distribution of remaining oil is verified by the spatial distribution characteristics of interlayers combined with the production situation of the M oilfield.</div></div>","PeriodicalId":100124,"journal":{"name":"Artificial Intelligence in Geosciences","volume":"6 1","pages":"Article 100119"},"PeriodicalIF":0.0,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143936977","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

A new integrated neurosymbolic approach for crop-yield prediction using environmental data and satellite imagery at field scale 利用环境数据和卫星图像进行作物产量预测的一种新的综合神经符号方法

Artificial Intelligence in Geosciences

Pub Date : 2025-06-01 Epub Date: 2025-05-26 DOI: 10.1016/j.aiig.2025.100125

Khadija Meghraoui , Teeradaj Racharak , Kenza Ait El Kadi , Saloua Bensiali , Imane Sebari

Crop-yield is a crucial metric in agriculture, essential for effective sector management and improving the overall production process. This indicator is heavily influenced by numerous environmental factors, particularly those related to soil and climate, which present a challenging task due to the complex interactions involved. In this paper, we introduce a novel integrated neurosymbolic framework that combines knowledge-based approaches with sensor data for crop-yield prediction. This framework merges predictions from vectors generated by modeling environmental factors using a newly developed ontology focused on key elements and evaluates this ontology using quantitative methods, specifically representation learning techniques, along with predictions derived from remote sensing imagery. We tested our proposed methodology on a public dataset centered on corn, aiming to predict crop-yield. Our developed smart model achieved promising results in terms of crop-yield prediction, with a root mean squared error (RMSE) of 1.72, outperforming the baseline models. The ontology-based approach achieved an RMSE of 1.73, while the remote sensing-based method yielded an RMSE of 1.77. This confirms the superior performance of our proposed approach over those using single modalities. This integrated neurosymbolic approach demonstrates that the fusion of statistical and symbolic artificial intelligence (AI) represents a significant advancement in agricultural applications. It is particularly effective for crop-yield prediction at the field scale, thus facilitating more informed decision-making in advanced agricultural practices. Additionally, it is acknowledged that results might be further improved by incorporating more detailed ontological knowledge and testing the model with higher-resolution imagery to enhance prediction accuracy.

作物产量是农业的一个关键指标，对有效的部门管理和改善整个生产过程至关重要。这一指标受到许多环境因素的严重影响，特别是与土壤和气候有关的因素，由于涉及复杂的相互作用，这是一项具有挑战性的任务。在本文中，我们介绍了一种新的集成神经符号框架，该框架将基于知识的方法与传感器数据相结合，用于作物产量预测。该框架使用新开发的专注于关键元素的本体对环境因素建模产生的向量进行预测，并使用定量方法（特别是表示学习技术）以及来自遥感图像的预测对该本体进行评估。我们在一个以玉米为中心的公共数据集上测试了我们提出的方法，旨在预测作物产量。我们开发的智能模型在作物产量预测方面取得了令人满意的结果，其均方根误差（RMSE）为1.72，优于基线模型。基于本体的方法RMSE为1.73，而基于遥感的方法RMSE为1.77。这证实了我们提出的方法优于使用单一模式的方法。这种综合神经符号方法表明，统计和符号人工智能（AI）的融合代表了农业应用的重大进步。它对田间规模的作物产量预测特别有效，从而促进在先进农业实践中做出更明智的决策。此外，我们还认识到，通过结合更详细的本体论知识和用更高分辨率的图像测试模型来提高预测精度，结果可能会进一步改善。

{"title":"A new integrated neurosymbolic approach for crop-yield prediction using environmental data and satellite imagery at field scale","authors":"Khadija Meghraoui , Teeradaj Racharak , Kenza Ait El Kadi , Saloua Bensiali , Imane Sebari","doi":"10.1016/j.aiig.2025.100125","DOIUrl":"10.1016/j.aiig.2025.100125","url":null,"abstract":"<div><div>Crop-yield is a crucial metric in agriculture, essential for effective sector management and improving the overall production process. This indicator is heavily influenced by numerous environmental factors, particularly those related to soil and climate, which present a challenging task due to the complex interactions involved. In this paper, we introduce a novel integrated neurosymbolic framework that combines knowledge-based approaches with sensor data for crop-yield prediction. This framework merges predictions from vectors generated by modeling environmental factors using a newly developed ontology focused on key elements and evaluates this ontology using quantitative methods, specifically representation learning techniques, along with predictions derived from remote sensing imagery. We tested our proposed methodology on a public dataset centered on corn, aiming to predict crop-yield. Our developed smart model achieved promising results in terms of crop-yield prediction, with a root mean squared error (RMSE) of 1.72, outperforming the baseline models. The ontology-based approach achieved an RMSE of 1.73, while the remote sensing-based method yielded an RMSE of 1.77. This confirms the superior performance of our proposed approach over those using single modalities. This integrated neurosymbolic approach demonstrates that the fusion of statistical and symbolic artificial intelligence (AI) represents a significant advancement in agricultural applications. It is particularly effective for crop-yield prediction at the field scale, thus facilitating more informed decision-making in advanced agricultural practices. Additionally, it is acknowledged that results might be further improved by incorporating more detailed ontological knowledge and testing the model with higher-resolution imagery to enhance prediction accuracy.</div></div>","PeriodicalId":100124,"journal":{"name":"Artificial Intelligence in Geosciences","volume":"6 1","pages":"Article 100125"},"PeriodicalIF":0.0,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144195736","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

Convolutional sparse coding network for sparse seismic time-frequency representation 用于稀疏地震时频表示的卷积稀疏编码网络

Artificial Intelligence in Geosciences

Pub Date : 2025-06-01 Epub Date: 2024-11-04 DOI: 10.1016/j.aiig.2024.100104

Qiansheng Wei , Zishuai Li , Haonan Feng , Yueying Jiang , Yang Yang , Zhiguo Wang

Seismic time-frequency (TF) transforms are essential tools in reservoir interpretation and signal processing, particularly for characterizing frequency variations in non-stationary seismic data. Recently, sparse TF transforms, which leverage sparse coding (SC), have gained significant attention in the geosciences due to their ability to achieve high TF resolution. However, the iterative approaches typically employed in sparse TF transforms are computationally intensive, making them impractical for real seismic data analysis. To address this issue, we propose an interpretable convolutional sparse coding (CSC) network to achieve high TF resolution. The proposed model is generated based on the traditional short-time Fourier transform (STFT) transform and a modified UNet, named ULISTANet. In this design, we replace the conventional convolutional layers of the UNet with learnable iterative shrinkage thresholding algorithm (LISTA) blocks, a specialized form of CSC. The LISTA block, which evolves from the traditional iterative shrinkage thresholding algorithm (ISTA), is optimized for extracting sparse features more effectively. Furthermore, we create a synthetic dataset featuring complex frequency-modulated signals to train ULISTANet. Finally, the proposed method's performance is subsequently validated using both synthetic and field data, demonstrating its potential for enhanced seismic data analysis.

地震时频（TF）变换是储层解释和信号处理的重要工具，特别是用于描述非稳态地震数据中的频率变化。最近，利用稀疏编码（SC）的稀疏时频变换因其实现高时频分辨率的能力而在地球科学领域备受关注。然而，稀疏 TF 变换通常采用的迭代方法需要大量计算，因此在实际地震数据分析中并不实用。为解决这一问题，我们提出了一种可解释卷积稀疏编码（CSC）网络，以实现高 TF 分辨率。我们提出的模型是基于传统的短时傅立叶变换（STFT）和改进的 UNet（名为 ULISTANet）生成的。在这一设计中，我们用可学习的迭代收缩阈值算法（LISTA）块（一种专门的 CSC 形式）取代了 UNet 的传统卷积层。LISTA 块由传统的迭代收缩阈值算法（ISTA）演化而来，经过优化，能更有效地提取稀疏特征。此外，我们还创建了一个以复杂频率调制信号为特征的合成数据集来训练 ULISTANet。最后，我们利用合成数据和野外数据对所提出方法的性能进行了验证，证明了该方法在增强地震数据分析方面的潜力。

{"title":"Convolutional sparse coding network for sparse seismic time-frequency representation","authors":"Qiansheng Wei , Zishuai Li , Haonan Feng , Yueying Jiang , Yang Yang , Zhiguo Wang","doi":"10.1016/j.aiig.2024.100104","DOIUrl":"10.1016/j.aiig.2024.100104","url":null,"abstract":"<div><div>Seismic time-frequency (TF) transforms are essential tools in reservoir interpretation and signal processing, particularly for characterizing frequency variations in non-stationary seismic data. Recently, sparse TF transforms, which leverage sparse coding (SC), have gained significant attention in the geosciences due to their ability to achieve high TF resolution. However, the iterative approaches typically employed in sparse TF transforms are computationally intensive, making them impractical for real seismic data analysis. To address this issue, we propose an interpretable convolutional sparse coding (CSC) network to achieve high TF resolution. The proposed model is generated based on the traditional short-time Fourier transform (STFT) transform and a modified UNet, named ULISTANet. In this design, we replace the conventional convolutional layers of the UNet with learnable iterative shrinkage thresholding algorithm (LISTA) blocks, a specialized form of CSC. The LISTA block, which evolves from the traditional iterative shrinkage thresholding algorithm (ISTA), is optimized for extracting sparse features more effectively. Furthermore, we create a synthetic dataset featuring complex frequency-modulated signals to train ULISTANet. Finally, the proposed method's performance is subsequently validated using both synthetic and field data, demonstrating its potential for enhanced seismic data analysis.</div></div>","PeriodicalId":100124,"journal":{"name":"Artificial Intelligence in Geosciences","volume":"6 1","pages":"Article 100104"},"PeriodicalIF":0.0,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142661128","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Optimizing zero-shot text-based segmentation of remote sensing imagery using SAM and Grounding DINO 基于SAM和ground DINO的遥感影像零射击文本分割优化

Artificial Intelligence in Geosciences

Pub Date : 2025-06-01 Epub Date: 2025-02-13 DOI: 10.1016/j.aiig.2025.100105

Mohanad Diab , Polychronis Kolokoussis , Maria Antonia Brovelli

The use of AI technologies in remote sensing (RS) tasks has been the focus of many individuals in both the professional and academic domains. Having more accessible interfaces and tools that allow people of little or no experience to intuitively interact with RS data of multiple formats is a potential provided by this integration. However, the use of AI and AI agents to help automate RS-related tasks is still in its infancy stage, with some frameworks and interfaces built on top of well-known vision language models (VLM) such as GPT-4, segment anything model (SAM), and grounding DINO. These tools do promise and draw guidelines on the potentials and limitations of existing solutions concerning the use of said models. In this work, the state of the art AI foundation models (FM) are reviewed and used in a multi-modal manner to ingest RS imagery input and perform zero-shot object detection using natural language. The natural language input is then used to define the classes or labels the model should look for, then, both inputs are fed to the pipeline. The pipeline presented in this work makes up for the shortcomings of the general knowledge FMs by stacking pre-processing and post-processing applications on top of the FMs; these applications include tiling to produce uniform patches of the original image for faster detection, outlier rejection of redundant bounding boxes using statistical and machine learning methods. The pipeline was tested with UAV, aerial and satellite images taken over multiple areas. The accuracy for the semantic segmentation showed improvement from the original 64% to approximately 80%–99% by utilizing the pipeline and techniques proposed in this work. GitHub Repository: MohanadDiab/LangRS.

人工智能技术在遥感（RS）任务中的应用一直是专业和学术领域许多人关注的焦点。这种集成提供了更易于访问的接口和工具，使很少或没有经验的人能够直观地与多种格式的RS数据进行交互。然而，使用人工智能和人工智能代理来帮助自动化rs相关任务仍处于起步阶段，一些框架和接口建立在知名的视觉语言模型（VLM）之上，如GPT-4、分段任何模型（SAM）和接地DINO。这些工具确实承诺并绘制了关于使用上述模型的现有解决方案的潜力和局限性的指导方针。在这项工作中，对最先进的人工智能基础模型（FM）进行了回顾，并以多模式方式使用它们来摄取RS图像输入并使用自然语言执行零射击目标检测。然后使用自然语言输入来定义模型应该查找的类或标签，然后将两个输入都提供给管道。本文提出的流水线通过在流水线上叠加预处理和后处理应用，弥补了一般知识模型的不足；这些应用包括平铺以产生原始图像的均匀补丁，以便更快地检测，使用统计和机器学习方法拒绝冗余边界框的异常值。该管道用无人机进行了测试，在多个地区拍摄了空中和卫星图像。利用本文提出的管道和技术，将语义分割的准确率从原来的64%提高到80%-99%左右。GitHub Repository: mohanadiab / langs。

{"title":"Optimizing zero-shot text-based segmentation of remote sensing imagery using SAM and Grounding DINO","authors":"Mohanad Diab , Polychronis Kolokoussis , Maria Antonia Brovelli","doi":"10.1016/j.aiig.2025.100105","DOIUrl":"10.1016/j.aiig.2025.100105","url":null,"abstract":"<div><div>The use of AI technologies in remote sensing (RS) tasks has been the focus of many individuals in both the professional and academic domains. Having more accessible interfaces and tools that allow people of little or no experience to intuitively interact with RS data of multiple formats is a potential provided by this integration. However, the use of AI and AI agents to help automate RS-related tasks is still in its infancy stage, with some frameworks and interfaces built on top of well-known vision language models (VLM) such as GPT-4, segment anything model (SAM), and grounding DINO. These tools do promise and draw guidelines on the potentials and limitations of existing solutions concerning the use of said models. In this work, the state of the art AI foundation models (FM) are reviewed and used in a multi-modal manner to ingest RS imagery input and perform zero-shot object detection using natural language. The natural language input is then used to define the classes or labels the model should look for, then, both inputs are fed to the pipeline. The pipeline presented in this work makes up for the shortcomings of the general knowledge FMs by stacking pre-processing and post-processing applications on top of the FMs; these applications include tiling to produce uniform patches of the original image for faster detection, outlier rejection of redundant bounding boxes using statistical and machine learning methods. The pipeline was tested with UAV, aerial and satellite images taken over multiple areas. The accuracy for the semantic segmentation showed improvement from the original 64% to approximately 80%–99% by utilizing the pipeline and techniques proposed in this work. <strong>GitHub Repository:</strong> <span><span>MohanadDiab/LangRS</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":100124,"journal":{"name":"Artificial Intelligence in Geosciences","volume":"6 1","pages":"Article 100105"},"PeriodicalIF":0.0,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143429918","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Applying deep learning to teleseismic phase detection and picking: PcP and PKiKP cases 将深度学习应用于远震相位检测和拾取：PcP和PKiKP案例

Artificial Intelligence in Geosciences

Pub Date : 2025-06-01 Epub Date: 2025-02-21 DOI: 10.1016/j.aiig.2025.100108

Congcong Yuan , Jie Zhang

The availability of a tremendous amount of seismic data demands seismological researchers to analyze seismic phases efficiently. Recently, deep learning algorithms exhibit a powerful capability of detecting and picking on P- and S-wave phases. However, it remains a challenge to effeciently process enormous teleseismic phases, which are crucial to probe Earth's interior structures and their dynamics. In this study, we propose a scheme to detect and pick teleseismic phases, such as seismic phase that reflects off the core-mantle boundary (i.e., PcP) and that reflects off the inner-core boundary (i.e., PKiKP), from a seismic dataset in Japan. The scheme consists of three steps: 1) latent phase traces are truncated from the whole seismogram with theoretical arrival times; 2) latent phases are recognized and evaluated by convolutional neural network (CNN) models; 3) arrivals of good or fair phase are picked with another CNN models. The testing detection result on 7386 seismograms shows that the scheme recognizes 92.15% and 94.13% of PcP and PKiKP phases. The testing picking result has a mean absolute error of 0.0742 s and 0.0636 s for the PcP and PKiKP phases, respectively. These seismograms were processed in just 5 min for phase detection and picking, demonstrating the efficiency of the proposed scheme in automatic teleseismic phase analysis.

大量地震资料的可用性要求地震学研究人员高效地分析地震相。最近，深度学习算法在探测和挑选P波和s波相位方面表现出强大的能力。然而，有效地处理巨大的远震相位仍然是一个挑战，而远震相位对于探测地球内部结构及其动力学至关重要。在这项研究中，我们提出了一种从日本地震数据集中检测和提取远震相位的方案，例如从核幔边界反射的地震相位（即PcP）和从内核边界反射的地震相位（即PKiKP）。该方案包括三个步骤：1)从具有理论到达时间的整个地震记录中截断潜相迹；2)利用卷积神经网络（CNN）模型对潜在相位进行识别和评估；3)用另一个CNN模型选择好的或一般的相位到达。7386张地震图的测试检测结果表明，该方案对PcP相位和PKiKP相位的识别率分别为92.15%和94.13%。PcP期和PKiKP期的平均绝对误差分别为0.0742 s和0.0636 s。这些地震记录在5分钟内进行了相位检测和拾取，证明了该方案在自动远震相位分析中的有效性。

{"title":"Applying deep learning to teleseismic phase detection and picking: PcP and PKiKP cases","authors":"Congcong Yuan , Jie Zhang","doi":"10.1016/j.aiig.2025.100108","DOIUrl":"10.1016/j.aiig.2025.100108","url":null,"abstract":"<div><div>The availability of a tremendous amount of seismic data demands seismological researchers to analyze seismic phases efficiently. Recently, deep learning algorithms exhibit a powerful capability of detecting and picking on P- and S-wave phases. However, it remains a challenge to effeciently process enormous teleseismic phases, which are crucial to probe Earth's interior structures and their dynamics. In this study, we propose a scheme to detect and pick teleseismic phases, such as seismic phase that reflects off the core-mantle boundary (i.e., PcP) and that reflects off the inner-core boundary (i.e., PKiKP), from a seismic dataset in Japan. The scheme consists of three steps: 1) latent phase traces are truncated from the whole seismogram with theoretical arrival times; 2) latent phases are recognized and evaluated by convolutional neural network (CNN) models; 3) arrivals of good or fair phase are picked with another CNN models. The testing detection result on 7386 seismograms shows that the scheme recognizes 92.15% and 94.13% of PcP and PKiKP phases. The testing picking result has a mean absolute error of 0.0742 s and 0.0636 s for the PcP and PKiKP phases, respectively. These seismograms were processed in just 5 min for phase detection and picking, demonstrating the efficiency of the proposed scheme in automatic teleseismic phase analysis.</div></div>","PeriodicalId":100124,"journal":{"name":"Artificial Intelligence in Geosciences","volume":"6 1","pages":"Article 100108"},"PeriodicalIF":0.0,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143488648","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Leveraging boosting machine learning for drilling rate of penetration (ROP) prediction based on drilling and petrophysical parameters 基于钻井和岩石物理参数，利用增强机器学习来预测钻进速度（ROP）

Artificial Intelligence in Geosciences

Pub Date : 2025-06-01 Epub Date: 2025-05-12 DOI: 10.1016/j.aiig.2025.100121

Raed H. Allawi , Watheq J. Al-Mudhafar , Mohammed A. Abbas , David A. Wood

Drilling optimization requires accurate drill bit rate-of-penetration (ROP) predictions. ROP decreases drilling time and costs and increases rig productivity. This study employs random forest (RF), gradient boosting modeling (GBM), extreme gradient boosting (XGBoost), and adaptive boosting (Adaboost) models to generate ROP predictions. The models use well data from a 3200-m segment across the stratigraphic column (Dibdibba to Zubair formations) of the large West Qurna oil field in Southern Iraq, penetrating 19 formations and four oil reservoirs. The reservoir sections are between 40 and 440 m thick and consist of both carbonate and clastic lithologies. The ROP predictive models were developed using 14 operational parameters: TVD, weight on bit (WOB), torque, effective circulating density (ECD), drilling rotation per minute (RPM), flow rate, standpipe pressure (SPP), bit size, total RPM, D exponent, gamma ray (GR), density, neutron, caliper, and discrete lithology distribution. Training and validation of the ROP models involves data compiled from three development wells. Applying Random subsampling, the compiled dataset was split into 85 % for training and 15 % for validation and testing. The test subgroup's measured and predicted ROP mismatch was assessed using root mean square error (RMSE) and coefficient of correlation (R²). The RF, GBM, and XGBoost models provide ROP predictions versus depth with low errors. Models with cross-validation that integrate data from three wells deliver more accurate ROP predictions than datasets from single well. The input variables' influences on ROP optimization identify the optimal value ranges for 14 operating parameters that help to increase drilling speed and reduce cost.

钻井优化需要精确的钻头钻速（ROP）预测。ROP减少了钻井时间和成本，提高了钻机生产率。本研究采用随机森林（RF）、梯度增强模型（GBM）、极端梯度增强（XGBoost）和自适应增强（Adaboost）模型来生成ROP预测。该模型使用了伊拉克南部West Qurna大型油田地层柱（Dibdibba至Zubair地层）3200米段的井数据，穿透了19个地层和4个油藏。储层剖面厚度在40 ~ 440 m之间，由碳酸盐岩和碎屑岩组成。ROP预测模型使用了14个操作参数：TVD、钻压（WOB）、扭矩、有效循环密度（ECD）、每分钟钻井转速（RPM）、流量、立管压力（SPP）、钻头尺寸、总RPM、D指数、伽马射线（GR）、密度、中子、井径器和离散岩性分布。ROP模型的训练和验证涉及三口开发井的数据。应用随机子抽样，编译的数据集被分成85%用于训练，15%用于验证和测试。采用均方根误差（RMSE）和相关系数（R2）对测试亚组测量和预测ROP失配进行评估。RF、GBM和XGBoost模型提供了相对深度的机械钻速预测，误差很小。与单井数据集相比，整合三口井数据的交叉验证模型可以提供更准确的ROP预测。输入变量对ROP优化的影响确定了14个操作参数的最佳取值范围，有助于提高钻井速度并降低成本。

{"title":"Leveraging boosting machine learning for drilling rate of penetration (ROP) prediction based on drilling and petrophysical parameters","authors":"Raed H. Allawi , Watheq J. Al-Mudhafar , Mohammed A. Abbas , David A. Wood","doi":"10.1016/j.aiig.2025.100121","DOIUrl":"10.1016/j.aiig.2025.100121","url":null,"abstract":"<div><div>Drilling optimization requires accurate drill bit rate-of-penetration (ROP) predictions. ROP decreases drilling time and costs and increases rig productivity. This study employs random forest (RF), gradient boosting modeling (GBM), extreme gradient boosting (XGBoost), and adaptive boosting (Adaboost) models to generate ROP predictions. The models use well data from a 3200-m segment across the stratigraphic column (Dibdibba to Zubair formations) of the large West Qurna oil field in Southern Iraq, penetrating 19 formations and four oil reservoirs. The reservoir sections are between 40 and 440 m thick and consist of both carbonate and clastic lithologies. The ROP predictive models were developed using 14 operational parameters: TVD, weight on bit (WOB), torque, effective circulating density (ECD), drilling rotation per minute (RPM), flow rate, standpipe pressure (SPP), bit size, total RPM, D exponent, gamma ray (GR), density, neutron, caliper, and discrete lithology distribution. Training and validation of the ROP models involves data compiled from three development wells. Applying Random subsampling, the compiled dataset was split into 85 % for training and 15 % for validation and testing. The test subgroup's measured and predicted ROP mismatch was assessed using root mean square error (RMSE) and coefficient of correlation (R<sup>2</sup>). The RF, GBM, and XGBoost models provide ROP predictions versus depth with low errors. Models with cross-validation that integrate data from three wells deliver more accurate ROP predictions than datasets from single well. The input variables' influences on ROP optimization identify the optimal value ranges for 14 operating parameters that help to increase drilling speed and reduce cost.</div></div>","PeriodicalId":100124,"journal":{"name":"Artificial Intelligence in Geosciences","volume":"6 1","pages":"Article 100121"},"PeriodicalIF":0.0,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143936979","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

Robust low frequency seismic bandwidth extension with a U-net and synthetic training data 鲁棒低频地震带宽扩展与U-net和综合训练数据

Artificial Intelligence in Geosciences

Pub Date : 2025-06-01 Epub Date: 2025-02-25 DOI: 10.1016/j.aiig.2025.100109

P. Zwartjes, J. Yoo

This work focuses on enhancing low frequency seismic data using a convolutional neural network trained on synthetic data. Traditional seismic data often lack both high and low frequencies, which are essential for detailed geological interpretation and various geophysical applications. Low frequency data is particularly valuable for reducing wavelet sidelobes and improving full waveform inversion (FWI). Conventional methods for bandwidth extension include seismic deconvolution and sparse inversion, which have limitations in recovering low frequencies. The study explores the potential of the U-net, which has been successful in other geophysical applications such as noise attenuation and seismic resolution enhancement. The novelty in our approach is that we do not rely on computationally expensive finite difference modelling to create training data. Instead, our synthetic training data is created from individual randomly perturbed events with variations in bandwidth, making it more adaptable to different data sets compared to previous deep learning methods. The method was tested on both synthetic and real seismic data, demonstrating effective low frequency reconstruction and sidelobe reduction. With a synthetic full waveform inversion to recover a velocity model and a seismic amplitude inversion to estimate acoustic impedance we demonstrate the validity and benefit of the proposed method. Overall, the study presents a robust approach to seismic bandwidth extension using deep learning, emphasizing the importance of diverse and well-designed but computationally inexpensive synthetic training data.

这项工作的重点是使用在合成数据上训练的卷积神经网络来增强低频地震数据。传统的地震数据往往缺乏高频和低频，这是详细的地质解释和各种地球物理应用所必需的。低频数据对于减少小波副瓣和改善全波形反演（FWI）特别有价值。传统的带宽扩展方法包括地震反褶积和稀疏反演，但在恢复低频方面存在局限性。该研究探索了U-net的潜力，U-net已经在其他地球物理应用中取得了成功，例如噪声衰减和地震分辨率提高。我们的方法的新颖之处在于，我们不依赖于计算昂贵的有限差分建模来创建训练数据。相反，我们的合成训练数据是由带宽变化的单个随机扰动事件创建的，与以前的深度学习方法相比，它更能适应不同的数据集。在合成地震和真实地震数据上进行了测试，结果表明该方法具有有效的低频重建和旁瓣抑制效果。通过合成全波形反演恢复速度模型和地震振幅反演估计声阻抗，验证了该方法的有效性和优越性。总的来说，该研究提出了一种利用深度学习扩展地震带宽的鲁棒方法，强调了多样化和精心设计但计算成本低廉的合成训练数据的重要性。

{"title":"Robust low frequency seismic bandwidth extension with a U-net and synthetic training data","authors":"P. Zwartjes, J. Yoo","doi":"10.1016/j.aiig.2025.100109","DOIUrl":"10.1016/j.aiig.2025.100109","url":null,"abstract":"<div><div>This work focuses on enhancing low frequency seismic data using a convolutional neural network trained on synthetic data. Traditional seismic data often lack both high and low frequencies, which are essential for detailed geological interpretation and various geophysical applications. Low frequency data is particularly valuable for reducing wavelet sidelobes and improving full waveform inversion (FWI). Conventional methods for bandwidth extension include seismic deconvolution and sparse inversion, which have limitations in recovering low frequencies. The study explores the potential of the U-net, which has been successful in other geophysical applications such as noise attenuation and seismic resolution enhancement. The novelty in our approach is that we do not rely on computationally expensive finite difference modelling to create training data. Instead, our synthetic training data is created from individual randomly perturbed events with variations in bandwidth, making it more adaptable to different data sets compared to previous deep learning methods. The method was tested on both synthetic and real seismic data, demonstrating effective low frequency reconstruction and sidelobe reduction. With a synthetic full waveform inversion to recover a velocity model and a seismic amplitude inversion to estimate acoustic impedance we demonstrate the validity and benefit of the proposed method. Overall, the study presents a robust approach to seismic bandwidth extension using deep learning, emphasizing the importance of diverse and well-designed but computationally inexpensive synthetic training data.</div></div>","PeriodicalId":100124,"journal":{"name":"Artificial Intelligence in Geosciences","volume":"6 1","pages":"Article 100109"},"PeriodicalIF":0.0,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143512149","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Robust high frequency seismic bandwidth extension with a deep neural network trained using synthetic data 利用合成数据训练的深度神经网络进行稳健的高频地震带宽扩展

Artificial Intelligence in Geosciences

Pub Date : 2024-12-01 Epub Date: 2024-02-03 DOI: 10.1016/j.aiig.2024.100071

Paul Zwartjes, Jewoo Yoo

Geophysicists interpreting seismic reflection data aim for the highest resolution possible as this facilitates the interpretation and discrimination of subtle geological features. Various deterministic methods based on Wiener filtering exist to increase the temporal frequency bandwidth and compress the seismic wavelet in a process called spectral shaping. Auto-encoder neural networks with convolutional layers have been applied to this problem, with encouraging results, but the problem of generalization to unseen data remains. Most published works have used supervised learning with training data constructed from field seismic data or synthetic seismic data generated based on measured well logs or based on seismic wavefield modelling. This leads to satisfactory results on datasets similar to the training data but requires re-training of the networks for unseen data with different characteristics. In this work seek to improve the generalization, not by experimenting with network architecture (we use a conventional U-net with some small modifications), but by adopting a different approach to creating the training data for the supervised learning process. Although the network is important, at this stage of development we see more improvement in prediction results by altering the design of the training data than by architectural changes. The approach we take is to create synthetic training data consisting of simple geometric shapes convolved with a seismic wavelet. We created a very diverse training dataset consisting of 9000 seismic images with between 5 and 300 seismic events resembling seismic reflections that have geophysically motived perturbations in terms of shape and character. The 2D U-net we have trained can boost robustly and recursively the dominant frequency by 50%. We demonstrate this on unseen field data with different bandwidths and signal-to-noise ratios. Additionally, this 2D U-net can handle non-stationary wavelets and overlapping events of different bandwidth without creating excessive ringing. It is also robust in the presence of noise. The significance of this result is that it simplifies the effort of bandwidth extension and demonstrates the usefulness of auto-encoder neural network for geophysical data processing.

地球物理学家在解释地震反射数据时，力求获得尽可能高的分辨率，因为这有助于解释和辨别微妙的地质特征。目前有各种基于维纳滤波的确定性方法，用于增加时间频率带宽和压缩地震小波，这一过程被称为频谱整形。带有卷积层的自动编码器神经网络已被应用于这一问题，并取得了令人鼓舞的成果，但仍存在对未见数据进行泛化的问题。大多数已发表的著作都采用了监督学习方法，训练数据由现场地震数据或根据测井记录或地震波场建模生成的合成地震数据构建。这在与训练数据类似的数据集上取得了令人满意的结果，但需要针对具有不同特征的未见数据重新训练网络。在这项工作中，我们不是通过试验网络结构（我们使用传统的 U 型网络，并做了一些小的修改），而是通过采用不同的方法来为监督学习过程创建训练数据，从而提高泛化能力。尽管网络很重要，但在目前的开发阶段，我们发现改变训练数据的设计比改变结构更能改善预测结果。我们采用的方法是创建由简单几何形状与地震小波卷积组成的合成训练数据。我们创建了一个非常多样化的训练数据集，由 9000 个地震图像组成，其中包含 5 到 300 个地震事件，这些地震事件类似于地震反射，在形状和特征方面具有地球物理动机扰动。我们训练的二维 U-net 可以将主频稳健地递增 50%。我们在不同带宽和信噪比的未见现场数据上演示了这一点。此外，这种二维 U-net 还能处理非稳态小波和不同带宽的重叠事件，而不会产生过度振铃。此外，它还能在出现噪声时保持稳定。这一结果的意义在于，它简化了扩展带宽的工作，并证明了自动编码器神经网络在地球物理数据处理中的实用性。

{"title":"Robust high frequency seismic bandwidth extension with a deep neural network trained using synthetic data","authors":"Paul Zwartjes, Jewoo Yoo","doi":"10.1016/j.aiig.2024.100071","DOIUrl":"https://doi.org/10.1016/j.aiig.2024.100071","url":null,"abstract":"<div><p>Geophysicists interpreting seismic reflection data aim for the highest resolution possible as this facilitates the interpretation and discrimination of subtle geological features. Various deterministic methods based on Wiener filtering exist to increase the temporal frequency bandwidth and compress the seismic wavelet in a process called spectral shaping. Auto-encoder neural networks with convolutional layers have been applied to this problem, with encouraging results, but the problem of generalization to unseen data remains. Most published works have used supervised learning with training data constructed from field seismic data or synthetic seismic data generated based on measured well logs or based on seismic wavefield modelling. This leads to satisfactory results on datasets similar to the training data but requires re-training of the networks for unseen data with different characteristics. In this work seek to improve the generalization, not by experimenting with network architecture (we use a conventional U-net with some small modifications), but by adopting a different approach to creating the training data for the supervised learning process. Although the network is important, at this stage of development we see more improvement in prediction results by altering the design of the training data than by architectural changes. The approach we take is to create synthetic training data consisting of simple geometric shapes convolved with a seismic wavelet. We created a very diverse training dataset consisting of 9000 seismic images with between 5 and 300 seismic events resembling seismic reflections that have geophysically motived perturbations in terms of shape and character. The 2D U-net we have trained can boost robustly and recursively the dominant frequency by 50%. We demonstrate this on unseen field data with different bandwidths and signal-to-noise ratios. Additionally, this 2D U-net can handle non-stationary wavelets and overlapping events of different bandwidth without creating excessive ringing. It is also robust in the presence of noise. The significance of this result is that it simplifies the effort of bandwidth extension and demonstrates the usefulness of auto-encoder neural network for geophysical data processing.</p></div>","PeriodicalId":100124,"journal":{"name":"Artificial Intelligence in Geosciences","volume":"5 ","pages":"Article 100071"},"PeriodicalIF":0.0,"publicationDate":"2024-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2666544124000121/pdfft?md5=c77a55aa6f15caf05f55e0608bb383f7&pid=1-s2.0-S2666544124000121-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139738330","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Thank you reviewers! 谢谢各位审稿人！

Artificial Intelligence in Geosciences

Pub Date : 2024-12-01 Epub Date: 2024-02-21 DOI: 10.1016/j.aiig.2024.100074

引用次数: 0