Quantitative evaluation of multiple-point simulations using image segmentation and texture descriptors

Abdollahifard, Mohammad Javad; Mariethoz, Grégoire; Ghavim, Maryam

doi:10.1007/s10596-019-09901-z

Cited by 8 publications

(4 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Respecting the patterns in the data and allowing sufficient variability is essential to produce correct predictions. Recent developments (Abdollahifard et al., 2019) aim to quantify variability and pattern consistency but with respect to the TI, not to the data. The advantage of our approach is that we no longer need to compare realizations with the training image and define quality indicators as in the works of Meerschman et al.…”

Section: Discussionmentioning

confidence: 99%

A Framework for the Cross‐Validation of Categorical Geostatistical Simulations

Juda

Renard

Straubhaar

2020

Earth and Space Science

View full text Add to dashboard Cite

The mapping of subsurface parameters and the quantification of spatial uncertainty requires selecting adequate models and their parameters. Cross‐validation techniques have been widely used for geostatistical model selection for continuous variables, but the situation is different for categorical variables. In these cases, cross‐validation is seldom applied, and there is no clear consensus on which method to employ. Therefore, this paper proposes a systematic framework for the cross‐validation of geostatistical simulations of categorical variables such as geological facies. The method is based on K‐fold cross‐validation combined with a proper scoring rule. It can be applied whenever an observation data set is available. At each cross‐validation iteration, the training set becomes conditioning data for the tested geostatistical model, and the ensemble of simulations is compared to true values. The proposed framework is generic. Its application is illustrated with two examples using multiple‐point statistics simulations. In the first test case, the aim is to identify a training image from a given data set. In the second test case, the aim is to identify the parameters in a situation including nonstationarity for a coastal alluvial aquifer in the south of France. Cross‐validation scores are used as metrics of model performance and quadratic scoring rule, zero‐one score, and balanced linear score are compared. The study shows that the proposed fivefold stratified cross‐validation with the quadratic scoring rule allows ranking the geostatistical models and helps to identify the proper parameters.

show abstract

Section: Discussionmentioning

confidence: 99%

A Framework for the Cross‐Validation of Categorical Geostatistical Simulations

Juda

Renard

Straubhaar

2020

Earth and Space Science

View full text Add to dashboard Cite

show abstract

“…Ref. [63] proposed a method for quantitative evaluation of MPS results, which involves estimating a coherence map using key point detection and matching. Ref.…”

Section: Introductionmentioning

confidence: 99%

Pixel-MPS: Stochastic Embedding and Density-Based Clustering of Image Patterns for Pixel-Based Multiple-Point Geostatistical Simulation

Asadi,

Chatterjee

2024

Geosciences

View full text Add to dashboard Cite

Multiple-point geostatistics (MPS) is an established tool for the uncertainty quantification of Earth systems modeling, particularly when dealing with the complexity and heterogeneity of geological data. This study presents a novel pixel-based MPS method for modeling spatial data using advanced machine-learning algorithms. Pixel-based multiple-point simulation implies the sequential modeling of individual points on the simulation grid, one at a time, by borrowing spatial information from the training image and honoring the conditioning data points. The developed methodology is based on the mapping of the training image patterns database using the t-Distributed Stochastic Neighbor Embedding (t-SNE) algorithm for dimensionality reduction, and the clustering of patterns by applying the Density-based Spatial Clustering of Applications with Noise (DBSCAN) algorithm, as an efficient unsupervised classification technique. For the automation, optimization, and input parameter tuning, multiple stages are implemented, including entropy-based determination of the template size and a k-nearest neighbors search for clustering parameter selection, to ensure the proposed method does not require the user’s interference. The proposed model is validated using synthetic two- and three-dimensional datasets, both for conditional and unconditional simulations, and runtime information is provided. Finally, the method is applied to a case study gold mine for stochastic orebody modeling. To demonstrate the computational efficiency and accuracy of the proposed method, a two-dimensional training image with 101 by 101 pixels is simulated for 100 conditional realizations in 453 s (~4.5 s per realization) using only 361 hard data points (~3.5% of the simulation grid), and the resulting average simulation has a good visual match and only an 11.8% pixel-wise mismatch with the training image.

show abstract

“…In the joint SCS, a hierarchy of the dependent variables should be defined and a variable with the high correlation is the starting point of a co-simulation. Other attempts were done by other authors with different techniques, such as Multiple-Point Statistics approaches (MPS) with applications in subsurface modeling, remote sensing, climate modeling, and rainfall simulations with a training image adaption [23][24][25][26][27].…”

Section: Introductionmentioning

confidence: 99%

Mapping of Aluminum Concentration in Bauxite Mining Residues Using Sentinel-2 Imagery

Kasmaeeyazdi

Mandanici

Balomenos³

et al. 2021

Remote Sensing

View full text Add to dashboard Cite

There is a growing interest in the characterization of mining residues, both for environmental assessments and critical raw materials recovery. The lack of sufficient in situ samples hampers an effective geostatistical modelling of material concentrations variability. This paper proposes a method to characterize the aluminum spatial variability in a mine residue from remote sensing data and imprecise information from daily dumping procedures. The method is proposed for the mapping of aluminum within a Greek bauxite residue, using Sentinel-2 imagery. The spatial correlation between metal concentrations and remote sensing indicators (e.g., spectral band ratios) is the premise for mapping aluminum varieties. The proposed method is based on Conditional Gaussian Co-Simulation, where Sentinel-2 images can be used as auxiliary variables. Simulation results are compared with the Co-kriging estimation method. To perform the Co-kriging estimation, the same conditions as simulation are used (same inputs, models, and neighborhoods). Simulation results quantified the metals variability in mining residues, presenting the metal concentration of piled materials in two time periods. For results validation and selecting the best map, fourteen validation samples were used. For the best representative maps of aluminum concentration, a correlation coefficient of about 0.7 between the validation data and obtained aluminum concentration map was obtained.

show abstract

Quantitative evaluation of multiple-point simulations using image segmentation and texture descriptors

Cited by 8 publications

References 40 publications

A Framework for the Cross‐Validation of Categorical Geostatistical Simulations

A Framework for the Cross‐Validation of Categorical Geostatistical Simulations

Pixel-MPS: Stochastic Embedding and Density-Based Clustering of Image Patterns for Pixel-Based Multiple-Point Geostatistical Simulation

Mapping of Aluminum Concentration in Bauxite Mining Residues Using Sentinel-2 Imagery

Contact Info

Product

Resources

About