Unconventional hydrocarbon resources: geological statistics, petrophysical characterization, and field development strategies

T Muther, HA Qureshi, FI Syed, H Aziz, A Siyal… - Journal of Petroleum …, 2022 - Springer
Hydrocarbons exist in abundant quantity beneath the earth's surface. These hydrocarbons
are generally classified as conventional and unconventional hydrocarbons depending upon …

Machine learning-based shale wettability prediction: Implications for H2, CH4 and CO2 geo-storage

B Pan, T Song, M Yue, S Chen, L Zhang… - International Journal of …, 2024 - Elsevier
Shale wettability determines shale gas productivities and gas (H 2, CH 4 and CO 2) geo-
storage efficiencies. However, shale wettability is a complex parameter which depends on …

[PDF][PDF] Pore-GNN: A graph neural network-based framework for predicting flow properties of porous media from micro-CT images.

MK Alzahrani, A Shapoval, Z Chen… - Advances in Geo-Energy …, 2023 - core.ac.uk
This paper presents a hybrid deep learning framework that combines graph neural networks
with convolutional neural networks to predict porous media properties. This approach …

A general-purpose tool for modeling multifunctional thin porous media (POREnet): From pore network to effective property tensors

PA García-Salaberri, IV Zenyuk - Heliyon, 2024 - cell.com
POREnet, a novel approach to model effective properties of thin porous media, TPM, is
presented. The methodology allows the extraction of local effective property tensors by …

[HTML][HTML] Microfluidic droplet detection via region-based and single-pass convolutional neural networks with comparison to conventional image analysis methodologies

GP Rutkowski, I Azizov, E Unmann, M Dudek… - Machine Learning with …, 2022 - Elsevier
As the complexity of microfluidic experiments and the associated image data volumes scale,
traditional feature extraction approaches begin to struggle at both detection and analysis …

Geological reservoir characterization tasks based on computer vision techniques

L da Silva Bomfim, MVT Soares, AC Vidal… - Marine and Petroleum …, 2024 - Elsevier
Reservoir characterization is of great importance in oil and gas exploration and production.
To automate and improve the procedures involved in this task, several approaches in the …

MicroGraphNets: Automated characterization of the micro-scale wettability of porous media using graph neural networks

MK Alzahrani, A Shapoval, Z Chen, SS Rahman - Capillarity, 2024 - capi.yandypress.com
This study introduces MicroGraphNets, a deep learning framework for automating the
microscopic characterization of wettability in porous media using graph neural networks …

2D-to-3D image translation of complex nanoporous volumes using generative networks

TI Anderson, B Vega, J McKinzie, SA Aryana… - Scientific Reports, 2021 - nature.com
Image-based characterization offers a powerful approach to studying geological porous
media at the nanoscale and images are critical to understanding reactive transport …

Multivariate Geostatistical Simulation and Deep Q-Learning to optimize mining decisions

S Avalos, JM Ortiz - Mathematical Geosciences, 2023 - Springer
In open pit mines, the long-term scheduling defines how the mine should be developed.
Uncertainties in geological attributes makes the search for an optimal scheduling a …

Automatic well test interpretation method for circular reservoirs with changing wellbore storage using one-dimensional convolutional neural network

X Liu, W Zha, D Li, X Li, L Shen - Journal of Energy …, 2023 - asmedigitalcollection.asme.org
In order to develop reservoirs rationally, accurate reservoir parameters are usually obtained
through well test analysis. However, a good deal of well test data with changing wellbore …