Imputation in well log data: A benchmark for machine learning methods

PHT Gama, J Faria, J Sena, F Neves, VR Riffel… - Computers & …, 2024 - Elsevier
Well log data are an important source of information about the geological patterns along the
wellbore but may present missing values due to sensor failure, wellbore irregularities or the …

[HTML][HTML] Multi-horizon well performance forecasting with temporal fusion transformers

E Maldonado-Cruz, MJ Pyrcz - Results in Engineering, 2024 - Elsevier
Forecasting fluid flow in subsurface resources such as groundwater, geothermal, and oil and
gas is essential to maximize project economics and maximize resource recovery. We …

An Integrated Workflow for Data Analytics-Assisted Reservoir Management with Incomplete Well Log Data

E Artun, S Canbolat, EC Yildirim, C Acikgoz, O Yuruker - SPE Journal, 2024 - onepetro.org
Advancements in data collection, storage, and processing have facilitated the widespread
adoption of data-driven models for forecasting and decision-making in the oil and gas …

A Missing Well-Logs Imputation Method Based on Conditional Denoising Diffusion Probabilistic Models

H Meng, B Lin, R Zhang, Y Jin - SPE Journal, 2024 - onepetro.org
Well logs comprise sequential data detailing the geological properties of formations at
varying depths encountered during drilling. They are fundamental for various applications in …

Machine learning-based uncertainty models for reservoir property prediction and forecasting

E Maldonado Cruz - 2023 - repositories.lib.utexas.edu
In subsurface data analytics and machine learning, advances enable new methods and
workflows for spatio-temporal, geoscience, and engineering property estimation and …

[PDF][PDF] Estimation of Missing Well-Log Sections Using Machine Learning Assisted Multivariate Imputation: A Case Study

E Artun, S Canbolat, EC Yıldırım, C Açıkgöz, O Yürüker - researchgate.net
Collecting high-quality data in upstream operations is crucial because it can have a
significant impact on future exploration and development decisions. Low-quality data can …