Artificial Intelligence in Geosciences最新文献_第5页

Comparison of processing speed of NRS-ANN hybrid and ANN models for oil production rate estimation of reservoir under waterflooding 水驱油藏采油速度估计的神经网络-神经网络混合模型与神经网络模型处理速度比较

Artificial Intelligence in Geosciences

Pub Date : 2025-06-24 DOI: 10.1016/j.aiig.2025.100139

Paul Theophily Nsulangi , Werneld Egno Ngongi , John Mbogo Kafuku , Guan Zhen Liang

This study compared the predictive performance and processing speed of an artificial neural network (ANN) and a hybrid of a numerical reservoir simulation (NRS) and artificial neural network (NRS-ANN) models in estimating the oil production rate of the ZH86 reservoir block under waterflood recovery. The historical input variables: reservoir pressure, reservoir pore volume containing hydrocarbons, reservoir pore volume containing water and reservoir water injection rate used as inputs for ANN models. To create the NRS-ANN hybrid models, 314 data sets extracted from the NRS model, which included reservoir pressure, reservoir pore volume containing hydrocarbons, reservoir pore volume containing water and reservoir water injection rate were used. The output of the models was the historical oil production rate (HOPR in m³ per day) recorded from the ZH86 reservoir block. Models were developed using MATLAB R2021a and trained with 25 models in three replicate conditions (2, 4 and 6), each at 1000 epochs. A comparative analysis indicated that, for all 25 models, the ANN outperformed the NRS-ANN in terms of processing speed and prediction performance. ANN models achieved an average of R² and MAE of 0.8433 and 8.0964 m³/day values, respectively, while NRS-ANN hybrid models achieved an average of R² and MAE of 0.7828 and 8.2484 m³/day values, respectively. In addition, ANN models achieved a processing speed of 49 epochs/sec, 32 epochs/sec, and 24 epochs/sec after 2, 4, and 6 replicates, respectively. Whereas the NRS-ANN hybrid models achieved lower average processing speeds of 45 epochs/sec, 23 epochs/sec and 20 epochs/sec. In addition, the ANN optimal model outperforms the NRS-ANN model in terms of both processing speed and accuracy. The ANN optimal model achieved a speed of 336.44 epochs/sec, compared to the NRS-ANN hybrid optimal model, which achieved a speed of 52.16 epochs/sec. The ANN optimal model achieved lower RMSE and MAE values of 7.9291 m³/day and 5.3855 m³/day in the validation dataset compared with the hybrid ANS optimal model, which achieved 13.6821 m³/day and 9.2047 m³/day, respectively. The study also showed that the ANN optimal model consistently achieved higher R² values: 0.9472, 0.9284 and 0.9316 in the training, test and validation data sets. Whereas the NRS-ANN hybrid optimal yielded lower R² values of 0.8030, 0.8622 and 0.7776 for the training, testing and validation datasets. The study showed that ANN models are a more effective and reliable tool, as they balance both processing speed and accuracy in estimating the oil production rate of the ZH86 reservoir block under the waterflooding recovery method.

对比了人工神经网络模型（ANN）与数值油藏模拟模型（NRS）和人工神经网络模型（NRS-ANN）混合模型对ZH86油藏区块注水开采下产油量的预测性能和处理速度。历史输入变量：储层压力、含烃储层孔隙体积、含水储层孔隙体积和油藏注水速度作为人工神经网络模型的输入。为了建立NRS- ann混合模型，使用了从NRS模型中提取的314个数据集，包括储层压力、储层含烃孔隙体积、储层含水孔隙体积和储层注水速率。模型的输出是ZH86油藏区块记录的历史产油量（HOPR, m3 / d）。使用MATLAB R2021a开发模型，在3个重复条件（2、4、6）下对25个模型进行训练，每个条件1000次。对比分析表明，对于所有25个模型，人工神经网络在处理速度和预测性能方面都优于NRS-ANN。ANN模型的R2和MAE均值分别为0.8433和8.0964 m3/day，而NRS-ANN混合模型的R2和MAE均值分别为0.7828和8.2484 m3/day。在重复2次、4次和6次后，ANN模型的处理速度分别达到49次/秒、32次/秒和24次/秒。而NRS-ANN混合模型的平均处理速度较低，分别为45、23和20 epoch /sec。此外，ANN最优模型在处理速度和精度方面都优于NRS-ANN模型。神经网络优化模型的速度为336.44 epoch /sec，而NRS-ANN混合优化模型的速度为52.16 epoch /sec。在验证数据集中，ANN优化模型的RMSE和MAE值分别为7.9291 m3/day和5.3855 m3/day，而混合ANS优化模型的RMSE和MAE值分别为13.6821 m3/day和9.2047 m3/day。研究还表明，ANN最优模型在训练、测试和验证数据集中均获得较高的R2值，分别为0.9472、0.9284和0.9316。而NRS-ANN混合优化在训练、测试和验证数据集上产生的R2值较低，分别为0.8030、0.8622和0.7776。研究表明，在水驱采油方法下，人工神经网络模型在计算ZH86油藏区块产油量时兼顾了处理速度和准确性，是一种更有效、更可靠的工具。

{"title":"Comparison of processing speed of NRS-ANN hybrid and ANN models for oil production rate estimation of reservoir under waterflooding","authors":"Paul Theophily Nsulangi , Werneld Egno Ngongi , John Mbogo Kafuku , Guan Zhen Liang","doi":"10.1016/j.aiig.2025.100139","DOIUrl":"10.1016/j.aiig.2025.100139","url":null,"abstract":"<div><div>This study compared the predictive performance and processing speed of an artificial neural network (ANN) and a hybrid of a numerical reservoir simulation (NRS) and artificial neural network (NRS-ANN) models in estimating the oil production rate of the ZH86 reservoir block under waterflood recovery. The historical input variables: reservoir pressure, reservoir pore volume containing hydrocarbons, reservoir pore volume containing water and reservoir water injection rate used as inputs for ANN models. To create the NRS-ANN hybrid models, 314 data sets extracted from the NRS model, which included reservoir pressure, reservoir pore volume containing hydrocarbons, reservoir pore volume containing water and reservoir water injection rate were used. The output of the models was the historical oil production rate (HOPR in m<sup>3</sup> per day) recorded from the ZH86 reservoir block. Models were developed using MATLAB R2021a and trained with 25 models in three replicate conditions (2, 4 and 6), each at 1000 epochs. A comparative analysis indicated that, for all 25 models, the ANN outperformed the NRS-ANN in terms of processing speed and prediction performance. ANN models achieved an average of R<sup>2</sup> and MAE of 0.8433 and 8.0964 m<sup>3</sup>/day values, respectively, while NRS-ANN hybrid models achieved an average of R<sup>2</sup> and MAE of 0.7828 and 8.2484 m<sup>3</sup>/day values, respectively. In addition, ANN models achieved a processing speed of 49 epochs/sec, 32 epochs/sec, and 24 epochs/sec after 2, 4, and 6 replicates, respectively. Whereas the NRS-ANN hybrid models achieved lower average processing speeds of 45 epochs/sec, 23 epochs/sec and 20 epochs/sec. In addition, the ANN optimal model outperforms the NRS-ANN model in terms of both processing speed and accuracy. The ANN optimal model achieved a speed of 336.44 epochs/sec, compared to the NRS-ANN hybrid optimal model, which achieved a speed of 52.16 epochs/sec. The ANN optimal model achieved lower RMSE and MAE values of 7.9291 m<sup>3</sup>/day and 5.3855 m<sup>3</sup>/day in the validation dataset compared with the hybrid ANS optimal model, which achieved 13.6821 m<sup>3</sup>/day and 9.2047 m<sup>3</sup>/day, respectively. The study also showed that the ANN optimal model consistently achieved higher R<sup>2</sup> values: 0.9472, 0.9284 and 0.9316 in the training, test and validation data sets. Whereas the NRS-ANN hybrid optimal yielded lower R<sup>2</sup> values of 0.8030, 0.8622 and 0.7776 for the training, testing and validation datasets. The study showed that ANN models are a more effective and reliable tool, as they balance both processing speed and accuracy in estimating the oil production rate of the ZH86 reservoir block under the waterflooding recovery method.</div></div>","PeriodicalId":100124,"journal":{"name":"Artificial Intelligence in Geosciences","volume":"6 2","pages":"Article 100139"},"PeriodicalIF":0.0,"publicationDate":"2025-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144653505","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

Interpretable machine learning models for evaluating strength of ternary geopolymers 用于评估三元地聚合物强度的可解释机器学习模型

Artificial Intelligence in Geosciences

Pub Date : 2025-06-23 DOI: 10.1016/j.aiig.2025.100128

Junfei Zhang , Huisheng Cheng , Ninghui Sun , Zehui Huo , Junlin Chen

Ternary geopolymers incorporating multiple solid wastes such as steel slag (SS), fly ash (FA), and granulated blast furnace slag (GBFS) are considered environmentally friendly and exhibit enhanced performance. However, the mechanisms governing strength development and the design of optimal mixtures are not fully understood due to the complexity of their components. This study presents the development of four machine learning models—Artificial Neural Network (ANN), Support Vector Regression (SVR), Extremely Randomized Tree (ERT), and Gradient Boosting Regression (GBR)—for predicting the unconfined compressive strength (UCS) of ternary geopolymers. The models were trained using a dataset comprising 120 mixtures derived from laboratory tests. Shapley Additive Explanations analysis was employed to interpret the machine learning models and elucidate the influence of different components on the properties of ternary geopolymers. The results indicate that ANN exhibits the highest predictive accuracy for UCS (R = 0.949). Furthermore, the UCS of ternary geopolymers is most sensitive to the content of GBFS. This study provides valuable insights for optimizing the mix proportions in ternary blended geopolymer mixtures.

含有多种固体废物（如钢渣（SS）、粉煤灰（FA）和粒状高炉渣（GBFS））的三元地聚合物被认为是环保的，并表现出增强的性能。然而，由于其成分的复杂性，控制强度发展和最佳混合物设计的机制尚未完全了解。本研究提出了四种机器学习模型的发展-人工神经网络（ANN），支持向量回归（SVR），极度随机树（ERT）和梯度增强回归(GBR) -用于预测三元地聚合物的无侧限抗压强度（UCS）。这些模型使用由实验室测试得出的120种混合物组成的数据集进行训练。采用Shapley加性解释分析来解释机器学习模型，并阐明不同组分对三元地聚合物性质的影响。结果表明，人工神经网络对UCS的预测准确率最高（R = 0.949）。此外，三元地聚合物的UCS对GBFS的含量最为敏感。该研究为优化三元共混地聚合物混合物的混合比例提供了有价值的见解。

{"title":"Interpretable machine learning models for evaluating strength of ternary geopolymers","authors":"Junfei Zhang , Huisheng Cheng , Ninghui Sun , Zehui Huo , Junlin Chen","doi":"10.1016/j.aiig.2025.100128","DOIUrl":"10.1016/j.aiig.2025.100128","url":null,"abstract":"<div><div>Ternary geopolymers incorporating multiple solid wastes such as steel slag (SS), fly ash (FA), and granulated blast furnace slag (GBFS) are considered environmentally friendly and exhibit enhanced performance. However, the mechanisms governing strength development and the design of optimal mixtures are not fully understood due to the complexity of their components. This study presents the development of four machine learning models—Artificial Neural Network (ANN), Support Vector Regression (SVR), Extremely Randomized Tree (ERT), and Gradient Boosting Regression (GBR)—for predicting the unconfined compressive strength (UCS) of ternary geopolymers. The models were trained using a dataset comprising 120 mixtures derived from laboratory tests. Shapley Additive Explanations analysis was employed to interpret the machine learning models and elucidate the influence of different components on the properties of ternary geopolymers. The results indicate that ANN exhibits the highest predictive accuracy for UCS (R = 0.949). Furthermore, the UCS of ternary geopolymers is most sensitive to the content of GBFS. This study provides valuable insights for optimizing the mix proportions in ternary blended geopolymer mixtures.</div></div>","PeriodicalId":100124,"journal":{"name":"Artificial Intelligence in Geosciences","volume":"6 2","pages":"Article 100128"},"PeriodicalIF":0.0,"publicationDate":"2025-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144523230","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

On the application of machine learning algorithms in predicting the permeability of oil reservoirs 机器学习算法在油藏渗透率预测中的应用研究

Artificial Intelligence in Geosciences

Pub Date : 2025-06-03 DOI: 10.1016/j.aiig.2025.100126

Andrey V. Soromotin , Dmitriy A. Martyushev , João Luiz Junho Pereira

Permeability is one of the main oil reservoir characteristics. It affects potential oil production, well-completion technologies, the choice of enhanced oil recovery methods, and more. The methods used to determine and predict reservoir permeability have serious shortcomings. This article aims to refine and adapt machine learning techniques using historical data from hydrocarbon field development to evaluate and predict parameters such as the skin factor and permeability of the remote reservoir zone. The article analyzes data from 4045 wells tests in oil fields in the Perm Krai (Russia). An evaluation of the performance of different Machine Learning (ML) algorithms in the prediction of the well permeability is performed. Three different real datasets are used to train more than 20 machine learning regressors, whose hyperparameters are optimized using Bayesian Optimization (BO). The resulting models demonstrate significantly better predictive performance compared to traditional methods and the best ML model found is one that never was applied before to this problem. The permeability prediction model is characterized by a high R² adjusted value of 0.799. A promising approach is the integration of machine learning methods and the use of pressure recovery curves to estimate permeability in real-time. The work is unique for its approach to predicting pressure recovery curves during well operation without stopping wells, providing primary data for interpretation. These innovations are exclusive and can improve the accuracy of permeability forecasts. It also reduces well downtime associated with traditional well-testing procedures. The proposed methods pave the way for more efficient and cost-effective reservoir development, ultimately supporting better decision-making and resource optimization in oil production.

渗透率是油藏的主要特征之一。它会影响潜在的产油量、完井技术、提高采收率方法的选择等。目前用于确定和预测储层渗透率的方法存在严重缺陷。本文旨在利用油气田开发的历史数据来改进和适应机器学习技术，以评估和预测偏远储层的表皮系数和渗透率等参数。本文分析了俄罗斯彼尔姆边疆区油田4045口试井的数据。对不同机器学习（ML）算法在预测井渗透率方面的性能进行了评估。使用三个不同的真实数据集训练20多个机器学习回归量，并使用贝叶斯优化（BO）对其超参数进行优化。与传统方法相比，结果模型显示出更好的预测性能，并且发现的最佳ML模型是以前从未应用于此问题的模型。渗透率预测模型具有较高的R2调整值（0.799）。一种很有前途的方法是结合机器学习方法和使用压力恢复曲线来实时估计渗透率。这项工作的独特之处在于，它可以在不停井的情况下预测井运行过程中的压力恢复曲线，为解释提供了原始数据。这些创新是独一无二的，可以提高渗透率预测的准确性。它还减少了与传统试井程序相关的井停工期。所提出的方法为更高效、更具成本效益的油藏开发铺平了道路，最终支持更好的石油生产决策和资源优化。

{"title":"On the application of machine learning algorithms in predicting the permeability of oil reservoirs","authors":"Andrey V. Soromotin , Dmitriy A. Martyushev , João Luiz Junho Pereira","doi":"10.1016/j.aiig.2025.100126","DOIUrl":"10.1016/j.aiig.2025.100126","url":null,"abstract":"<div><div>Permeability is one of the main oil reservoir characteristics. It affects potential oil production, well-completion technologies, the choice of enhanced oil recovery methods, and more. The methods used to determine and predict reservoir permeability have serious shortcomings. This article aims to refine and adapt machine learning techniques using historical data from hydrocarbon field development to evaluate and predict parameters such as the skin factor and permeability of the remote reservoir zone. The article analyzes data from 4045 wells tests in oil fields in the Perm Krai (Russia). An evaluation of the performance of different Machine Learning (ML) algorithms in the prediction of the well permeability is performed. Three different real datasets are used to train more than 20 machine learning regressors, whose hyperparameters are optimized using Bayesian Optimization (BO). The resulting models demonstrate significantly better predictive performance compared to traditional methods and the best ML model found is one that never was applied before to this problem. The permeability prediction model is characterized by a high R<sup>2</sup> adjusted value of 0.799. A promising approach is the integration of machine learning methods and the use of pressure recovery curves to estimate permeability in real-time. The work is unique for its approach to predicting pressure recovery curves during well operation without stopping wells, providing primary data for interpretation. These innovations are exclusive and can improve the accuracy of permeability forecasts. It also reduces well downtime associated with traditional well-testing procedures. The proposed methods pave the way for more efficient and cost-effective reservoir development, ultimately supporting better decision-making and resource optimization in oil production.</div></div>","PeriodicalId":100124,"journal":{"name":"Artificial Intelligence in Geosciences","volume":"6 2","pages":"Article 100126"},"PeriodicalIF":0.0,"publicationDate":"2025-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144330611","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 staged deep learning approach to spatial refinement in 3D temporal atmospheric transport 基于阶段深度学习的三维时空大气传输空间细化方法

Artificial Intelligence in Geosciences

Pub Date : 2025-06-01 DOI: 10.1016/j.aiig.2025.100120

M. Giselle Fernández-Godino , Wai Tong Chung , Akshay A. Gowardhan , Matthias Ihme , Qingkai Kong , Donald D. Lucas , Stephen C. Myers

High-resolution spatiotemporal simulations effectively capture the complexities of atmospheric plume dispersion in complex terrain. However, their high computational cost makes them impractical for applications requiring rapid responses or iterative processes, such as optimization, uncertainty quantification, or inverse modeling. To address this challenge, this work introduces the Dual-Stage Temporal Three-dimensional UNet Super-resolution (DST3D-UNet-SR) model, a highly efficient deep learning model for plume dispersion predictions. DST3D-UNet-SR is composed of two sequential modules: the temporal module (TM), which predicts the transient evolution of a plume in complex terrain from low-resolution temporal data, and the spatial refinement module (SRM), which subsequently enhances the spatial resolution of the TM predictions. We train DST3D-UNet-SR using a comprehensive dataset derived from high-resolution large eddy simulations (LES) of plume transport. We propose the DST3D-UNet-SR model to significantly accelerate LES of three-dimensional (3D) plume dispersion by three orders of magnitude. Additionally, the model demonstrates the ability to dynamically adapt to evolving conditions through the incorporation of new observational data, substantially improving prediction accuracy in high-concentration regions near the source.

高分辨率时空模拟有效地捕捉了复杂地形下大气羽散的复杂性。然而，它们的高计算成本使得它们不适合需要快速响应或迭代过程的应用，例如优化、不确定性量化或逆建模。为了应对这一挑战，本工作引入了双阶段时间三维UNet超分辨率（DST3D-UNet-SR）模型，这是一种用于羽散预测的高效深度学习模型。DST3D-UNet-SR由两个连续模块组成：时间模块（TM）和空间细化模块（SRM），前者从低分辨率时间数据预测复杂地形中羽流的瞬态演变，后者提高了TM预测的空间分辨率。我们使用来自羽流传输的高分辨率大涡模拟（LES）的综合数据集来训练DST3D-UNet-SR。我们提出了DST3D-UNet-SR模型，将三维羽散的LES显著加速了三个数量级。此外，该模型通过纳入新的观测数据，显示出动态适应不断变化的条件的能力，大大提高了源附近高浓度区域的预测精度。

{"title":"A staged deep learning approach to spatial refinement in 3D temporal atmospheric transport","authors":"M. Giselle Fernández-Godino , Wai Tong Chung , Akshay A. Gowardhan , Matthias Ihme , Qingkai Kong , Donald D. Lucas , Stephen C. Myers","doi":"10.1016/j.aiig.2025.100120","DOIUrl":"10.1016/j.aiig.2025.100120","url":null,"abstract":"<div><div>High-resolution spatiotemporal simulations effectively capture the complexities of atmospheric plume dispersion in complex terrain. However, their high computational cost makes them impractical for applications requiring rapid responses or iterative processes, such as optimization, uncertainty quantification, or inverse modeling. To address this challenge, this work introduces the Dual-Stage Temporal Three-dimensional UNet Super-resolution (DST3D-UNet-SR) model, a highly efficient deep learning model for plume dispersion predictions. DST3D-UNet-SR is composed of two sequential modules: the temporal module (TM), which predicts the transient evolution of a plume in complex terrain from low-resolution temporal data, and the spatial refinement module (SRM), which subsequently enhances the spatial resolution of the TM predictions. We train DST3D-UNet-SR using a comprehensive dataset derived from high-resolution large eddy simulations (LES) of plume transport. We propose the DST3D-UNet-SR model to significantly accelerate LES of three-dimensional (3D) plume dispersion by three orders of magnitude. Additionally, the model demonstrates the ability to dynamically adapt to evolving conditions through the incorporation of new observational data, substantially improving prediction accuracy in high-concentration regions near the source.</div></div>","PeriodicalId":100124,"journal":{"name":"Artificial Intelligence in Geosciences","volume":"6 1","pages":"Article 100120"},"PeriodicalIF":0.0,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144185115","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 description of rock thin sections: A web application 岩石薄片的自动描述：一个web应用程序

Artificial Intelligence in Geosciences

Pub Date : 2025-06-01 DOI: 10.1016/j.aiig.2025.100118

Stalyn Paucar, Christian Mejia-Escobar, Victor Collaguazo

The identification and characterization of rock types is a core activity in geology and related fields, including mining, petroleum, environmental science, industry, and construction. Traditionally, this task is performed by human specialists who analyze and describe the type, composition, texture, shape, and other properties of rock samples, whether collected in-situ or prepared in a laboratory. However, the process is subjective, dependent on the specialist’s experience, and time-consuming. This study proposes an artificial intelligence-based approach that combines computer vision and natural language processing to generate both textual and verbal descriptions from images of rock thin sections. A dataset of images and corresponding textual descriptions is used to train a hybrid deep learning model. Features extracted from the images using EfficientNetB7 are processed by a Transformer network to generate textual descriptions, which are then converted into verbal responses using a speech synthesis service. The experimental results show an accuracy of 0.892 and a BLEU score of 0.71. This model offers potential utility for research, professional, and academic applications and has been deployed as a web application for public use.

岩石类型的识别和表征是地质和相关领域的核心活动，包括采矿、石油、环境科学、工业和建筑。传统上，这项任务是由人类专家来完成的，他们分析和描述岩石样品的类型、成分、质地、形状和其他特性，无论是在现场收集还是在实验室制备。然而，这个过程是主观的，取决于专家的经验，而且很耗时。本研究提出了一种基于人工智能的方法，将计算机视觉和自然语言处理相结合，从岩石薄片图像中生成文本和口头描述。使用图像和相应文本描述的数据集来训练混合深度学习模型。使用effentnetb7从图像中提取的特征由Transformer网络处理以生成文本描述，然后使用语音合成服务将其转换为口头响应。实验结果表明，该方法的准确率为0.892，BLEU分数为0.71。该模型为研究、专业和学术应用程序提供了潜在的实用程序，并已作为公共使用的web应用程序部署。

{"title":"Automatic description of rock thin sections: A web application","authors":"Stalyn Paucar, Christian Mejia-Escobar, Victor Collaguazo","doi":"10.1016/j.aiig.2025.100118","DOIUrl":"10.1016/j.aiig.2025.100118","url":null,"abstract":"<div><div>The identification and characterization of rock types is a core activity in geology and related fields, including mining, petroleum, environmental science, industry, and construction. Traditionally, this task is performed by human specialists who analyze and describe the type, composition, texture, shape, and other properties of rock samples, whether collected in-situ or prepared in a laboratory. However, the process is subjective, dependent on the specialist’s experience, and time-consuming. This study proposes an artificial intelligence-based approach that combines computer vision and natural language processing to generate both textual and verbal descriptions from images of rock thin sections. A dataset of images and corresponding textual descriptions is used to train a hybrid deep learning model. Features extracted from the images using EfficientNetB7 are processed by a Transformer network to generate textual descriptions, which are then converted into verbal responses using a speech synthesis service. The experimental results show an accuracy of 0.892 and a BLEU score of 0.71. This model offers potential utility for research, professional, and academic applications and has been deployed as a web application for public use.</div></div>","PeriodicalId":100124,"journal":{"name":"Artificial Intelligence in Geosciences","volume":"6 1","pages":"Article 100118"},"PeriodicalIF":0.0,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144212094","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

Self-supervised multi-stage deep learning network for seismic data denoising 地震数据去噪的自监督多阶段深度学习网络

Artificial Intelligence in Geosciences

Pub Date : 2025-06-01 DOI: 10.1016/j.aiig.2025.100123

Omar M. Saad , Matteo Ravasi , Tariq Alkhalifah

Seismic data denoising is a critical process usually applied at various stages of the seismic processing workflow, as our ability to mitigate noise in seismic data affects the quality of our subsequent analyses. However, finding an optimal balance between preserving seismic signals and effectively reducing seismic noise presents a substantial challenge. In this study, we introduce a multi-stage deep learning model, trained in a self-supervised manner, designed specifically to suppress seismic noise while minimizing signal leakage. This model operates as a patch-based approach, extracting overlapping patches from the noisy data and converting them into 1D vectors for input. It consists of two identical sub-networks, each configured differently. Inspired by the transformer architecture, each sub-network features an embedded block that comprises two fully connected layers, which are utilized for feature extraction from the input patches. After reshaping, a multi-head attention module enhances the model’s focus on significant features by assigning higher attention weights to them. The key difference between the two sub-networks lies in the number of neurons within their fully connected layers. The first sub-network serves as a strong denoiser with a small number of neurons, effectively attenuating seismic noise; in contrast, the second sub-network functions as a signal-add-back model, using a larger number of neurons to retrieve some of the signal that was not preserved in the output of the first sub-network. The proposed model produces two outputs, each corresponding to one of the sub-networks, and both sub-networks are optimized simultaneously using the noisy data as the label for both outputs. Evaluations conducted on both synthetic and field data demonstrate the model’s effectiveness in suppressing seismic noise with minimal signal leakage, outperforming some benchmark methods.

地震数据去噪是一个关键的过程，通常应用于地震处理工作流程的各个阶段，因为我们减轻地震数据噪声的能力会影响我们后续分析的质量。然而，在保留地震信号和有效降低地震噪声之间找到最佳平衡是一个巨大的挑战。在本研究中，我们引入了一种多阶段深度学习模型，该模型以自监督的方式进行训练，专门用于抑制地震噪声，同时最大限度地减少信号泄漏。该模型是一种基于patch的方法，从噪声数据中提取重叠的patch，并将其转换为1D矢量进行输入。它由两个相同的子网组成，每个子网的配置不同。受变压器架构的启发，每个子网络都有一个嵌入式块，该块由两个完全连接的层组成，用于从输入补丁中提取特征。在重塑后，多头注意模块通过分配更高的注意权重来增强模型对重要特征的关注。这两个子网络的关键区别在于它们完全连接层中的神经元数量。第一个子网络作为强去噪器，神经元数量少，能有效地衰减地震噪声；相比之下，第二个子网络作为一个信号加回模型，使用更多的神经元来检索一些在第一个子网络的输出中没有保留的信号。所提出的模型产生两个输出，每个输出对应于一个子网络，并且两个子网络同时使用噪声数据作为两个输出的标签进行优化。对合成数据和现场数据的评估表明，该模型在以最小的信号泄漏抑制地震噪声方面是有效的，优于一些基准方法。

{"title":"Self-supervised multi-stage deep learning network for seismic data denoising","authors":"Omar M. Saad , Matteo Ravasi , Tariq Alkhalifah","doi":"10.1016/j.aiig.2025.100123","DOIUrl":"10.1016/j.aiig.2025.100123","url":null,"abstract":"<div><div>Seismic data denoising is a critical process usually applied at various stages of the seismic processing workflow, as our ability to mitigate noise in seismic data affects the quality of our subsequent analyses. However, finding an optimal balance between preserving seismic signals and effectively reducing seismic noise presents a substantial challenge. In this study, we introduce a multi-stage deep learning model, trained in a self-supervised manner, designed specifically to suppress seismic noise while minimizing signal leakage. This model operates as a patch-based approach, extracting overlapping patches from the noisy data and converting them into 1D vectors for input. It consists of two identical sub-networks, each configured differently. Inspired by the transformer architecture, each sub-network features an embedded block that comprises two fully connected layers, which are utilized for feature extraction from the input patches. After reshaping, a multi-head attention module enhances the model’s focus on significant features by assigning higher attention weights to them. The key difference between the two sub-networks lies in the number of neurons within their fully connected layers. The first sub-network serves as a strong denoiser with a small number of neurons, effectively attenuating seismic noise; in contrast, the second sub-network functions as a signal-add-back model, using a larger number of neurons to retrieve some of the signal that was not preserved in the output of the first sub-network. The proposed model produces two outputs, each corresponding to one of the sub-networks, and both sub-networks are optimized simultaneously using the noisy data as the label for both outputs. Evaluations conducted on both synthetic and field data demonstrate the model’s effectiveness in suppressing seismic noise with minimal signal leakage, outperforming some benchmark methods.</div></div>","PeriodicalId":100124,"journal":{"name":"Artificial Intelligence in Geosciences","volume":"6 1","pages":"Article 100123"},"PeriodicalIF":0.0,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144243298","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

Thank you reviewers! 谢谢审稿人！

Artificial Intelligence in Geosciences

Pub Date : 2025-06-01 DOI: 10.1016/j.aiig.2025.100114

引用次数: 0

Deep learning based identification of rock minerals from un-processed digital microscopic images of undisturbed broken-surfaces 基于深度学习的岩石矿物识别，从未受干扰的破碎表面的未处理的数字显微图像

Artificial Intelligence in Geosciences

Pub Date : 2025-06-01 DOI: 10.1016/j.aiig.2025.100127

M.A. Dalhat, Sami A. Osman

This study employed convolutional neural networks (CNNs) for the classification of rock minerals based on 3179 RGB-scale original microstructural images of undisturbed broken surfaces. The image dataset covers 40 distinct rock mineral-types. Three CNN architectures (Simple model, SqueezeNet, and Xception) were evaluated to compare their performance and feature extraction capabilities. Gradient-weighted Class Activation Mapping (Grad-CAM) was employed to visualize the features influencing model predictions, providing insights into how each model distinguishes between mineral classes. Key discriminative attributes included texture, grain size, pattern, and color variations. Texture and grain boundaries were identified as the most critical features, as they were strongly activated regions by the best model. Patterns such as banding and chromatic contrasts further enhanced classification accuracy. Performance analysis revealed that the Simple model had limited ability to isolate fine-grained details, producing broad and less specific activations (0.84 test accuracy). SqueezeNet demonstrated improved localization of discriminative features but occasionally missed finer textural details (0.95 test accuracy). The Xception model outperformed the others, achieving the highest classification accuracy (0.98 test accuracy) by exhibiting precise and tightly focused activations, capturing intricate textures and subtle chromatic variations. Its superior performance can be attributed to its deep architecture and efficient depth-wise separable convolutions, which enabled hierarchical and detailed feature extraction. Results underscores the importance of texture, pattern, and chromatic features in accurate mineral classification and highlights the suitability of deep, efficient architectures like Xception for such tasks. These findings demonstrate the potential of CNNs in geoscience research, offering a framework for automated mineral identification in industrial and scientific applications.

本研究基于3179张rgb尺度原始破碎面显微结构图像，采用卷积神经网络（cnn）对岩石矿物进行分类。图像数据集涵盖了40种不同的岩石矿物类型。我们评估了三种CNN架构（Simple model、SqueezeNet和Xception），比较了它们的性能和特征提取能力。梯度加权类激活映射（Grad-CAM）用于可视化影响模型预测的特征，提供每个模型如何区分矿物类别的见解。关键的鉴别属性包括纹理、粒度、图案和颜色变化。纹理和晶界被认为是最关键的特征，因为它们是被最佳模型强烈激活的区域。带状和彩色对比等模式进一步提高了分类的准确性。性能分析表明，Simple模型隔离细粒度细节的能力有限，产生广泛而不太特定的激活（测试精度为0.84）。SqueezeNet在判别特征的定位上得到了改进，但偶尔会遗漏更精细的纹理细节（测试精度为0.95）。Xception模型优于其他模型，通过展示精确和紧密聚焦的激活，捕获复杂的纹理和微妙的颜色变化，实现了最高的分类精度（0.98测试精度）。其优越的性能可归因于其深层架构和高效的深度可分离卷积，这使得分层和详细的特征提取成为可能。结果强调了纹理、图案和颜色特征在准确矿物分类中的重要性，并强调了像Xception这样的深层、高效架构对此类任务的适用性。这些发现证明了cnn在地球科学研究中的潜力，为工业和科学应用中的自动矿物识别提供了一个框架。

{"title":"Deep learning based identification of rock minerals from un-processed digital microscopic images of undisturbed broken-surfaces","authors":"M.A. Dalhat, Sami A. Osman","doi":"10.1016/j.aiig.2025.100127","DOIUrl":"10.1016/j.aiig.2025.100127","url":null,"abstract":"<div><div>This study employed convolutional neural networks (CNNs) for the classification of rock minerals based on 3179 RGB-scale original microstructural images of undisturbed broken surfaces. The image dataset covers 40 distinct rock mineral-types. Three CNN architectures (Simple model, SqueezeNet, and Xception) were evaluated to compare their performance and feature extraction capabilities. Gradient-weighted Class Activation Mapping (Grad-CAM) was employed to visualize the features influencing model predictions, providing insights into how each model distinguishes between mineral classes. Key discriminative attributes included texture, grain size, pattern, and color variations. Texture and grain boundaries were identified as the most critical features, as they were strongly activated regions by the best model. Patterns such as banding and chromatic contrasts further enhanced classification accuracy. Performance analysis revealed that the Simple model had limited ability to isolate fine-grained details, producing broad and less specific activations (0.84 test accuracy). SqueezeNet demonstrated improved localization of discriminative features but occasionally missed finer textural details (0.95 test accuracy). The Xception model outperformed the others, achieving the highest classification accuracy (0.98 test accuracy) by exhibiting precise and tightly focused activations, capturing intricate textures and subtle chromatic variations. Its superior performance can be attributed to its deep architecture and efficient depth-wise separable convolutions, which enabled hierarchical and detailed feature extraction. Results underscores the importance of texture, pattern, and chromatic features in accurate mineral classification and highlights the suitability of deep, efficient architectures like Xception for such tasks. These findings demonstrate the potential of CNNs in geoscience research, offering a framework for automated mineral identification in industrial and scientific applications.</div></div>","PeriodicalId":100124,"journal":{"name":"Artificial Intelligence in Geosciences","volume":"6 1","pages":"Article 100127"},"PeriodicalIF":0.0,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144255175","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 microseismic event detection with TransUNet: A deep learning approach for simultaneous pickings of P-wave and S-wave first arrivals 利用TransUNet增强微地震事件检测：一种深度学习方法，用于同时拾取p波和s波首次到达

Artificial Intelligence in Geosciences

Pub Date : 2025-06-01 DOI: 10.1016/j.aiig.2025.100129

Kun Chen , Meng Li , Xiaolian Li , Guangzhi Cui , Jia Tian , JiaLe Li , RuoYao Mu , JunJie Zhu

Microseismic monitoring is essential for understanding subsurface dynamics and optimizing oil and gas production. However, traditional methods for the automatic detection of microseismic events rely heavily on characteristic functions and human intervention, often resulting in suboptimal performance when dealing with complex and noisy data. In this study, we propose a novel approach that leverages deep learning frame to extract multiscale features from microseismic data using a TransUNet neural network. Our model integrates the advantages of Transformer and UNet architectures to achieve high accuracy in multivariate image segmentation and precise picking of P-wave and S-wave first arrivals simultaneously. We validate our approach using both synthetic and field microseismic datasets recorded from gas storage monitoring and roof fracturing in a coal seam. The robustness of the proposed method has been verified in the testing of synthetic data with various levels of Gaussian and real background noises extracted from field data. The comparisons of the proposed method with UNet and SwinUNet in terms of the model architecture and classification performance demonstrate the TransUNet achieves the optimal balance in its architecture and inference speed. With relatively low inference time and network complexity, it operates effectively in high-precision microseismic phase pickings. This advancement holds significant promise for enhancing microseismic monitoring technology in hydraulic fracturing and reservoir monitoring applications.

微地震监测对于了解地下动态和优化油气生产至关重要。然而，传统的微地震事件自动检测方法严重依赖特征函数和人为干预，在处理复杂和有噪声的数据时，往往导致性能不佳。在这项研究中，我们提出了一种新的方法，利用深度学习框架，利用TransUNet神经网络从微地震数据中提取多尺度特征。我们的模型融合了Transformer和UNet架构的优点，实现了高精度的多变量图像分割和同时精确提取p波和s波首到达。我们利用煤层气储气库监测和顶板压裂记录的合成和现场微地震数据集验证了我们的方法。该方法的鲁棒性已在不同高斯噪声和真实背景噪声的合成数据测试中得到验证。通过与UNet和SwinUNet在模型结构和分类性能上的比较，表明TransUNet在模型结构和推理速度上达到了最佳平衡。该方法具有较低的推理时间和较低的网络复杂度，能够有效地进行高精度微震相位采集。这一进展为加强微地震监测技术在水力压裂和储层监测中的应用带来了重大希望。

{"title":"Enhancing microseismic event detection with TransUNet: A deep learning approach for simultaneous pickings of P-wave and S-wave first arrivals","authors":"Kun Chen , Meng Li , Xiaolian Li , Guangzhi Cui , Jia Tian , JiaLe Li , RuoYao Mu , JunJie Zhu","doi":"10.1016/j.aiig.2025.100129","DOIUrl":"10.1016/j.aiig.2025.100129","url":null,"abstract":"<div><div>Microseismic monitoring is essential for understanding subsurface dynamics and optimizing oil and gas production. However, traditional methods for the automatic detection of microseismic events rely heavily on characteristic functions and human intervention, often resulting in suboptimal performance when dealing with complex and noisy data. In this study, we propose a novel approach that leverages deep learning frame to extract multiscale features from microseismic data using a TransUNet neural network. Our model integrates the advantages of Transformer and UNet architectures to achieve high accuracy in multivariate image segmentation and precise picking of P-wave and S-wave first arrivals simultaneously. We validate our approach using both synthetic and field microseismic datasets recorded from gas storage monitoring and roof fracturing in a coal seam. The robustness of the proposed method has been verified in the testing of synthetic data with various levels of Gaussian and real background noises extracted from field data. The comparisons of the proposed method with UNet and SwinUNet in terms of the model architecture and classification performance demonstrate the TransUNet achieves the optimal balance in its architecture and inference speed. With relatively low inference time and network complexity, it operates effectively in high-precision microseismic phase pickings. This advancement holds significant promise for enhancing microseismic monitoring technology in hydraulic fracturing and reservoir monitoring applications.</div></div>","PeriodicalId":100124,"journal":{"name":"Artificial Intelligence in Geosciences","volume":"6 1","pages":"Article 100129"},"PeriodicalIF":0.0,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144314011","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 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 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