Applied Computing and Geosciences最新文献_第9页

GPE-DNeRF:Neural radiance field method for surface geological bodies reconstruction GPE-DNeRF：地表地质体重建的神经辐射场方法

IF 2.6 Q2 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Applied Computing and Geosciences

Pub Date : 2025-06-01 Epub Date: 2025-04-17 DOI: 10.1016/j.acags.2025.100239

Xinyi Wang , Weihua Hua , Xiuguo Liu , Peng Li , Guohe Li

Three-dimensional (3D) geological models are crucial for a comprehensive understanding of regional geological formations. Deep learning-based 3D reconstruction technologies offer highly automated approaches for recognizing complex data patterns and generating realistic reconstruction results. The application of these methods in the reconstruction of surface geological bodies is particularly significant in the context of advancing the construction of digital mines nationwide. Neural Radiance Fields (NeRF) have been employed to generate 3D scenes by training models on images captured from different viewpoints. However, parallax errors across viewpoints may lead to misalignment or overlapping of details in the generated images, especially in regions with complex geometric structures. These errors can hinder the model's ability to accurately reconstruct surface details, resulting in substantial distortions in the final output. To address this issue and reduce artifacts and noise in the reconstructed 3D surface geological model, this study explores the use of NeRF for geologic body reconstruction. We propose an enhanced method, GPE-DNeRF, which integrates depth information with Gaussian positional encoding to achieve high-quality reconstruction of geological surfaces. The performance of the proposed method is evaluated, and comparative analyses are conducted with the SfM-MVS and NeRF methods. The GPE-DNeRF method demonstrates a strong capability to eliminate artifacts and retain detailed terrain features, thereby enhancing reconstruction quality and ensuring a closer alignment with actual surface geological conditions.

三维（3D）地质模型对于全面了解区域地质构造至关重要。基于深度学习的三维重建技术为识别复杂的数据模式和生成真实的重建结果提供了高度自动化的方法。这些方法在地表地质体重建中的应用，在全国推进数字矿山建设的背景下显得尤为重要。神经辐射场（NeRF）已被用于生成3D场景的训练模型从不同的视点捕获的图像。然而，视差误差可能导致生成图像中的细节不对齐或重叠，特别是在具有复杂几何结构的区域。这些误差会阻碍模型准确重建表面细节的能力，导致最终输出的大量扭曲。为了解决这一问题，减少重建的三维地表地质模型中的伪影和噪声，本研究探索了使用NeRF进行地质体重建。本文提出了一种改进的GPE-DNeRF方法，该方法将深度信息与高斯位置编码相结合，实现了高质量的地质表面重建。对该方法的性能进行了评价，并与SfM-MVS和NeRF方法进行了比较分析。GPE-DNeRF方法显示出强大的消除伪影和保留详细地形特征的能力，从而提高了重建质量，并确保与实际地表地质条件更接近。

{"title":"GPE-DNeRF:Neural radiance field method for surface geological bodies reconstruction","authors":"Xinyi Wang , Weihua Hua , Xiuguo Liu , Peng Li , Guohe Li","doi":"10.1016/j.acags.2025.100239","DOIUrl":"10.1016/j.acags.2025.100239","url":null,"abstract":"<div><div>Three-dimensional (3D) geological models are crucial for a comprehensive understanding of regional geological formations. Deep learning-based 3D reconstruction technologies offer highly automated approaches for recognizing complex data patterns and generating realistic reconstruction results. The application of these methods in the reconstruction of surface geological bodies is particularly significant in the context of advancing the construction of digital mines nationwide. Neural Radiance Fields (NeRF) have been employed to generate 3D scenes by training models on images captured from different viewpoints. However, parallax errors across viewpoints may lead to misalignment or overlapping of details in the generated images, especially in regions with complex geometric structures. These errors can hinder the model's ability to accurately reconstruct surface details, resulting in substantial distortions in the final output. To address this issue and reduce artifacts and noise in the reconstructed 3D surface geological model, this study explores the use of NeRF for geologic body reconstruction. We propose an enhanced method, GPE-DNeRF, which integrates depth information with Gaussian positional encoding to achieve high-quality reconstruction of geological surfaces. The performance of the proposed method is evaluated, and comparative analyses are conducted with the SfM-MVS and NeRF methods. The GPE-DNeRF method demonstrates a strong capability to eliminate artifacts and retain detailed terrain features, thereby enhancing reconstruction quality and ensuring a closer alignment with actual surface geological conditions.</div></div>","PeriodicalId":33804,"journal":{"name":"Applied Computing and Geosciences","volume":"26 ","pages":"Article 100239"},"PeriodicalIF":2.6,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143854654","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

Comparison of three one-dimensional time-domain electromagnetic forward algorithms 三种一维时域电磁正演算法的比较

IF 2.6 Q2 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Applied Computing and Geosciences

Pub Date : 2025-06-01 Epub Date: 2025-05-08 DOI: 10.1016/j.acags.2025.100243

Frederik Alexander Falk, Anders Vest Christiansen, Thomas Mejer Hansen

Accurate, efficient, and accessible forward modeling of geophysical processes is essential for understanding them and for inversion of geophysical data. Various algorithms are available for predicting data with the time domain electromagnetic method (TDEM). These algorithms differ in their approach and implementation, making some more suitable than others for specific applications. In this study, we compare three different algorithms for calculating the solution to the 1D forward response problem in TDEM, provided by Geoscience Australia, AarhusInv and SimPEG. Our comparison focuses on four main aspects: efficiency, accuracy, generality and convenience. Efficiency is evaluated from the perspective of computational speed. Accuracy is evaluated in two steps. First, we analyze the relative modeling error of each algorithm’s forward calculation for conductive half-space models, compared to an analytic solution. Secondly, we evaluate the accuracy of the algorithms relative to each other in the context of more complex earth models where no analytic solutions exist. This evaluation assumes a realistic TDEM instrument. Generality is the ability to model a variety of real TDEM scenarios. Lastly, we assess the convenience of each algorithm by considering factors such as ease of use, extensibility, code accessibility, and licensing requirements. We find that no single tested forward algorithm is best for all cases. AarhusInv is accurate and fast while it also has the most options for modeling real TDEM systems, but it requires a license, and is the hardest forward algorithm to interface to. SimPEG is open source, fast, easy to install and results may easily be shared, but has accuracy limitations at early times when modeling real systems with gate integration and low-pass filters. Lastly, Geoscience Australia is open source, accurate, and fast, but can only model dipole sources.

准确、高效、方便的地球物理过程正演模拟对于理解地球物理过程和反演地球物理数据至关重要。时域电磁法（TDEM）预测数据的算法有很多种。这些算法在其方法和实现上有所不同，使得一些算法比其他算法更适合特定的应用程序。在这项研究中，我们比较了三种不同的算法来计算TDEM中1D正演响应问题的解，这三种算法分别由澳大利亚地球科学、AarhusInv和SimPEG提供。我们的比较主要集中在四个方面：效率、准确性、通用性和方便性。效率是从计算速度的角度来评价的。准确度的评估分两步进行。首先，与解析解相比，我们分析了每种算法对导电半空间模型的正演计算的相对建模误差。其次，在没有解析解的更复杂的地球模型中，我们评估了算法相对于彼此的准确性。这个评估假设了一个现实的TDEM仪器。通用性是对各种真实的TDEM场景进行建模的能力。最后，我们通过考虑诸如易用性、可扩展性、代码可访问性和许可要求等因素来评估每种算法的便利性。我们发现没有一种经过测试的前向算法对所有情况都是最好的。AarhusInv是准确和快速的，同时它也有最多的选择来建模真实的TDEM系统，但它需要许可证，是最难接口的前向算法。SimPEG是开源的、快速的、易于安装的，并且结果可以很容易地共享，但是在早期使用门集成和低通滤波器对真实系统建模时存在精度限制。最后，澳大利亚地球科学是开源的、准确的、快速的，但只能模拟偶极子源。

{"title":"Comparison of three one-dimensional time-domain electromagnetic forward algorithms","authors":"Frederik Alexander Falk, Anders Vest Christiansen, Thomas Mejer Hansen","doi":"10.1016/j.acags.2025.100243","DOIUrl":"10.1016/j.acags.2025.100243","url":null,"abstract":"<div><div>Accurate, efficient, and accessible forward modeling of geophysical processes is essential for understanding them and for inversion of geophysical data. Various algorithms are available for predicting data with the time domain electromagnetic method (TDEM). These algorithms differ in their approach and implementation, making some more suitable than others for specific applications. In this study, we compare three different algorithms for calculating the solution to the 1D forward response problem in TDEM, provided by Geoscience Australia, AarhusInv and SimPEG. Our comparison focuses on four main aspects: efficiency, accuracy, generality and convenience. Efficiency is evaluated from the perspective of computational speed. Accuracy is evaluated in two steps. First, we analyze the relative modeling error of each algorithm’s forward calculation for conductive half-space models, compared to an analytic solution. Secondly, we evaluate the accuracy of the algorithms relative to each other in the context of more complex earth models where no analytic solutions exist. This evaluation assumes a realistic TDEM instrument. Generality is the ability to model a variety of real TDEM scenarios. Lastly, we assess the convenience of each algorithm by considering factors such as ease of use, extensibility, code accessibility, and licensing requirements. We find that no single tested forward algorithm is best for all cases. AarhusInv is accurate and fast while it also has the most options for modeling real TDEM systems, but it requires a license, and is the hardest forward algorithm to interface to. SimPEG is open source, fast, easy to install and results may easily be shared, but has accuracy limitations at early times when modeling real systems with gate integration and low-pass filters. Lastly, Geoscience Australia is open source, accurate, and fast, but can only model dipole sources.</div></div>","PeriodicalId":33804,"journal":{"name":"Applied Computing and Geosciences","volume":"26 ","pages":"Article 100243"},"PeriodicalIF":2.6,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143937833","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

Examining the impacts of salt precipitation on soil hydraulic properties at the field lysimeter scale 在田间渗湿计尺度上考察盐降水对土壤水力特性的影响

IF 2.6 Q2 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Applied Computing and Geosciences

Pub Date : 2025-06-01 Epub Date: 2025-04-09 DOI: 10.1016/j.acags.2025.100238

Qian Liu , Yanfeng Liu , Menggui Jin , Jinlong Zhou , Paul A. Ferré

Previous bench-scale investigations have demonstrated that salt precipitation reduces soil saturated hydraulic conductivity (K_s) due to the clogging effect. However, this conclusion may be confounded by the boundary effects inherent to the physical model. While existing field-scale studies have primarily focused on water-solute migration by directly assuming that salt precipitation reduces K_s, systematic investigations examining how salt crystallization alters soil hydraulic properties remain scarce. This study employed a time-windowed inverse method to analyze one set of data from four lysimeters supplied through the bottom with NaCl solution at concentrations of 3, 30, 100, and 250 g/L under field condition, aiming to examine: (1) whether the salt precipitation impacts the soil hydraulic properties; and (2) whether the degree of this impact depends on the water salinity. Results in each column showed that the inverse-derived K_s unexpectedly increased by more than 50 % at the intermediate time and then decreased to its early-time value. This trend in inverse-derived K_s showed a strong positive correlation with the ambient evaporation rate. Based on measurements of bottom fluxes and ambient evaporation, these opposing trends in inverse-derived K_s are primarily ascribed to the actual K_s change caused by the salt precipitation, rather than variations in salt crust-soil surface hydraulic connectivity (which also affect effective K_s). These findings highlight the need for future experiments to investigate salt precipitation-induced soil pore structure changes under varying evaporation intensities and across multiple scales.

以往的台阶研究表明，由于堵塞效应，盐沉淀会降低土壤饱和导水性（Ks）。然而，这一结论可能会受到物理模型固有的边界效应的影响。现有的实地尺度研究主要集中在水溶液迁移方面，直接假定盐沉淀会降低 Ks，而对盐结晶如何改变土壤水力特性的系统研究仍然很少。本研究采用时间窗口反演法分析了在野外条件下从底部注入浓度分别为 3、30、100 和 250 克/升的 NaCl 溶液的四个溶液池的一组数据，旨在研究：(1) 盐分析出是否会影响土壤的水力特性；(2) 这种影响的程度是否取决于水的盐度。各列结果显示，反演 Ks 在中间时间意外增加了 50%以上，然后又下降到早期时间的值。反演 Ks 的这一趋势与环境蒸发率呈强烈的正相关。根据对底部通量和环境蒸发的测量，反演 Ks 的这些相反趋势主要归因于盐沉淀引起的实际 Ks 变化，而不是盐壳-土壤表面水力连通性的变化（这也会影响有效 Ks）。这些发现突出表明，今后有必要开展实验，研究在不同蒸发强度和多尺度条件下盐降水引起的土壤孔隙结构变化。

{"title":"Examining the impacts of salt precipitation on soil hydraulic properties at the field lysimeter scale","authors":"Qian Liu , Yanfeng Liu , Menggui Jin , Jinlong Zhou , Paul A. Ferré","doi":"10.1016/j.acags.2025.100238","DOIUrl":"10.1016/j.acags.2025.100238","url":null,"abstract":"<div><div>Previous bench-scale investigations have demonstrated that salt precipitation reduces soil saturated hydraulic conductivity (<em>K</em><sub>s</sub>) due to the clogging effect. However, this conclusion may be confounded by the boundary effects inherent to the physical model. While existing field-scale studies have primarily focused on water-solute migration by directly assuming that salt precipitation reduces <em>K</em><sub>s</sub>, systematic investigations examining how salt crystallization alters soil hydraulic properties remain scarce. This study employed a time-windowed inverse method to analyze one set of data from four lysimeters supplied through the bottom with NaCl solution at concentrations of 3, 30, 100, and 250 g/L under field condition, aiming to examine: (1) whether the salt precipitation impacts the soil hydraulic properties; and (2) whether the degree of this impact depends on the water salinity. Results in each column showed that the inverse-derived <em>K</em><sub>s</sub> unexpectedly increased by more than 50 % at the intermediate time and then decreased to its early-time value. This trend in inverse-derived <em>K</em><sub>s</sub> showed a strong positive correlation with the ambient evaporation rate. Based on measurements of bottom fluxes and ambient evaporation, these opposing trends in inverse-derived <em>K</em><sub>s</sub> are primarily ascribed to the actual <em>K</em><sub>s</sub> change caused by the salt precipitation, rather than variations in salt crust-soil surface hydraulic connectivity (which also affect effective <em>K</em><sub>s</sub>). These findings highlight the need for future experiments to investigate salt precipitation-induced soil pore structure changes under varying evaporation intensities and across multiple scales.</div></div>","PeriodicalId":33804,"journal":{"name":"Applied Computing and Geosciences","volume":"26 ","pages":"Article 100238"},"PeriodicalIF":2.6,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143821294","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

Prediction of carbon dioxide phase at bottomhole by adaptive factorization network considering well geometry 考虑井形的自适应分解网络预测井底二氧化碳相

IF 2.6 Q2 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Applied Computing and Geosciences

Pub Date : 2025-06-01 Epub Date: 2025-05-21 DOI: 10.1016/j.acags.2025.100254

Sungil Kim , Tea-Woo Kim , Yongjun Hong , Hoonyoung Jeong

Accurate carbon dioxide (CO₂) phase prediction at the bottomhole of injection wells is essential for ensuring safe and efficient CO₂ storage and enhanced gas recovery (EGR). Phase misclassification can cause operational inefficiencies, equipment failure, and compromised storage integrity, posing significant risks to CO₂ injection projects. While previous studies have contributed to CO₂ phase prediction, they have overlooked well geometry effects, which can impact reliability in real-world applications. This study addresses these challenges by introducing a deep learning framework based on the adaptive factorization network (AFN), which enhances CO₂ phase prediction accuracy by leveraging feature interactions. The AFN model was trained on ∼43,000 wells across seven major North American shale gas basins, covering a wide range of well geometries and injection conditions. CO₂ phases were classified into supercritical and dense categories, reflecting prevailing flow conditions. To enhance practical applicability, we incorporated real-field wellbore data, ensuring alignment with actual injection environments. The standard AFN model achieved an F1-score of 0.94, with data augmentation further improving performance by reducing false predictions by 50 % and increasing the F1-score to 0.97. Rigorous validation demonstrated the model's robustness for optimizing wellhead temperature to achieve the desired CO₂ phase transition. By explicitly considering well geometry effects and real-field conditions, this study advances data-driven CO₂ injection modeling, providing a scalable, high-accuracy framework for evaluating CO₂ storage and EGR feasibility.

注水井井底准确的二氧化碳（CO2）相预测是确保安全高效的CO2储存和提高气采（EGR）的关键。阶段分类错误会导致操作效率低下、设备故障和存储完整性受损，给二氧化碳注入项目带来重大风险。虽然之前的研究对CO2相预测做出了贡献，但它们忽略了井的几何形状效应，这可能会影响实际应用中的可靠性。本研究通过引入基于自适应分解网络（AFN）的深度学习框架来解决这些挑战，该框架通过利用特征交互来提高CO2相位预测的准确性。AFN模型在北美7个主要页岩气盆地的约43,000口井中进行了训练，涵盖了各种井的几何形状和注入条件。CO2相分为超临界和致密两类，反映了主流的流动条件。为了提高实际适用性，我们结合了现场井眼数据，确保与实际注入环境一致。标准AFN模型的f1得分为0.94，数据增强进一步提高了性能，减少了50%的错误预测，并将f1得分提高到0.97。严格的验证证明了该模型在优化井口温度以实现所需的CO2相变方面的鲁棒性。通过明确考虑井的几何效应和现场条件，该研究推进了数据驱动的二氧化碳注入建模，为评估二氧化碳储存和EGR可行性提供了可扩展的、高精度的框架。

{"title":"Prediction of carbon dioxide phase at bottomhole by adaptive factorization network considering well geometry","authors":"Sungil Kim , Tea-Woo Kim , Yongjun Hong , Hoonyoung Jeong","doi":"10.1016/j.acags.2025.100254","DOIUrl":"10.1016/j.acags.2025.100254","url":null,"abstract":"<div><div>Accurate carbon dioxide (CO<sub>2</sub>) phase prediction at the bottomhole of injection wells is essential for ensuring safe and efficient CO<sub>2</sub> storage and enhanced gas recovery (EGR). Phase misclassification can cause operational inefficiencies, equipment failure, and compromised storage integrity, posing significant risks to CO<sub>2</sub> injection projects. While previous studies have contributed to CO<sub>2</sub> phase prediction, they have overlooked well geometry effects, which can impact reliability in real-world applications. This study addresses these challenges by introducing a deep learning framework based on the adaptive factorization network (AFN), which enhances CO<sub>2</sub> phase prediction accuracy by leveraging feature interactions. The AFN model was trained on ∼43,000 wells across seven major North American shale gas basins, covering a wide range of well geometries and injection conditions. CO<sub>2</sub> phases were classified into supercritical and dense categories, reflecting prevailing flow conditions. To enhance practical applicability, we incorporated real-field wellbore data, ensuring alignment with actual injection environments. The standard AFN model achieved an F1-score of 0.94, with data augmentation further improving performance by reducing false predictions by 50 % and increasing the F1-score to 0.97. Rigorous validation demonstrated the model's robustness for optimizing wellhead temperature to achieve the desired CO<sub>2</sub> phase transition. By explicitly considering well geometry effects and real-field conditions, this study advances data-driven CO<sub>2</sub> injection modeling, providing a scalable, high-accuracy framework for evaluating CO<sub>2</sub> storage and EGR feasibility.</div></div>","PeriodicalId":33804,"journal":{"name":"Applied Computing and Geosciences","volume":"26 ","pages":"Article 100254"},"PeriodicalIF":2.6,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144123572","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

Resistivity imaging and uncertainty assessment of volcanic covered sedimentary basins of India derived from a new strategy 印度火山覆盖沉积盆地电阻率成像及不确定度评价新策略

IF 2.6 Q2 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Applied Computing and Geosciences

Pub Date : 2025-06-01 Epub Date: 2025-04-26 DOI: 10.1016/j.acags.2025.100244

Jit Varish Tiwari , Kuldeep Sarkar , Upendra K. Singh

In basalt-covered areas like Saurashtra, India, the Deccan Traps are a significant part of the Indian lithosphere with notable geophysical anomalies and tectono-thermal history dating back to the Mesozoic. Magnetotellurics (MT) is commonly used to image subtrappean Tertiary and Quaternary strata in these regions. We assessed the Improved Wolf Optimization (IWOA) strategy, inspired by whale hunting behavior, to enhance the electrical resistivity structure in basalt-covered regions without relying on seismic and borehole data. Initially tested on theoretical/synthetic MT datasets representing geological scenarios, IWOA was then applied to field data from hydrocarbon potential basins: (i) trap-covered areas, yielding reliable subsurface models with MT alone, and (ii) traps overlain by conductive Tertiary sediments. Instead of selecting the global model with the lowest error, we used Bayesian posterior probability density function (PDF) to reconstruct models. This approach considers models with PDF values above 68.27 % confidence interval, constructing an average model from these models with lesser uncertainty. Our analysis revealed a thick subtrappean Tertiary sedimentary layer over volcanic cover in the Cambay basin. The method also identified two layers: a highly conductive layer likely alluvium and a major resistive layer probably due to volcanic deposits. These findings align with geological stratigraphy and drill samples, demonstrating that IWOA provides a reliable and superior subsurface model.

在玄武岩覆盖的地区，如印度的索拉什特拉，德干圈闭是印度岩石圈的重要组成部分，具有显著的地球物理异常和构造-热历史，可追溯到中生代。大地电磁成像是这些地区第三系和第四纪地层的常用成像方法。受鲸鱼捕猎行为的启发，我们评估了改进狼优化（IWOA）策略，该策略可以在不依赖地震和钻孔数据的情况下增强玄武岩覆盖地区的电阻率结构。首先在代表地质情景的理论/合成MT数据集上进行测试，然后将IWOA应用于来自潜在油气盆地的现场数据：(i)圈闭覆盖区域，仅使用MT就可以获得可靠的地下模型；（ii）被导电第三纪沉积物覆盖的圈闭。采用贝叶斯后验概率密度函数（PDF）重建模型，而不是选择误差最小的全局模型。该方法考虑PDF值高于68.27%置信区间的模型，从这些模型构建不确定性较小的平均模型。我们的分析表明，在坎贝盆地火山覆盖层上有一层厚的次盖层第三纪沉积层。该方法还确定了两层：一个可能是冲积层的高导电层和一个可能是火山沉积物的主要电阻层。这些发现与地质地层学和钻井样品相一致，表明IWOA提供了可靠且优越的地下模型。

{"title":"Resistivity imaging and uncertainty assessment of volcanic covered sedimentary basins of India derived from a new strategy","authors":"Jit Varish Tiwari , Kuldeep Sarkar , Upendra K. Singh","doi":"10.1016/j.acags.2025.100244","DOIUrl":"10.1016/j.acags.2025.100244","url":null,"abstract":"<div><div>In basalt-covered areas like Saurashtra, India, the Deccan Traps are a significant part of the Indian lithosphere with notable geophysical anomalies and tectono-thermal history dating back to the Mesozoic. Magnetotellurics (MT) is commonly used to image subtrappean Tertiary and Quaternary strata in these regions. We assessed the Improved Wolf Optimization (IWOA) strategy, inspired by whale hunting behavior, to enhance the electrical resistivity structure in basalt-covered regions without relying on seismic and borehole data. Initially tested on theoretical/synthetic MT datasets representing geological scenarios, IWOA was then applied to field data from hydrocarbon potential basins: (i) trap-covered areas, yielding reliable subsurface models with MT alone, and (ii) traps overlain by conductive Tertiary sediments. Instead of selecting the global model with the lowest error, we used Bayesian posterior probability density function (PDF) to reconstruct models. This approach considers models with PDF values above 68.27 % confidence interval, constructing an average model from these models with lesser uncertainty. Our analysis revealed a thick subtrappean Tertiary sedimentary layer over volcanic cover in the Cambay basin. The method also identified two layers: a highly conductive layer likely alluvium and a major resistive layer probably due to volcanic deposits. These findings align with geological stratigraphy and drill samples, demonstrating that IWOA provides a reliable and superior subsurface model.</div></div>","PeriodicalId":33804,"journal":{"name":"Applied Computing and Geosciences","volume":"26 ","pages":"Article 100244"},"PeriodicalIF":2.6,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143886148","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

Statistical approaches for modeling correlated grade and tonnage distributions and applications for mineral resource assessments 建立相关等级和吨位分布模型的统计方法及其在矿产资源评价中的应用

IF 2.6 Q2 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Applied Computing and Geosciences

Pub Date : 2025-06-01 Epub Date: 2025-04-16 DOI: 10.1016/j.acags.2025.100240

Joshua M. Rosera , Graham W. Lederer , John H. Schuenemeyer

Correlations between grade and tonnage exist in mineral resource data compiled from published reports, but they are not always addressed during quantitative assessment of undiscovered mineral resources. Failure to account for correlated grade and tonnage distributions can result in geologically unrealistic assessment results. Current software tools simulate univariate ore tonnage and multivariate resource grades of undiscovered deposits independently. As a result, analysts are forced to rely on ad-hoc solutions to minimize the correlation issues by: 1) creating subsets of data with restricted criteria; 2) truncating grade and tonnage distributions; and 3) testing model robustness using exploratory data analysis. While these methods represent pragmatic solutions, the statistical solutions presented here provide additional options to address real correlations in grade and tonnage data used for mineral resource assessments. We present a modified version of the MapMark4 package in R that introduces two alternatives for modeling grade and tonnage distributions, consisting of a multivariate solution that accounts for correlations between ore tonnage and metal grades and an empirical solution that utilizes simple random sampling with replacement to reproduce coupled grades and tonnages from the input data. We present simulations for contained ore and metal for three case studies representing tungsten skarn, komatiite-hosted nickel, and sediment-hosted carbonate amagmatic zinc-lead (Mississippi Valley-type) deposits. Employing the methods presented here yields quantitative mineral resource assessment results that more closely reflect the empirical distributions of grades and tonnages observed in nature and expands the applicability of these tools for ongoing critical mineral resource assessments.

从已发表的报告汇编的矿物资源数据中存在品位和吨位之间的相关性，但在对未发现的矿物资源进行定量评价时并不总是处理这些相关性。未能考虑到相关的品位和吨位分布可能导致地质上不现实的评估结果。目前的软件工具可以独立地模拟未发现矿床的单变量矿石吨位和多变量资源品位。因此，分析人员被迫依靠特别的解决方案，通过以下方式将相关性问题最小化：1)创建具有限制标准的数据子集；2)截断品位和吨位分布；3)利用探索性数据分析检验模型的稳健性。虽然这些方法是实用的解决办法，但这里提出的统计解决办法提供了额外的选择，以解决用于矿产资源评估的品位和吨位数据之间的实际相关性。我们在R中提出了MapMark4软件包的修改版本，其中引入了两种用于建模品位和吨位分布的替代方案，其中包括一个考虑矿石吨位和金属品位之间相关性的多元解决方案，以及一个利用简单随机抽样的经验解决方案，该解决方案利用替换从输入数据中重现耦合的品位和吨位。我们为三个案例研究提供了包含矿石和金属的模拟，分别代表钨矽卡岩、科马铁矿含镍和沉积物含碳酸盐岩浆锌铅（密西西比河谷型）矿床。采用本文提出的方法可以产生定量的矿产资源评估结果，这些结果更接近地反映了在自然界中观察到的等级和吨位的经验分布，并扩大了这些工具对正在进行的关键矿产资源评估的适用性。

{"title":"Statistical approaches for modeling correlated grade and tonnage distributions and applications for mineral resource assessments","authors":"Joshua M. Rosera , Graham W. Lederer , John H. Schuenemeyer","doi":"10.1016/j.acags.2025.100240","DOIUrl":"10.1016/j.acags.2025.100240","url":null,"abstract":"<div><div>Correlations between grade and tonnage exist in mineral resource data compiled from published reports, but they are not always addressed during quantitative assessment of undiscovered mineral resources. Failure to account for correlated grade and tonnage distributions can result in geologically unrealistic assessment results. Current software tools simulate univariate ore tonnage and multivariate resource grades of undiscovered deposits independently. As a result, analysts are forced to rely on <em>ad-hoc</em> solutions to minimize the correlation issues by: 1) creating subsets of data with restricted criteria; 2) truncating grade and tonnage distributions; and 3) testing model robustness using exploratory data analysis. While these methods represent pragmatic solutions, the statistical solutions presented here provide additional options to address real correlations in grade and tonnage data used for mineral resource assessments. We present a modified version of the MapMark4 package in R that introduces two alternatives for modeling grade and tonnage distributions, consisting of a multivariate solution that accounts for correlations between ore tonnage and metal grades and an empirical solution that utilizes simple random sampling with replacement to reproduce coupled grades and tonnages from the input data. We present simulations for contained ore and metal for three case studies representing tungsten skarn, komatiite-hosted nickel, and sediment-hosted carbonate amagmatic zinc-lead (Mississippi Valley-type) deposits. Employing the methods presented here yields quantitative mineral resource assessment results that more closely reflect the empirical distributions of grades and tonnages observed in nature and expands the applicability of these tools for ongoing critical mineral resource assessments.</div></div>","PeriodicalId":33804,"journal":{"name":"Applied Computing and Geosciences","volume":"26 ","pages":"Article 100240"},"PeriodicalIF":2.6,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143868651","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

Seismic Intelligence Tool: an extensive multipurpose software for seismic signal analysis 地震智能工具：一个广泛的多用途软件，用于地震信号分析

IF 2.6 Q2 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Applied Computing and Geosciences

Pub Date : 2025-06-01 Epub Date: 2025-04-15 DOI: 10.1016/j.acags.2025.100241

Andrea Bono

Over the past five years, the Istituto Nazionale di Geofisica e Vulcanologia (INGV) has started a technological transformation of its real-time seismic monitoring capabilities. This comprehensive restructuring initiative represents a pivotal moment in the Institute's commitment to advancing seismic research and enhancing public safety. At the heart of this transformation lies the development and deployment of the integrated system known as Caravel. Caravel stands as a testament to INGV's dedication to cutting-edge seismic monitoring technology and its mission to provide timely and accurate seismic information to researchers, emergency responders, and the general public. It represents a leap forward in real-time seismic monitoring, integrating state-of-the-art technologies and methodologies to detect, analyze, and disseminate seismic data with unprecedented efficiency and precision. This development reflects INGV's commitment to staying at the forefront of seismic research and hazard mitigation. This integrated system not only improves the accuracy of earthquake detection but also enhances our ability to rapidly assess the potential impact of seismic events, enabling more informed decision-making during emergency situations. Seismic Intelligence Tool (SIT) emerges as a software fork from one of Caravel's components previously known as PickFX. The reason behind this fork is to share with the scientific community a robust, multi-platform and freely accessible data analysis tool that adheres to current standards for representing seismic data while removing all INGV specific customizations from PickFX. The decision to fork the original software and release SIT underscores a commitment to democratizing access to advanced seismic analysis tools. By offering this resource at no cost, the scientific community gains access to a platform that is fully compatible with contemporary seismic data representation standards and that can become very powerful with time and cooperation. This endeavor not only promotes open access to critical seismic research tools but also facilitates collaboration and knowledge sharing among researchers, ultimately contributing to advancements in our understanding of seismic activity and its implications.

在过去的五年中，意大利国家地质火山研究所（INGV）已经开始对其实时地震监测能力进行技术改造。这一全面的重组举措代表了该研究所致力于推进地震研究和加强公共安全的关键时刻。这种转变的核心是开发和部署被称为Caravel的集成系统。卡拉维尔是INGV致力于尖端地震监测技术的证明，它的使命是为研究人员、应急人员和公众提供及时、准确的地震信息。它代表了实时地震监测的飞跃，整合了最先进的技术和方法，以前所未有的效率和精度检测、分析和传播地震数据。这一发展反映了INGV致力于保持在地震研究和减灾的前沿。这套综合系统不仅提高了地震探测的准确性，而且提高了我们快速评估地震事件潜在影响的能力，使我们在紧急情况下作出更明智的决策。地震智能工具（SIT）是由之前被称为PickFX的Caravel组件衍生而来的软件。这个分支背后的原因是与科学界分享一个强大的、多平台的、自由访问的数据分析工具，它坚持当前的地震数据表示标准，同时从PickFX中删除所有INGV特定的定制。采用原始软件并发布SIT的决定强调了先进地震分析工具大众化的承诺。通过免费提供这些资源，科学界获得了一个与当代地震数据表示标准完全兼容的平台，随着时间的推移和合作，这个平台将变得非常强大。这一努力不仅促进了关键地震研究工具的开放获取，而且促进了研究人员之间的合作和知识共享，最终有助于我们对地震活动及其影响的理解。

{"title":"Seismic Intelligence Tool: an extensive multipurpose software for seismic signal analysis","authors":"Andrea Bono","doi":"10.1016/j.acags.2025.100241","DOIUrl":"10.1016/j.acags.2025.100241","url":null,"abstract":"<div><div>Over the past five years, the <em>Istituto Nazionale di Geofisica e Vulcanologia</em> (INGV) has started a technological transformation of its real-time seismic monitoring capabilities. This comprehensive restructuring initiative represents a pivotal moment in the Institute's commitment to advancing seismic research and enhancing public safety. At the heart of this transformation lies the development and deployment of the integrated system known as <em>Caravel</em>. Caravel stands as a testament to INGV's dedication to cutting-edge seismic monitoring technology and its mission to provide timely and accurate seismic information to researchers, emergency responders, and the general public. It represents a leap forward in real-time seismic monitoring, integrating state-of-the-art technologies and methodologies to detect, analyze, and disseminate seismic data with unprecedented efficiency and precision. This development reflects INGV's commitment to staying at the forefront of seismic research and hazard mitigation. This integrated system not only improves the accuracy of earthquake detection but also enhances our ability to rapidly assess the potential impact of seismic events, enabling more informed decision-making during emergency situations. <em>Seismic Intelligence Tool (SIT)</em> emerges as a software <em>fork</em> from one of Caravel's components previously known as <em>PickFX</em>. The reason behind this fork is to share with the scientific community a robust, multi-platform and freely accessible data analysis tool that adheres to current standards for representing seismic data while removing all INGV specific customizations from PickFX. The decision to fork the original software and release SIT underscores a commitment to democratizing access to advanced seismic analysis tools. By offering this resource at no cost, the scientific community gains access to a platform that is fully compatible with contemporary seismic data representation standards and that can become very powerful with time and cooperation. This endeavor not only promotes open access to critical seismic research tools but also facilitates collaboration and knowledge sharing among researchers, ultimately contributing to advancements in our understanding of seismic activity and its implications.</div></div>","PeriodicalId":33804,"journal":{"name":"Applied Computing and Geosciences","volume":"26 ","pages":"Article 100241"},"PeriodicalIF":2.6,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143858828","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 deep learning physics-informed neural network (PINN) for predicting drilled shaft axial capacity 一种深度学习物理信息神经网络（PINN），用于预测钻井轴向容量

IF 2.6 Q2 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Applied Computing and Geosciences

Pub Date : 2025-06-01 Epub Date: 2025-05-04 DOI: 10.1016/j.acags.2025.100246

M.E. Al-Atroush

Accurately estimating the axial capacity of drilled shafts remains a persistent challenge in geotechnical engineering, as evidenced by significant discrepancies between measured load-test results and theoretical predictions. To bridge this gap, a novel Deep Learning–Physics-Informed Neural Network (DL-PINN) framework is proposed. Employing Meyerhof's bearing capacity equations as a physics-based constraint, the developed PINN integrated soil and geometric parameters directly into its training loss function. By combining these first-principles relationships with empirical data, the model preserved fundamental geotechnical mechanisms while refining predictive accuracy through dynamic weight adjustments between data-driven and physics-based loss components. Comparative experiments with a standard artificial neural network (ANN), using a dataset derived from the loaded-to-failure in-situ pile test and subsequent numerical simulations, demonstrated that although the ANN may attain lower statistical errors, the PINN's adherence to physical laws yields predictions that better align with established geotechnical behavior. This balance between physics fidelity and data adaptability may nominate these PINN frameworks to address the “black box” nature of deep learning in geotechnical applications. The paper also suggested the future research needs to fulfill the scientific and practical gap.

在岩土工程中，准确估计钻井竖井的轴向承载力一直是一个挑战，实测载荷测试结果与理论预测之间存在显著差异。为了弥补这一差距，提出了一种新的深度学习-物理-知情神经网络（DL-PINN）框架。采用Meyerhof承载力方程作为物理约束，将土壤和几何参数直接集成到其训练损失函数中。通过将这些第一性原理关系与经验数据相结合，该模型保留了基本的岩土力学机制，同时通过数据驱动和基于物理的损失分量之间的动态权重调整来提高预测精度。与标准人工神经网络（ANN）的对比实验，使用从加载到破坏的原位桩试验和随后的数值模拟中获得的数据集，表明尽管ANN可能获得更低的统计误差，但PINN对物理定律的遵守产生的预测更符合已建立的岩土力学行为。这种物理保真度和数据适应性之间的平衡可能会提名这些PINN框架来解决岩土工程应用中深度学习的“黑盒子”性质。本文还提出了未来的研究需要填补科学与实践的差距。

{"title":"A deep learning physics-informed neural network (PINN) for predicting drilled shaft axial capacity","authors":"M.E. Al-Atroush","doi":"10.1016/j.acags.2025.100246","DOIUrl":"10.1016/j.acags.2025.100246","url":null,"abstract":"<div><div>Accurately estimating the axial capacity of drilled shafts remains a persistent challenge in geotechnical engineering, as evidenced by significant discrepancies between measured load-test results and theoretical predictions. To bridge this gap, a novel Deep Learning–Physics-Informed Neural Network (DL-PINN) framework is proposed. Employing Meyerhof's bearing capacity equations as a physics-based constraint, the developed PINN integrated soil and geometric parameters directly into its training loss function. By combining these first-principles relationships with empirical data, the model preserved fundamental geotechnical mechanisms while refining predictive accuracy through dynamic weight adjustments between data-driven and physics-based loss components. Comparative experiments with a standard artificial neural network (ANN), using a dataset derived from the loaded-to-failure in-situ pile test and subsequent numerical simulations, demonstrated that although the ANN may attain lower statistical errors, the PINN's adherence to physical laws yields predictions that better align with established geotechnical behavior. This balance between physics fidelity and data adaptability may nominate these PINN frameworks to address the “black box” nature of deep learning in geotechnical applications. The paper also suggested the future research needs to fulfill the scientific and practical gap.</div></div>","PeriodicalId":33804,"journal":{"name":"Applied Computing and Geosciences","volume":"26 ","pages":"Article 100246"},"PeriodicalIF":2.6,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143917318","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

Prediction of rare and anomalous minerals using anomaly detection and machine learning techniques 使用异常检测和机器学习技术预测稀有和异常矿物

IF 2.6 Q2 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Applied Computing and Geosciences

Pub Date : 2025-06-01 Epub Date: 2025-05-10 DOI: 10.1016/j.acags.2025.100250

Abish Sharapatov , Alisher Saduov , Nazerke Assirbek , Madiyar Abdyrov , Beibit Zhumabayev

This study applies machine learning to detect and classify anomalous minerals within a large mineralogical dataset, enhancing geological exploration and resource identification. Using Isolation Forest and One-Class SVM, we identified rare minerals with distinct physical and chemical properties that deviate from common mineral compositions. These anomalies were further grouped using KMeans clustering into three categories, each linked to different geological formation environments: evaporitic, metamorphic, and magmatic processes. The study also evaluates the reliability of these machine learning models using a statistical benchmark and explores the role of deep learning in improving anomaly detection. The findings demonstrate the potential of unsupervised learning to enhance mineral classification, reduce exploration costs, and improve predictive modeling for rare mineral deposits. Future research will refine these methods by integrating Deep Isolation Forest, Autoencoders, and Graph Neural Networks, further strengthening machine learning applications in geosciences.

本研究将机器学习应用于大型矿物学数据集中的异常矿物检测和分类，加强地质勘探和资源识别。利用隔离森林和一类支持向量机，我们识别出与普通矿物成分不同的具有独特物理和化学性质的稀有矿物。利用KMeans聚类将这些异常进一步分为三类，每一类都与不同的地质形成环境有关：蒸发作用、变质作用和岩浆作用。该研究还使用统计基准评估了这些机器学习模型的可靠性，并探讨了深度学习在改进异常检测方面的作用。这些发现证明了无监督学习在增强矿物分类、降低勘探成本和改进稀有矿床预测建模方面的潜力。未来的研究将通过整合深度隔离森林、自动编码器和图神经网络来完善这些方法，进一步加强机器学习在地球科学中的应用。

{"title":"Prediction of rare and anomalous minerals using anomaly detection and machine learning techniques","authors":"Abish Sharapatov , Alisher Saduov , Nazerke Assirbek , Madiyar Abdyrov , Beibit Zhumabayev","doi":"10.1016/j.acags.2025.100250","DOIUrl":"10.1016/j.acags.2025.100250","url":null,"abstract":"<div><div>This study applies machine learning to detect and classify anomalous minerals within a large mineralogical dataset, enhancing geological exploration and resource identification. Using Isolation Forest and One-Class SVM, we identified rare minerals with distinct physical and chemical properties that deviate from common mineral compositions. These anomalies were further grouped using KMeans clustering into three categories, each linked to different geological formation environments: evaporitic, metamorphic, and magmatic processes. The study also evaluates the reliability of these machine learning models using a statistical benchmark and explores the role of deep learning in improving anomaly detection. The findings demonstrate the potential of unsupervised learning to enhance mineral classification, reduce exploration costs, and improve predictive modeling for rare mineral deposits. Future research will refine these methods by integrating Deep Isolation Forest, Autoencoders, and Graph Neural Networks, further strengthening machine learning applications in geosciences.</div></div>","PeriodicalId":33804,"journal":{"name":"Applied Computing and Geosciences","volume":"26 ","pages":"Article 100250"},"PeriodicalIF":2.6,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143937834","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 Indian summer monsoon prediction: Deep learning approach for skillful long-lead forecasts of rainfall 加强印度夏季风预测：深度学习方法用于熟练的长期降雨预测

IF 2.6 Q2 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Applied Computing and Geosciences

Pub Date : 2025-06-01 Epub Date: 2025-06-11 DOI: 10.1016/j.acags.2025.100257

Kalpesh R. Patil, Takeshi Doi, J.V. Ratnam, Swadhin K. Behera

The prediction of the Indian summer monsoon rainfall (ISMR) in the June–September (JJAS) season at long-lead times is challenging. The state-of-the-art dynamical models often fail to capture the sign and amplitude of the rainfall anomalies in the extreme rainfall seasons, limiting the overall skill of the models. We attempted to address this issue using a deep learning model based on convolutional neural networks (CNN). An ensemble of JJAS rainfall predictions using the CNN model with a unique custom function showed high skills in predicting ISMR at a long-lead time of 12 months. The predictions had an anomaly correlation coefficient (ACC) exceeding 0.5 at all the lead times from 2 to 17 months. The CNN model predictions could capture the sign and phase of the extreme rainfall events in the study period realistically. Analysis of saliency-based heatmaps indicated the high skill to be due to the model capturing the leading modes of climate variability, such as the Indian Ocean Dipole and El Niño-Southern Oscillation, realistically. The ensemble of CNN ISMR predictions can supplement the predictions of the forecasting centers.

6 - 9月（JJAS）季节的印度夏季季风降雨（ISMR）的长期预测是具有挑战性的。最先进的动力模式往往不能捕捉极端降雨季节降雨异常的信号和幅度，限制了模式的整体技能。我们尝试使用基于卷积神经网络（CNN）的深度学习模型来解决这个问题。使用CNN模型和独特的自定义函数的JJAS降雨预测集合显示出在12个月的长提前期预测ISMR的高技能。2 ~ 17个月的预测异常相关系数（ACC）均大于0.5。CNN模型预测能够真实地捕捉研究时段极端降雨事件的信号和阶段。对基于显著性的热图的分析表明，高技能是由于该模式实际捕获了气候变率的主要模式，如印度洋偶极子和El Niño-Southern振荡。CNN ISMR预测集合可以补充预报中心的预测。

{"title":"Enhancing Indian summer monsoon prediction: Deep learning approach for skillful long-lead forecasts of rainfall","authors":"Kalpesh R. Patil, Takeshi Doi, J.V. Ratnam, Swadhin K. Behera","doi":"10.1016/j.acags.2025.100257","DOIUrl":"10.1016/j.acags.2025.100257","url":null,"abstract":"<div><div>The prediction of the Indian summer monsoon rainfall (ISMR) in the June–September (JJAS) season at long-lead times is challenging. The state-of-the-art dynamical models often fail to capture the sign and amplitude of the rainfall anomalies in the extreme rainfall seasons, limiting the overall skill of the models. We attempted to address this issue using a deep learning model based on convolutional neural networks (CNN). An ensemble of JJAS rainfall predictions using the CNN model with a unique custom function showed high skills in predicting ISMR at a long-lead time of 12 months. The predictions had an anomaly correlation coefficient (ACC) exceeding 0.5 at all the lead times from 2 to 17 months. The CNN model predictions could capture the sign and phase of the extreme rainfall events in the study period realistically. Analysis of saliency-based heatmaps indicated the high skill to be due to the model capturing the leading modes of climate variability, such as the Indian Ocean Dipole and El Niño-Southern Oscillation, realistically. The ensemble of CNN ISMR predictions can supplement the predictions of the forecasting centers.</div></div>","PeriodicalId":33804,"journal":{"name":"Applied Computing and Geosciences","volume":"26 ","pages":"Article 100257"},"PeriodicalIF":2.6,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144291535","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