Characterization of Subsurface Hydrogeological Structures With Convolutional Conditional Neural Processes on Limited Training Data

Cui, Zhesi; Chen, Qiyu

doi:10.1029/2022wr033161

Cited by 13 publications

(6 citation statements)

References 63 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Given the notable surge in the volume of observations and the rapid progression of deep learning as an advanced tool for data analysis (Cho et al., 2019), deep generative modeling techniques have facilitated significant progress in the characterization of spatial heterogeneity (Bai & Tahmasebi, 2020; Cui et al., 2022, 2023; K. Liu et al., 2019; Y. Liu et al., 2019; A. Y. Sun, 2018).…”

Section: Introductionmentioning

confidence: 99%

SA‐RelayGANs: A Novel Framework for the Characterization of Complex Hydrological Structures Based on GANs and Self‐Attention Mechanism

Cui,

Chen,

Liu

et al. 2024

Water Resources Research

Self Cite

View full text Add to dashboard Cite

Increased availability and quality of surface and subsurface observations provide the chance to improve the perception of hydrological phenomena. An important factor that hinders our understanding of hydrological structures is the characterization of heterogeneous patterns with continuous attributes inside the structures (e.g., porosity, permeability, fluid saturation, etc.). Unlike categorical attributes, continuous attributes convey more realistic characteristics but require more computational resources to characterize such complex earth systems. In this work, we propose a novel deep learning approach for the characterization of complex hydrological realism with continuous attributes based on generative adversarial networks (GANs) and self‐attention mechanism, named SA‐RelayGANs. To address the complexity of heterogeneous hydrological structures, we divide the modeling process into two stages: facies construction stage and property reconstruction stage. In the first stage, we employ an improved GAN with self‐attention mechanism to construct the heterogeneous structures while adhering to hard conditioning constraints. In the second stage, we utilize another GAN with an attribute enhancement term to reconstruct realizations based on the constructed structures and observations. SA‐RelayGANs can successfully predict the statistical distributions of heterogeneous structures with continuous attributes by using limited observations. This study highlights the effectiveness of using GANs to characterize the heterogeneous patterns of hydrological realism and the application over large geoscience fields.

show abstract

Section: Introductionmentioning

confidence: 99%

SA‐RelayGANs: A Novel Framework for the Characterization of Complex Hydrological Structures Based on GANs and Self‐Attention Mechanism

Cui,

Chen,

Liu

et al. 2024

Water Resources Research

Self Cite

View full text Add to dashboard Cite

show abstract

“…Geologic heterogeneity can also be characterized by assimilating dynamic data into hydraulic conductivity field using MPS (Kumar & Srinivasan, 2020). Despite the extensive applications of MPS in geological modeling, acquiring training images, especially for 3D situations, which accurately capture the actual pattern of modeling domain, remains a challenging task (Comunian et al., 2012; Cui et al., 2022). Additionally, there is always a trade‐off between the realism of simulated structural patterns and the increased demand on CPU and/or RAM incurred by tuning specific parameters in these MPS methods.…”

Section: Introductionmentioning

confidence: 99%

Borehole‐Based Interval Kriging for 3D Lithofacies Modeling

Song,

Tsai

2024

Water Resources Research

View full text Add to dashboard Cite

Developing a three‐dimensional (3D) lithofacies model from boreholes is critical for providing a coherent understanding of complex subsurface geology, which is essential for groundwater studies. This study aims to introduce a new geostatistical method—interval kriging—to efficiently conduct 3D borehole‐based lithological modeling with sand/non‐sand binary indicators. Interval kriging is a best linear unbiased estimator for irregular interval supports. Interval kriging considers 3D anisotropies between two orthogonal components—a horizontal plane and a vertical axis. A new 3D interval semivariogram is developed. To cope with the nonconvexity of estimation variance, the minimization of estimation variance is regulated with an additional regularization term. The minimization problem is solved by a global‐local genetic algorithm embedded with quadratic programming and Brent's method to obtain kriging weights and kriging length. Four numerical and real‐world case studies demonstrate that interval kriging is more computationally efficient than 3D kriging because the covariance matrix is largely reduced without sacrificing borehole data. Moreover, interval kriging produces more realistic geologic characteristics than 2.5D kriging, while conditional to spatial borehole data. Compared to the multiple‐point statistics (MPS) algorithm—SNESIM, interval kriging can reproduce the geological architecture and spatial connectivity of channel‐type features, meanwhile producing tabular‐type features with better connectivity. Because the regularization term constrains kriged value toward 0 or 1, interval kriging produces more certainty in sand/non‐sand classification than 2.5D kriging, 3D kriging, and SNESIM. In conclusion, interval kriging is an effective and efficient 3D geostatistical algorithm that can capture the 3D structural complexity while significantly reducing computational time.

show abstract

“…The importance of the reconnaissance stage is due to the identification and separation of potential and barren areas in terms of ore mineralization; the potential areas will be lost or not identified if there is any error or lack of accuracy during this stage [5,6]. Geochemical modeling of stream sediment samples using methods such as multifractal analysis, clustering, principal component analysis (PCA), factor analysis, and artificial neural networks (ANN) is a valuable tool for mineral exploration [7][8][9][10][11]. Each method has advantages and disadvantages for geochemical modeling of stream sediment samples [12][13][14].…”

Section: Introductionmentioning

confidence: 99%

Geochemical Modeling of Copper Mineralization Using Geostatistical and Machine Learning Algorithms in the Sahlabad Area, Iran

Shirazi,

Hezarkhani,

Shirazy

et al. 2023

Minerals

View full text Add to dashboard Cite

Analyzing geochemical data from stream sediment samples is one of the most proactive tools in the geochemical modeling of ore mineralization and mineral exploration. The main purpose of this study is to develop a geochemical model for prospecting copper mineralization anomalies in the Sahlabad area, South Khorasan province, East Iran. In this investigation, 709 stream sediment samples were analyzed using inductively coupled plasma mass spectrometry (ICP-MS), and geostatistical and machine learning techniques. Subsequently, hierarchical analysis (HA), Spearman’s rank correlation coefficient, concentration–area (C–A) fractal analysis, Kriging interpolation, and descriptive statistics studies were performed on the geochemical dataset. Machine learning algorithms, namely K-means clustering, factor analysis (FA), and linear discriminant analysis (LDA) were employed to deliver a comprehensive geochemical model of copper mineralization in the study area. The identification of trace elements and the predictor composition of copper mineralization, the separation of copper geochemical communities, and the investigation of the geochemical behavior of copper vs. its trace elements were targeted and accomplished. As a result, the elements Ag, Mo, Pb, Zn, and Sn were distinguished as trace elements and predictors of copper geochemical modeling in the study area. Additionally, geochemical anomalies of copper mineralization were identified based on trace elements. Conclusively, the nonlinear behavior of the copper element versus its trace elements was modeled. This study demonstrates that the integration and synchronous use of geostatistical and machine learning methods can specifically deliver a comprehensive geochemical modeling of ore mineralization for prospecting mineral anomalies in metallogenic provinces around the globe.

show abstract

Characterization of Subsurface Hydrogeological Structures With Convolutional Conditional Neural Processes on Limited Training Data

Cited by 13 publications

References 63 publications

SA‐RelayGANs: A Novel Framework for the Characterization of Complex Hydrological Structures Based on GANs and Self‐Attention Mechanism

SA‐RelayGANs: A Novel Framework for the Characterization of Complex Hydrological Structures Based on GANs and Self‐Attention Mechanism

Borehole‐Based Interval Kriging for 3D Lithofacies Modeling

Geochemical Modeling of Copper Mineralization Using Geostatistical and Machine Learning Algorithms in the Sahlabad Area, Iran

Contact Info

Product

Resources

About