Explore Richards Okiemute's peer-reviewed publications on Geo-energy (CCUS and Hydrogen storage), sustainable energy systems, and applied computational methods.
Current research
NuclearPolicyAfrica Energy
African Nuclear Standards and Technology Development Initiative
Richards Okiemute, Research Fellow
ASME Engineering for Change (E4C) Fellowship, in partnership with the American Society of Mechanical Engineers (ASME). Ongoing.
A structured assessment of the nuclear energy landscape across African nations: mapping national energy plans and key stakeholders, documenting knowledge gaps in nuclear technology standards, and reviewing the investment landscape. The output is a region-specific intelligence package to guide standards development and Africa–EU collaboration.
Artificial Intelligence in Subsurface Energy Systems: A Comprehensive Review of CO₂ Storage, Hydrogen Storage, and Geothermal Energy
Okiemute, R. O.*, Oyetunji, O. S., Yakubu, K. S., Ibrahim, U. F., Olude, D. A., & Abubakar, A.
Science World Journal, 21(3), 928–936. Published 29 September 2026.
*Corresponding author
Abstract
The global shift toward clean energy is turning deep underground rock layers into a vital infrastructure for storing energy and cutting carbon emissions. This paper examines how computer models and smart data tools are being used to improve three major areas: capturing and burying carbon dioxide, storing hydrogen underground for later use, and tapping into volcanic heat for geothermal energy. By analyzing 46 relevant peer-reviewed studies, this review shows how these models can quickly assess underground sites, monitor for gas leaks, handle the stress of repeated storage cycles, and help prevent small earthquakes. It compares the readiness of each technology, addresses current hurdles such as data gaps and the difficulty of interpreting "black box" models, and explores future trends including secure data sharing and automated safety systems.
@article{okiemute2026subsurface,
author = {Okiemute, Richards Obada and Oyetunji, Oluwatimilehin Samuel and Yakubu, Kabiru Sani and Ibrahim, Umar Faruk and Olude, Dolapo Abraham and Abubakar, Abdulbasid},
title = {Artificial Intelligence in Subsurface Energy Systems: A Comprehensive Review of {CO$_2$} Storage, Hydrogen Storage, and Geothermal Energy},
journal = {Science World Journal},
volume = {21},
number = {3},
pages = {928--936},
year = {2026},
url = {https://scienceworldjournal.org/article/view/24856}
}
2025
Nuclear FusionAI/MLSustainable Energy
Application of Artificial Intelligence in Shaping the Future of Sustainable Nuclear Fusion Energy
Emmanuel, E. T., Thanni, A. A., Jimson, I. O., Okiemute, R. O., Muritala, I. O., & Igbokwe, O. F.
World Journal of Advances in Engineering and Technology Studies (WJAETS), 17(01), 041–060. 2025.
Abstract
This review examines the expanding contribution of artificial intelligence to fusion science, focusing on machine learning and deep learning for modelling, control and data interpretation. Drawing on a decade of peer-reviewed work, it finds that these methods enable markedly faster diagnostic inference, real-time plasma control through reinforcement learning, and large reductions in transport-model computation and cost through physics-informed neural networks, while AI–physics hybrid modelling lifts predictive accuracy beyond conventional simulation. It also sets out persistent challenges: fusion data remains hard to standardise, many models lack interpretability, reactors demand frequent recalibration, and ethical and operational constraints slow roll-out. The review argues that AI in fusion must become more physics-aware, adaptive and transparent, complementing rather than replacing the traditional scientific method.
@article{emmanuel2025fusion,
author = {Emmanuel, E. T. and Thanni, A. A. and Jimson, I. O. and Okiemute, R. O. and others},
title = {Application of Artificial Intelligence in Shaping the Future of Sustainable Nuclear Fusion Energy},
journal = {World Journal of Advances in Engineering and Technology Studies},
volume = {17},
number = {1},
pages = {041--060},
year = {2025},
doi = {10.30574/wjaets.2025.17.1.1378}
}
AI/MLOil & GasPredictive Maintenance
Leveraging Machine Learning and Data Analytics for Equipment Reliability in Oil and Gas Using Predictive Maintenance
Ekunke, O. V., Okiemute, R. O., Oke, B. O., Jimson, I. O., Iwalokun, A. O., Akinbolusere, M. O., & Pius, A. B.
World Journal of Advanced Research and Reviews, 25(01), 2212–2218. January 2025.
Abstract
The oil and gas industry operates under extreme conditions that make equipment reliability a persistent challenge. Predictive maintenance, now possible through machine learning and data analytics, is changing equipment management by enabling real-time failure prediction, reducing unplanned downtime and optimising maintenance schedules. This review covers advances in supervised and unsupervised machine learning, deep learning models and integration with IoT and big-data analytics, and summarises case studies from major international oil companies including Shell, BP, ExxonMobil, Chevron and TotalEnergies. It compares key performance indicators between traditional and predictive approaches and examines the advantages, challenges and future opportunities of predictive maintenance for operational efficiency and sustainability in the sector.
@article{ekunke2025predictive,
author = {Ekunke, Onyeka Virginia and Okiemute, Richards Obada and Oke, Bioluwatife Oluwaferanmi and Jimson, Israel Oluwaseun and Iwalokun, Austine Oluwole and Akinbolusere, Michael Oluwatosin and Pius, Awe Boluwatife},
title = {Leveraging Machine Learning and Data Analytics for Equipment Reliability in Oil and Gas Using Predictive Maintenance},
journal = {World Journal of Advanced Research and Reviews},
volume = {25},
number = {1},
pages = {2212--2218},
month = jan,
year = {2025},
doi = {10.30574/wjarr.2025.25.1.0295}
}
2024
CCUSDownstreamEmissions
Investigation into the Feasibility and Efficiency of Implementing Carbon Capture and Storage Technologies in Downstream Facilities: To Mitigate Greenhouse Gas Emissions
Godwin, E. O., Odey, P. O., Okiemute, R. O., Owunna, I. B., Asere, J. B., & Enem, C. E.
World Journal of Advanced Research and Reviews, 24(02), 1004–1016. November 2024.
Abstract
This research investigates the feasibility and efficiency of carbon capture and storage (CCS) technologies in downstream oil and gas facilities, such as refining, distribution, petrochemical production and retail, as a means of cutting greenhouse gas emissions. It examines three primary CCS techniques — post-combustion, pre-combustion and oxy-fuel combustion — each of which permits continued use of fossil-fuel sources while reducing CO₂ output. Post-combustion suits retrofitting existing plants, pre-combustion captures CO₂ at around 90% efficiency while producing hydrogen as a by-product, and oxy-fuel combustion yields a pure CO₂ stream for new-build facilities. The study also covers CCS applications in enhanced oil recovery and industrial decarbonisation, and weighs high costs, infrastructure needs and regulatory requirements against each technology's suitability for existing or new installations.
@article{godwin2024ccs,
author = {Godwin, Ekunke Odor and Odey, Peter Odey and Okiemute, Richards Obada and Owunna, Ikechukwu Bismarck and Asere, Joshua Babatunde and Enem, Chukwudike Eric},
title = {Investigation into the Feasibility and Efficiency of Implementing Carbon Capture and Storage Technologies in Downstream Facilities: To Mitigate Greenhouse Gas Emissions},
journal = {World Journal of Advanced Research and Reviews},
volume = {24},
number = {2},
pages = {1004--1016},
month = nov,
year = {2024},
doi = {10.30574/wjarr.2024.24.2.3438}
}
EORReservoir Eng.Biopolymers
Enhanced Oil Recovery Methods Using Biodegradable Materials in Different Reservoirs
Ekunke, O. V., Nzereogu, S. K., Uyanah, J. J., Okiemute, R. O., Ikechukwu, S. V., Ifechukwu, E. J., Collins, I., Chadi, P., Ibe, M. E., & Dauda, Y. P.
Global Scientific Journal (GSJ), 12(9), 647–664. September 2024.
Abstract
This review examines the use of biodegradable materials in enhanced oil recovery (EOR), highlighting their environmental benefits over traditional methods, and explores how biosurfactants, biopolymers and microbial formulations perform in different reservoir types. Biosurfactants, derived from microorganisms and plants, reduce interfacial tension and improve recovery in sandstone and carbonate reservoirs; biopolymers such as guar gum and xanthan gum improve fluid stability and sweep efficiency in heavy-oil and unconventional reservoirs; and microbial EOR uses bacteria to maximise oil displacement. The review weighs the advantages and limitations of these materials, including technical and industry-adoption challenges, and closes with recommendations for advancing biodegradable EOR technologies to improve sustainability and reduce environmental impact.
@article{ekunke2024eor,
author = {Ekunke, Onyeka Virginia and Nzereogu, Stella Kosi and Uyanah, Joseph Junior and Okiemute, Richards Obada and Ikechukwu, Stephen Victor and Ifechukwu, Enem Jeffery and Collins, Ikiebe and Chadi, Paul and Ibe, Madujibeya Ebuka and Dauda, Yusuf Peter},
title = {Enhanced Oil Recovery Methods Using Biodegradable Materials in Different Reservoirs},
journal = {Global Scientific Journal},
volume = {12},
number = {9},
pages = {647--664},
month = sep,
year = {2024}
}
DrillingSustainabilityOil & Gas
Advancements in Eco-friendly Drilling Fluids: A Review of Recent Innovations and Their Environmental Impacts
Ekunke, O. V., Nzereogu, S. K., Oluyimika, J. O., Okiemute, R. O., Agbonze, N. G., Ugbine, O. F., & Bello, A. R.
International Journal of Advances in Engineering and Management (IJAEM), 6(9), 179–187. September 2024.
Abstract
With growing environmental concerns, the oil and gas industry is increasingly turning to sustainable alternatives to traditional drilling fluids, which have been linked to ecological damage. This review examines recent advances in eco-friendly drilling fluids, focusing on biodegradable and non-toxic formulations — biopolymers, biosurfactants and plant-based oils — and their potential to replace conventional fluids across different geological settings. It addresses the scalability and economic viability of these alternatives, their effectiveness under extreme drilling conditions, and their compatibility with existing drilling technologies, while noting that significant gaps remain in long-term environmental-impact studies and comprehensive risk assessment. The review also considers the role of regulatory frameworks in supporting adoption, aiming to guide the industry toward more environmentally responsible drilling practices without sacrificing performance.
@article{ekunke2024drilling,
author = {Ekunke, Onyeka Virginia and Nzereogu, Stella Kosi and Oluyimika, Jaiyeola Omowoleola and Okiemute, Richards Obada and Agbonze, Nosa Godwin and Ugbine, Oghenefegor Favour and Bello, Afolabi Ridwan},
title = {Advancements in Eco-friendly Drilling Fluids: A Review of Recent Innovations and Their Environmental Impacts},
journal = {International Journal of Advances in Engineering and Management},
volume = {6},
number = {9},
pages = {179--187},
month = sep,
year = {2024}
}
IoTAI/MLCybersecurity
Identifying Internet of Things Devices through Unique Digital Signatures and Advanced Machine Learning Techniques
Akintayo, T. A., Okiemute, R. O., Owoeye, M. C., Balogun, O. S., Paul, C., Queenet, M. M. C., Okereke, R. O., Moluno, R. C., Adediran, A. S., Nzeanorue, C. C., Ngozi, E. R., & Madukwe, C. M.
Path of Science, 10(7), 1001–1007. July 2024.
Abstract
The rapid growth of the Internet of Things (IoT) has led to a surge in connected devices across sectors, making reliable device recognition increasingly important. This paper proposes a device-fingerprinting method that analyses network behaviour, communication patterns and hardware features, using machine learning to classify device fingerprints with high accuracy across sensors, actuators and intelligent appliances. The method effectively detects suspicious devices and has low computational overhead, making it suitable for real-time deployment; its effectiveness is demonstrated through testing and validation on multiple IoT datasets. The approach offers benefits for IoT ecosystem management, including enhanced security, improved network management and greater visibility into device behaviour.
@article{akintayo2024iot,
author = {Akintayo, Taiwo Abdulahi and Okiemute, Richards Obada and Owoeye, Moyosore Celestina and Balogun, Oluwaseyi Sulaimon and Paul, Chadi and Queenet, Madumere Madumere Chiamaka and Okereke, Ruth Onyekachi and Moluno, Richie Chukwunalu and Adediran, Adedokun Seyi and Nzeanorue, Christian Chukwuemeka and Ngozi, Egenuka Rhoda and Madukwe, Chika Moses},
title = {Identifying Internet of Things Devices through Unique Digital Signatures and Advanced Machine Learning Techniques},
journal = {Path of Science},
volume = {10},
number = {7},
pages = {1001--1007},
month = jul,
year = {2024}
}
Research and Fellowship Experience(Click to expand / collapse)
Research Fellow | ASME Engineering for Change (E4C) Fellowship
May 2026 – Nov 2026
Conducting desktop research on Africa Nuclear Energy and Technology Development Initiatives across South Africa, Egypt, Nigeria, Ghana, and Kenya.
Leading research on South Africa’s energy landscape, energy mix including Green Hydrogen, biomass, hydropower, solar energy, CSP, wind power, and emerging energy technologies (P2X, EVs).
Developing Stakeholders Mapping database and evaluating local/international supply chains in South Africa's energy ecosystem.
Graduate Research Assistant | University of Benin, Nigeria
Jan 2023 – Nov 2025
Developed CO₂StoreCap, an assistant for estimating storage capacity, assessing trapping and leakage risks, and optimizing injection and monitoring strategies.
Designed a K-Means clustering model for lithology classification in sandstone–shale intercalations, enhancing understanding of subsurface heterogeneity.
Graduate Research Engineer (Computational Modeling & Systems Optimization) | Welltec Oilfield Services
Jan 2020 – May 2022
Conducted data collection, cleaning, and transformation for model training and validation.
Applied Random Forest, Linear Regression, and XGBoost to automate system performance prediction, achieving an R² score of 97.43% and reducing operational downtime by 15%.
Mathematics Teacher | Government Girls Secondary School (UBE), Rivers State, Nigeria (NYSC)
Feb 2019 – Oct 2020
Taught mathematics to Junior Secondary School classes (age group 8–13 years) for two terms.
Improved student passing score by 83% from 45%.
Graded over 200 examinations and test scripts.
Undergraduate Researcher | Petroleum Training Institute (PTI), Delta State, Nigeria
Jul 2018 – Sept 2018
Thesis: Analysis of Water Coning in Vertical Oil Wells in Niger Delta.
Performed parametric and sensitivity analysis using four models (Meyer and Garder, Schols, Chaperon, Hoyland et al.) to determine water breakthrough time and critical production rates.
Identified Hoyland et al. for optimal production rates and Meyer and Garder for breakthrough time prediction.
Undergraduate Researcher (National Diploma) | Petroleum Training Institute (PTI), Delta State, Nigeria
May 2014 – Oct 2014
Thesis: Reservoir Pressure Maintenance to Increase Oil Production by Water Injection Method (Obagi Oil Field, OML 58).
Conducted case study analyzing historical production and pressure trend data (1964–1996) to evaluate water injection as a secondary recovery method.
Performed correlation analysis showing increased injection volumes drove production recovery to 62,625 BOPD.
Gas Development & Energy Analyst Intern | Nigeria National Petroleum Corporation (NNPC-NAPIMS)
Apr 2017 – Sept 2017
Reviewed First E&P's OML 83 & 85 gas development plan and strategy, evaluating phased processing build-out (300 MMscfd initial, scaling to 900 MMscfd) against a joint production forecast plateau of 640 MMscfd.
Contributed to review of Assa North Field Development Plan (FDP) and supported gas division's gas flare-out programme compliance tracking.
Education(Click to expand / collapse)
BSc. Petroleum Engineering | University of Benin, Nigeria
Feb 2015 – Sept 2018
Dissertation: Analysis of Water Coning in Vertical Oil Wells in Niger Delta, Nigeria.
Advisor: Professor Ohenhen Ikponmwosa.
Diploma in Petroleum Engineering Technology | Petroleum Training Institute, Nigeria
Nov 2011 – Oct 2014
Dissertation: Reservoir Pressure Maintenance to Improve Oil Production from Depleted Reservoirs.