Photoelectric factor prediction using automated learning and uncertainty quantification

被引:0
|
作者
Khalid Alsamadony
Ahmed Farid Ibrahim
Salaheldin Elkatatny
Abdulazeez Abdulraheem
机构
[1] King Fahd University of Petroleum & Minerals,Department of Petroleum Engineering
[2] King Fahd University of Petroleum & Minerals,Center for Integrative Petroleum Research
来源
Neural Computing and Applications | 2023年 / 35卷
关键词
Machine learning algorithms; Well logging; Photoelectric factor; Automated learning; Uncertainty quantification; Gaussian process regression; Fuzzy logic; Artificial neural network (ANN);
D O I
暂无
中图分类号
学科分类号
摘要
The photoelectric factor (PEF) is an important well-logging tool to distinguish between different types of reservoir rocks because PEF measurement is sensitive to elements with high atomic numbers. Furthermore, the ratio of rock minerals could be determined by combining PEF log with other well logs. However, PEF logs could be missing in some cases such as in old well logs and wells drilled with barite-based mud. Therefore, developing models for estimating missing PEF logs is essential in those circumstances. In this work, we developed various machine learning models to predict PEF values using the following well logs as inputs: bulk density (RHOB), neutron porosity (NPHI), gamma ray (GR), compressional and shear velocity. The predictions of PEF values using adaptive-network-fuzzy inference system (ANFIS) and artificial neural network (ANN) models have errors of about 16% and 14% average absolute percentage error (AAPE) in the testing dataset, respectively. Thus, a different approach was proposed that is based on the concept of automated machine learning. It works by automatically searching for the optimal model type and optimizes its hyperparameters for the dataset under investigation. This approach selected a Gaussian process regression (GPR) model for the accurate estimation of PEF values. The developed GPR model decreases the AAPE of the predicted PEF values in the testing dataset to about 10% AAPE. This error could be further decreased to about 2% by modeling the potential noise in the measurements using the GPR model.
引用
收藏
页码:22595 / 22604
页数:9
相关论文
共 50 条
  • [31] Bayesian deep learning for uncertainty quantification and prediction of jet grout column diameter
    Tamang, Rakam
    Zhu, Yichuan
    Coe, Joseph
    COMPUTERS AND GEOTECHNICS, 2025, 179
  • [32] Uncertainty Quantification of a Machine Learning Model for Identification of Isolated Nonlinearities With Conformal Prediction
    Najera-Flores, David A.
    Jacobs, Justin
    Dane Quinn, D.
    Garland, Anthony
    Todd, Michael D.
    JOURNAL OF VERIFICATION, VALIDATION AND UNCERTAINTY QUANTIFICATION, 2024, 9 (02):
  • [33] Conformalized Graph Learning for Molecular ADMET Property Prediction and Reliable Uncertainty Quantification
    Li, Peiyao
    Hua, Lan
    Ma, Zhechao
    Hu, Wenbo
    Liu, Ye
    Zhu, Jun
    JOURNAL OF CHEMICAL INFORMATION AND MODELING, 2024, 64 (23) : 8705 - 8717
  • [34] Uncertainty quantification for Bayesian active learning in rupture life prediction of ferritic steels
    Osman Mamun
    M. F. N. Taufique
    Madison Wenzlick
    Jeffrey Hawk
    Ram Devanathan
    Scientific Reports, 12
  • [35] Streamflow Prediction with Uncertainty Quantification forWater Management: A Constrained Reasoning and Learning Approach
    Gharsallaoui, Mohammed Amine
    Singh, Bhupinderjeet
    Savalkar, Supriya
    Deshwal, Aryan
    Kalyanaraman, Ananth
    Rajagopalan, Kirti
    Doppa, Janardhan Rao
    PROCEEDINGS OF THE THIRTY-THIRD INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, IJCAI 2024, 2024, : 7269 - 7277
  • [36] Uncertainty quantification for Bayesian active learning in rupture life prediction of ferritic steels
    Mamun, Osman
    Taufique, M. F. N.
    Wenzlick, Madison
    Hawk, Jeffrey
    Devanathan, Ram
    SCIENTIFIC REPORTS, 2022, 12 (01)
  • [37] Stochastic Stratigraphic Simulation and Uncertainty Quantification Using Machine Learning
    Wang, Hui
    Wei, Xingxing
    GEO-CONGRESS 2022: SITE AND SOIL CHARACTERIZATION, COMPUTATIONAL GEOTECHNICS, RISK, AND LESSONS LEARNED, 2022, 333 : 337 - 346
  • [38] Uncertainty Quantification Using Ensemble Learning and Monte Carlo Sampling for Performance Prediction and Monitoring in Cell Culture Processes
    Khuat, Thanh Tung
    Bassett, Robert
    Otte, Ellen
    Gabrys, Bogdan
    JOURNAL OF RAMAN SPECTROSCOPY, 2025,
  • [39] Prediction and uncertainty quantification of compressive strength of high-strength concrete using optimized machine learning algorithms
    Han, Bing
    Wu, Yanqi
    Liu, Lulu
    STRUCTURAL CONCRETE, 2022, 23 (06) : 3772 - 3785
  • [40] Probabilistic framework for strain-based fatigue life prediction and uncertainty quantification using interpretable machine learning
    Deng, Xi
    Zhu, Shun-Peng
    Wang, Lanyi
    Luo, Changqi
    Fu, Sicheng
    Wang, Qingyuan
    INTERNATIONAL JOURNAL OF FATIGUE, 2025, 190