Xuejia Du

Dr. Xuejia Du

orcid

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
Verified
Journal Article
Open access
PDF file
Xuejia DuXuejia Du
Xuejia Du
SSSameer Salasakar
Sameer Salasakar
Ganesh C ThakurGanesh C Thakur
Ganesh C Thakur
This paper focuses on the current application of machine learning (ML) in enhanced oil recovery (EOR) through CO2 injection, which exhibits promising economic and environmental benefits for climate-change mitigation strategies. Our comprehensive review explores the diverse use cases of ML techniques in CO2-EOR, including aspects such as minimum miscible pressure (MMP) prediction, well location optimization, oil production and recovery factor prediction, multi-objective optimization, Pressure–Volume–Temperature (PVT) property estimation, Water Alternating Gas (WAG) analysis, and CO2-foam EOR, from 101 reviewed papers. We catalog relative information, including the input parameters, objectives, data sources, train/test/validate information, results, evaluation, and rating score for each area based on criteria such as data quality, ML-building process, and the analysis of results. We also briefly summarized the benefits and limitations of ML methods in petroleum industry applications. Our detailed and extensive study could serve as an invaluable reference for employing ML techniques in the petroleum industry. Based on the review, we found that ML techniques offer great potential in solving problems in the majority of CO2-EOR areas involving prediction and regression. With the generation of massive amounts of data in the everyday oil and gas industry, machine learning techniques can provide efficient and reliable preliminary results for the industry.

10 January 2025 in Journal of Genetics and Genomics
Verified
Journal Article
Closed access
CLChunrong Li
Chunrong Li
Xuejia DuXuejia Du
Xuejia Du
CLCuimin Liu
Cuimin Liu

11 April 2025 in Processes
Verified
Journal Article
Open access
PDF file
Xuejia DuXuejia Du
Xuejia Du
MKMuhammad Noman Khan
Muhammad Noman Khan
Ganesh C ThakurGanesh C Thakur
Ganesh C Thakur
Carbon Capture, Utilization, and Storage (CCUS) technologies have emerged as indispensable tools in reducing greenhouse gas (GHG) emissions and combating climate change. However, the optimization and scalability of CCUS processes face significant technical and economic challenges that hinder their widespread implementation. Machine Learning (ML) offers innovative solutions by providing faster, more accurate alternatives to traditional methods across the CCUS value chain. Despite the growing body of research in this field, the applications of ML in CCUS remain fragmented, lacking a cohesive synthesis that bridges these advancements to practical implementation. This review addresses this gap by systematically evaluating ML applications across all major CCUS components—CO2 capture, transport, storage, and utilization. We provide structured representative examples for each CCUS category and critically examine various ML techniques, optimization objectives, and methodological frameworks employed in recent studies. Additionally, we identify key parameters, practical limitations, and future opportunities for applying ML to enhance CCUS systems. Our review thus offers comprehensive insights and practical guidance to CCUS stakeholders, supporting informed decision-making and accelerating ML-driven CCUS commercialization.

17 May 2025 in Gases
Verified
Journal Article
Open access
PDF file
Xuejia DuXuejia Du
Xuejia Du
SGShihui Gao
Shihui Gao
GYGang Yang
Gang Yang
Hydrogen is increasingly recognized as a key contributor to a low-carbon energy future, and machine learning (ML) is emerging as a valuable tool to optimize hydrogen production processes. This review presents a comprehensive analysis of ML applications across various hydrogen production pathways, including gray, blue, and green hydrogen, with additional insights into pink, turquoise, white, and black/brown hydrogen. A total of 51 peer-reviewed studies published between 2012 and 2025 were systematically reviewed. Among these, green hydrogen—particularly via water electrolysis and biomass gasification—received the most attention, reflecting its central role in decarbonization strategies. ML algorithms such as artificial neural networks (ANNs), random forest (RF), and gradient boosting regression (GBR) have been widely applied to predict hydrogen yield, optimize operational conditions, reduce emissions, and improve process efficiency. Despite promising results, real-world deployment remains limited due to data sparsity, model integration challenges, and economic barriers. Nonetheless, this review identifies significant opportunities for ML to accelerate innovation across the hydrogen value chain. By highlighting trends, key methodologies, and current gaps, this study offers strategic guidance for future research and development in intelligent hydrogen systems aimed at achieving sustainable and cost-effective energy solutions.

9 August 2024 in Energies
Verified
Journal Article
Open access
PDF file
Xuejia DuXuejia Du
Xuejia Du
Ganesh C ThakurGanesh C Thakur
Ganesh C Thakur
This paper presents a comprehensive analysis of water injection management practices for complex and impactful onshore and offshore carbonate reservoirs. It delves into the fundamental aspects of waterflooding design, surveillance techniques, and monitoring methods tailored for the unique challenges posed by carbonate formations. Two case studies from the Permian Basin in Texas and two from Lula Field offshore Brazil and Agbami Field offshore Nigeria are examined considering scientific principles into practice to provide insights into best practices, lessons learned, and strategies to maximize the benefits derived from real noteworthy waterflood operations. The paper underscores the significance of rigorous reservoir characterization, including understanding reservoir architecture, heterogeneities, fracture networks, fluid communication pathways, and rock–fluid interactions. It emphasizes the crucial role of integrated multidisciplinary teams involving geologists, reservoir engineers, production engineers, and field operators in ensuring successful waterflood design, implementation, and optimization. Through the case studies, the paper highlights the importance of designing pattern configurations, well placements, and injection/production strategies to the specific reservoir characteristics, continually optimizing these elements based on surveillance data. It also stresses the necessity of comprehensive data acquisition, advanced analytics, numerical simulations, and frequent model updates for effective reservoir management and decision-making. The paper is impactful in terms of the lessons learned from the actual case studies, and how can these be implemented in actual field projects. Different case studies documented in the paper provide the challenges facing them and how different authors have addressed their problems in unique ways. The paper distills the information and important findings from a variety of case studies and provides succinct information that is of immense value as a reference. Important findings of these case studies are connected using creativity and are innovative as they introduce unique techniques and establish successful ideas to create new value in terms of maximizing oil recovery. Most importantly, this paper explores the application of innovative technologies, such as intelligent completions, 4D seismic monitoring, and water–alternating gas (WAG) injection, which can significantly improve waterflood performance in complex carbonate reservoirs. In summary, the paper provides a thorough understanding of the factors contributing to the success and failure of waterfloods in carbonate reservoirs through case studies based on factually and technically sound operations. It documents guidelines for optimizing waterflood performance and reducing or eliminating the potential for failures, reinforcing positive results in these challenging yet invaluable hydrocarbon resources.

17 April 2025 in Frontiers in Earth Science
Verified
Journal Article
Open access
PDF file
YZYuqi Zhang
Yuqi Zhang
Xuejia DuXuejia Du
Xuejia Du
DJDingwen Jiang
Dingwen Jiang
This study addresses wellbore instability in shale formations by conducting mechanical experiments on bedded shale samples with varying hydration times. We fitted experimental data using two anisotropic strength criteria to determine the shale’s strength parameters. A transverse isotropic stress model was developed to predict the lower limit of the safe drilling fluid density window, examining the effects of hydration time and anisotropy on wellbore stability. Results indicate that rock strength initially increases and then decreases with bedding angle. Within the β1 to β2 range, both the Jaeger’s Plane of Weakness model (JPW) and Plane of Patchy Weakness Model (PPW) accurately predicted shale strength; however, below β1, the JPW criterion overestimated strength, while the PPW criterion better reflected strength variations. Anisotropy due to bedding significantly increased wellbore collapse pressure, shifting the optimal well trajectory from the direction of minimum horizontal stress to maximum horizontal stress, altering collapse pressure contour distributions. The choice of strength criteria had minimal impact on the trend of collapse pressure with well trajectory. While shale hydration can significantly affect wellbore stability and the lower safe drilling mud window with well trajectory, prolonged contact between drilling fluid and rock gradually increased lower safe drilling mud window. Collapse pressure in vertical or horizontal wellbores was minimally affected by soaking time, whereas inclined wellbores showed greater sensitivity. Notably, horizontal wells drilled in the direction of minimum horizontal stress were more responsive to contact time with drilling fluid, leading to a faster increase in collapse pressure.