Extreme learning machine for multivariate reservoir characterization

Liu, Xingye; Ge, Qiang; Chen, Xiaohong; Li, Jingye; Chen, Yangkang

doi:10.1016/j.petrol.2021.108869

Cited by 25 publications

(3 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Further, these litho-facies were predicted throughout the 3D volume using seismic attributes as input features (Table 2) and litho-log from wells as target features. Previously, various scientists have successfully applied supervised and unsupervised ML methods on well logs and seismic data for litho-facies prediction (Wang and Carr, 2012;Bhattacharya et al, 2016;Zhang and Zhan, 2017;Chevitarese et al, 2018;Bressan et al, 2020;Liu et al, 2021;Xu et al, 2021;Babu et al, 2022). These studies were mostly applied two-or three-ML methods to interpret the lithological distribution in hydrocarbon and coal explorations.…”

Section: Discussionmentioning

confidence: 99%

“…As a result, integrating ML algorithms with the inputs of existing petrophysical and geophysical data enables geoscientists to categorize the different lithologies precisely. Several studies have successfully identified litho-facies on geophysical logs using statistical approaches, and supervised and unsupervised ML algorithms (Wang and Carr, 2012;Schmitt et al, 2013;Bhattacharya et al, 2016;Bressan et al, 2020;Xu et al, 2021), and reservoir characterization in petroleum exploration (Keynejad et al, 2019;Liu et al, 2021). On the other hand, only a few research works have been done to determine the various litho-facies and reservoir properties using seismic data (Zhang and Zhan, 2017;Chevitarese et al, 2018;Babu et al, 2022).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Accuracy assessment of various supervised machine learning algorithms in litho-facies classification from seismic data in the Penobscot field, Scotian Basin

Narayan,

Konka,

Chandra

et al. 2023

Front. Earth Sci.

View full text Add to dashboard Cite

Litho-facies classification is an essential task in characterizing the complex reservoirs in petroleum exploration and subsequent field development. The lithofacies classification at borehole locations is detailed but lacks in providing larger coverage areas. The acquired 3D seismic data provides global coverage for studying the reservoir facies heterogeneities in the study area. This study applies six supervised machine learning techniques (Random Forest, Support Vector Machine, Artificial Neural Network, Adaptive Boosting, Xtreme Gradient Boosting, and Multilayer Perceptron) to 3D post-stack seismic data to accurately estimate different litho-facies in inter-well regions and compares their performance. Initially, the efficacy of the said models was critically examined via the confusion matrix (accuracy and misclass) and evaluation matrix (precision, recall, F1-score) on the test data. It was found that all the machine learning models performed best in classifying the shale facies (87%–94%) followed by the sand (65%–79%) and carbonate facies (60%–78%) in the Penobscot field, Scotian Basin. On an overall accuracy scale, we found the multilayer perceptron method the best-performing tool, whereas the adaptive boosting method was the least-performing tool in classifying all three litho-facies in the current analysis. While other methods also performed moderately good for the classification of all three litho-facies. The predicted litho-facies using seismic attributes matched well with the log data interpreted facies on the borehole locations. It indicates that the facies estimated in inter-well regions are accurate and reliable. Furthermore, we validated the estimated results with the other seismic attributes to ascertain the accuracy and reliability of the predicted litho-facies between the borehole locations. This study recommends machine learning applications for litho-facies classification to reduce the risk associated with reservoir characterization.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Accuracy assessment of various supervised machine learning algorithms in litho-facies classification from seismic data in the Penobscot field, Scotian Basin

Narayan,

Konka,

Chandra

et al. 2023

Front. Earth Sci.

View full text Add to dashboard Cite

show abstract

“…Extreme learning machine (ELM) is an enhanced version of a single hidden layer feedforward network with conventional potentials to adjust network weights (such as the output and input weights) and biases using traditional gradient descent approach [40,41]. However, this approach consumes appreciable training time with characteristic less efficiency [42]. Extreme learning machine algorithm trains single hidden layer feedforward network using amazing trick in which the values of the biases and input weights are chosen randomly and arbitrarily.…”

Section: Introductionmentioning

confidence: 99%

Specific Surface Area Characterization of Spinel Ferrite Nanostructure Based Compounds for Photocatalysis and Other Applications Using Extreme Learning Machine Method

Souiyah

Owolabi

Saliu

et al. 2022

Mathematical Problems in Engineering

View full text Add to dashboard Cite

Nanocrystalline spinel ferrite based compounds are technological driven materials with interesting potentials in photocatalysis for renewable energy generation, gas sensing for pollution control, magnetic drug delivery, rod antennas, storage media (high density) and supercapacitive materials, among others. Specific surface area of spinel ferrite based compounds contributes immensely to the application of this semiconductor in industrial domains. Experimental determination of specific surface area is laborious and costly and consumes appreciable time. Compositional substitutions in crystal structure effectively improve physical properties and enhance specific surface area through alteration of moment distribution between tetrahedral oxygen sites and octahedral coordination. With the aid of distorted lattice parameters due to compositional substitution and the spinel ferrite nanocrystallite size as model descriptors, this present work models the specific surface area of spinel ferrite nanomaterial through extreme learning machine (ELM) based intelligent modeling method. The developed sigmoid activation function-based ELM (S-ELM) model shows superior performance over genetic algorithm based support vector regression (GBSVR) and stepwise regression (STWR) models existing in the literature with performance improvement of 61.31% and 70.01%, respectively, using root mean square error performance metric. The significances of cobalt and lanthanum compositional substitution on the specific surface area of spinel ferrite nanomaterials were investigated using S-ELM model. Ease of implementation of S-ELM model as compared with the existing GBSVR model, coupled with the demonstrated improved performance and persistent closeness of its predictions with the experimental values, would be highly meritorious for quick and precise characterization of specific surface area of spinel ferrite nanomaterials for various desired applications.

show abstract