Seismic facies classification remains a critical yet challenging task in subsurface characterization due to the complexity of depositional systems and limitations of manual interpretation. This study presents a supervised deep learning workflow for seismic facies prediction using a dip-steered median filtered (DSMF) seismic volume. Ten facies label sets, representing minima and maxima responses, were derived from unsupervised vector quantization (UVQ) clustering and subsequently refined using Thalweg tracking, with 1,500 samples per class. These labels, together with the DSMF volume, were used to extract 3D cubelets (41×41×3) for training convolutional neural networks (CNNs). Three archite... More >

The pore structure of continental shale reservoirs is complex and diverse, exhibiting multi-scale pore size distributions spanning from nanometers to micrometers. In particular, accurate porosity measurement has remained a major challenge in shale reservoir characterization. To achieve accurate porosity determination for continental shale, this study takes the Gulong shale as a case example. Based on the fluid occupancy characteristics of shale pores, the pore space is classified into three types: gas-occupied, water-occupied, and oil-occupied pores. The volumes of these three pore types are measured experimentally via kerosene saturation, ethanol extraction, and solvent washing, respectivel... More >

Since its launch in 2025, Reservoir Science (RS) has completed its first year of development. This editorial reviews the journal’s progress over the past year, analyzes current challenges, and outlines future strategic directions. In the past year, RS has published 18 high-quality papers contributed by 63 authors from 7 countries and regions (as of May 30, 2026). The journal has been indexed in CAS. Adopting an Open Access model (CC BY), RS has established an international editorial board and published research covering reservoir exploration, characterization, CCUS, geothermal energy, underground hydrogen storage, reservoir materials science, environmental science, and artificial intellige... More >

Hydrocarbon reserve estimation and reservoir characterization remain critical aspects of field development planning, particularly in mature offshore basins such as the Niger Delta. This study integrates 3D seismic interpretation with petrophysical analysis to evaluate reservoir quality and estimate hydrocarbon volumes within the BUKS offshore field, Niger Delta, Nigeria. Structural interpretation of the seismic data identified a NNW-trending rollover anticline associated with four major listric growth faults (F1–F4), forming the principal trapping system in the field. Petrophysical evaluation of four wells revealed favourable reservoir properties, with average porosity values ranging from... More >

The selection of optimal artificial lift methods using machine learning remains challenging due to complex interactions among reservoir characteristics, fluid properties, and operational constraints. Conventional approaches rely on engineering expertise and static screening criteria, often insufficient to capture multifactorial dependencies. This study presents a framework for classifying the most suitable lift method from four common techniques: ESP, Gas Lift, Rod Pumps, and PCP. A dataset of 990 wells with twelve physically meaningful parameters was compiled, including depth, temperature, GOR, API gravity, reservoir pressure, water cut, production rate, viscosity, sand production, deviatio... More >

Owing to their high calorific value and sustainable characteristics, natural gas hydrates are expected to serve as a promising alternative energy resource to conventional oil and gas in the near future. Of course, this prospect relies on the premise that hydrates can be developed in a safe and efficient manner. Hydrate-bearing sediments are highly sensitive to temperature and pressure conditions and are therefore particularly vulnerable to disturbances induced by production operation, which may result in challenges such as wellhead instability. In this study, the physical parameters of artificially prepared hydrate-bearing sediments were experimentally characterized to provide a parameter fo... More >

Heavy oil reservoirs often retain substantial remaining oil after polymer flooding with vertical wells due to unfavorable oil-water mobility ratios and reservoir heterogeneity. Although horizontal wells can improve oil displacement efficiency by providing a larger contact area with the formation, systematic studies on the displacement behavior and key influencing factors of polymer flooding in opposed horizontal wells are still lacking. This study addresses this gap by combining two-dimensional physical simulation experiments with Eclipse numerical simulation to investigate the displacement dynamics and remaining oil distribution. The experimental results show that increasing well spacing pr... More >

The morphological transformation of methane hydrates during re-exploitation, caused by depressurization and changes in reservoir environment, significantly impacts hydrate extraction. The present study explores the adsorption and desorption behaviour of methane under different environmental factors by constructing a rock adsorption and desorption device, which can contribute to the efficient extraction of methane during the decomposition of methane hydrates. The findings demonstrate that reservoir temperature strongly promotes methane desorption. Desorption capacity increased markedly above $100^{\circ}\mathrm{C}$, reaching $9.4~\mu\mathrm{g/g}$ at $120^{\circ}\mathrm{C}$, consistent with re... More >