Application of neural architecture search in lithology identification

Abstract Identifying rock types is the essential step in geological exploration because it guides reservoir description and development planning. Conventional methods that rely on empirical correlations or elementary machine learning approaches frequently produce suboptimal outcomes under complex, m...

Full description

Saved in:
Bibliographic Details
Main Authors: Yuhao Zhang, Hanmin Xiao, Meng Du, Qingjie Liu, Jingwei Tao, Yongcheng Luo, Li Peng, Jianbo Tan
Format: Article
Language:English
Published: SpringerOpen 2025-07-01
Series:Journal of Petroleum Exploration and Production Technology
Subjects:
Online Access:https://doi.org/10.1007/s13202-025-02039-y
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849333707533451264
author Yuhao Zhang
Hanmin Xiao
Meng Du
Qingjie Liu
Jingwei Tao
Yongcheng Luo
Li Peng
Jianbo Tan
author_facet Yuhao Zhang
Hanmin Xiao
Meng Du
Qingjie Liu
Jingwei Tao
Yongcheng Luo
Li Peng
Jianbo Tan
author_sort Yuhao Zhang
collection DOAJ
description Abstract Identifying rock types is the essential step in geological exploration because it guides reservoir description and development planning. Conventional methods that rely on empirical correlations or elementary machine learning approaches frequently produce suboptimal outcomes under complex, multidimensional subsurface conditions. Although recent advancements in Artificial Intelligence (AI) have introduced automated approaches, these often exhibit limited adaptability when confronted with intricate well-log data. To address these constraints, the present study proposes an enhanced Neural Architecture Search (NAS) framework featuring an expanded search space that incorporates advanced the deep learning constructs, including one-dimensional deep neural network (DNN), long short-term memory (LSTM), and Transformers. This comprehensive strategy facilitates the automated discovery of specialized network configurations specifically designed for lithology classification. Experimental findings indicate that the NAS-derived model achieves an accuracy of approximately 96% on lithology test data, underscoring its effectiveness in managing heterogeneity within complex formations. Furthermore, the incorporation of Shapley Additive Explanations (SHAP) enhances interpretability by quantifying the contribution of each logging parameter, thereby ensuring consistency with geological reasoning. These results highlight the potential of a geoscience-adaptive NAS methodology for lithology identification by delivering improved performance, greater adaptability, and reduced reliance on exhaustive manual tuning.
format Article
id doaj-art-9d2dfa77d3664c93ace1b320b5853e2c
institution Kabale University
issn 2190-0558
2190-0566
language English
publishDate 2025-07-01
publisher SpringerOpen
record_format Article
series Journal of Petroleum Exploration and Production Technology
spelling doaj-art-9d2dfa77d3664c93ace1b320b5853e2c2025-08-20T03:45:47ZengSpringerOpenJournal of Petroleum Exploration and Production Technology2190-05582190-05662025-07-0115811910.1007/s13202-025-02039-yApplication of neural architecture search in lithology identificationYuhao Zhang0Hanmin Xiao1Meng Du2Qingjie Liu3Jingwei Tao4Yongcheng Luo5Li Peng6Jianbo Tan7University of Chinese Academy of SciencesUniversity of Chinese Academy of SciencesUniversity of Chinese Academy of SciencesUniversity of Chinese Academy of SciencesShanghai Pukka Information Tech LtdResearch Institute of Tsinghua University in ShenzhenBeijing Ashoka Technology Development Co.Beijing Ashoka Technology Development Co.Abstract Identifying rock types is the essential step in geological exploration because it guides reservoir description and development planning. Conventional methods that rely on empirical correlations or elementary machine learning approaches frequently produce suboptimal outcomes under complex, multidimensional subsurface conditions. Although recent advancements in Artificial Intelligence (AI) have introduced automated approaches, these often exhibit limited adaptability when confronted with intricate well-log data. To address these constraints, the present study proposes an enhanced Neural Architecture Search (NAS) framework featuring an expanded search space that incorporates advanced the deep learning constructs, including one-dimensional deep neural network (DNN), long short-term memory (LSTM), and Transformers. This comprehensive strategy facilitates the automated discovery of specialized network configurations specifically designed for lithology classification. Experimental findings indicate that the NAS-derived model achieves an accuracy of approximately 96% on lithology test data, underscoring its effectiveness in managing heterogeneity within complex formations. Furthermore, the incorporation of Shapley Additive Explanations (SHAP) enhances interpretability by quantifying the contribution of each logging parameter, thereby ensuring consistency with geological reasoning. These results highlight the potential of a geoscience-adaptive NAS methodology for lithology identification by delivering improved performance, greater adaptability, and reduced reliance on exhaustive manual tuning.https://doi.org/10.1007/s13202-025-02039-yNeural architecture searchLithology identificationTight sandstone reservoirsDeep learningSHAP model interpretation
spellingShingle Yuhao Zhang
Hanmin Xiao
Meng Du
Qingjie Liu
Jingwei Tao
Yongcheng Luo
Li Peng
Jianbo Tan
Application of neural architecture search in lithology identification
Journal of Petroleum Exploration and Production Technology
Neural architecture search
Lithology identification
Tight sandstone reservoirs
Deep learning
SHAP model interpretation
title Application of neural architecture search in lithology identification
title_full Application of neural architecture search in lithology identification
title_fullStr Application of neural architecture search in lithology identification
title_full_unstemmed Application of neural architecture search in lithology identification
title_short Application of neural architecture search in lithology identification
title_sort application of neural architecture search in lithology identification
topic Neural architecture search
Lithology identification
Tight sandstone reservoirs
Deep learning
SHAP model interpretation
url https://doi.org/10.1007/s13202-025-02039-y
work_keys_str_mv AT yuhaozhang applicationofneuralarchitecturesearchinlithologyidentification
AT hanminxiao applicationofneuralarchitecturesearchinlithologyidentification
AT mengdu applicationofneuralarchitecturesearchinlithologyidentification
AT qingjieliu applicationofneuralarchitecturesearchinlithologyidentification
AT jingweitao applicationofneuralarchitecturesearchinlithologyidentification
AT yongchengluo applicationofneuralarchitecturesearchinlithologyidentification
AT lipeng applicationofneuralarchitecturesearchinlithologyidentification
AT jianbotan applicationofneuralarchitecturesearchinlithologyidentification