Cargando…

Echo State Neural Network Based on an Improved Gray Wolf Algorithm Predicts Porosity through Logging Data

[Image: see text] In oil exploration and development, many reservoir parameters are very essential for reservoir description, especially porosity. The porosity obtained by indoor experiments is reliable, but human and material resources will be greatly invested. Experts have introduced machine learn...

Descripción completa

Detalles Bibliográficos
Autores principales: Youzhuang, Sun, Junhua, Zhang, Yongan, Zhang
Formato: Online Artículo Texto
Lenguaje:English
Publicado: American Chemical Society 2023
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10268646/
https://www.ncbi.nlm.nih.gov/pubmed/37332818
http://dx.doi.org/10.1021/acsomega.3c02217
_version_ 1785059133528997888
author Youzhuang, Sun
Junhua, Zhang
Yongan, Zhang
author_facet Youzhuang, Sun
Junhua, Zhang
Yongan, Zhang
author_sort Youzhuang, Sun
collection PubMed
description [Image: see text] In oil exploration and development, many reservoir parameters are very essential for reservoir description, especially porosity. The porosity obtained by indoor experiments is reliable, but human and material resources will be greatly invested. Experts have introduced machine learning into the field of porosity prediction but with the shortcomings of traditional machine learning models, such as hyperparameter abuse and poor network structure. In this paper, a meta-heuristic algorithm (Gray Wolf Optimization algorithm) is introduced to optimize the ESN (echo state neural) network for logging porosity prediction. Tent mapping, a nonlinear control parameter strategy, and PSO (particle swarm optimization) thought are introduced to optimize the Gray Wolf Optimization algorithm to improve the global search accuracy and avoid local optimal solutions. The database is constructed by using logging data and porosity values measured in the laboratory. Five logging curves are used as model input parameters, and porosity is used as the model output parameter. At the same time, three other prediction models (BP neural network, least squares support vector machine, and linear regression) are introduced to compare with the optimized models. The research results show that the improved Gray Wolf Optimization algorithm has more advantages than the ordinary Gray Wolf Optimization algorithm in terms of super parameter adjustment. The IGWO-ESN neural network is better than all machine learning models mentioned in this paper (GWO-ESN, ESN, BP neural network, least squares support vector machine, and linear regression) in terms of porosity prediction accuracy.
format Online
Article
Text
id pubmed-10268646
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher American Chemical Society
record_format MEDLINE/PubMed
spelling pubmed-102686462023-06-16 Echo State Neural Network Based on an Improved Gray Wolf Algorithm Predicts Porosity through Logging Data Youzhuang, Sun Junhua, Zhang Yongan, Zhang ACS Omega [Image: see text] In oil exploration and development, many reservoir parameters are very essential for reservoir description, especially porosity. The porosity obtained by indoor experiments is reliable, but human and material resources will be greatly invested. Experts have introduced machine learning into the field of porosity prediction but with the shortcomings of traditional machine learning models, such as hyperparameter abuse and poor network structure. In this paper, a meta-heuristic algorithm (Gray Wolf Optimization algorithm) is introduced to optimize the ESN (echo state neural) network for logging porosity prediction. Tent mapping, a nonlinear control parameter strategy, and PSO (particle swarm optimization) thought are introduced to optimize the Gray Wolf Optimization algorithm to improve the global search accuracy and avoid local optimal solutions. The database is constructed by using logging data and porosity values measured in the laboratory. Five logging curves are used as model input parameters, and porosity is used as the model output parameter. At the same time, three other prediction models (BP neural network, least squares support vector machine, and linear regression) are introduced to compare with the optimized models. The research results show that the improved Gray Wolf Optimization algorithm has more advantages than the ordinary Gray Wolf Optimization algorithm in terms of super parameter adjustment. The IGWO-ESN neural network is better than all machine learning models mentioned in this paper (GWO-ESN, ESN, BP neural network, least squares support vector machine, and linear regression) in terms of porosity prediction accuracy. American Chemical Society 2023-05-31 /pmc/articles/PMC10268646/ /pubmed/37332818 http://dx.doi.org/10.1021/acsomega.3c02217 Text en © 2023 The Authors. Published by American Chemical Society https://creativecommons.org/licenses/by-nc-nd/4.0/Permits non-commercial access and re-use, provided that author attribution and integrity are maintained; but does not permit creation of adaptations or other derivative works (https://creativecommons.org/licenses/by-nc-nd/4.0/).
spellingShingle Youzhuang, Sun
Junhua, Zhang
Yongan, Zhang
Echo State Neural Network Based on an Improved Gray Wolf Algorithm Predicts Porosity through Logging Data
title Echo State Neural Network Based on an Improved Gray Wolf Algorithm Predicts Porosity through Logging Data
title_full Echo State Neural Network Based on an Improved Gray Wolf Algorithm Predicts Porosity through Logging Data
title_fullStr Echo State Neural Network Based on an Improved Gray Wolf Algorithm Predicts Porosity through Logging Data
title_full_unstemmed Echo State Neural Network Based on an Improved Gray Wolf Algorithm Predicts Porosity through Logging Data
title_short Echo State Neural Network Based on an Improved Gray Wolf Algorithm Predicts Porosity through Logging Data
title_sort echo state neural network based on an improved gray wolf algorithm predicts porosity through logging data
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10268646/
https://www.ncbi.nlm.nih.gov/pubmed/37332818
http://dx.doi.org/10.1021/acsomega.3c02217
work_keys_str_mv AT youzhuangsun echostateneuralnetworkbasedonanimprovedgraywolfalgorithmpredictsporositythroughloggingdata
AT junhuazhang echostateneuralnetworkbasedonanimprovedgraywolfalgorithmpredictsporositythroughloggingdata
AT yonganzhang echostateneuralnetworkbasedonanimprovedgraywolfalgorithmpredictsporositythroughloggingdata