Impacts of Artificial Intelligence-Based Predictive Models for Enhanced Drilling Efficiency

Nanna Nanven Rimtip

Abstract


Drilling operations in Nigeria’s Niger Delta region are characterized by complex geological formations, high non-productive time (NPT), and operational risks that hinder efficiency and profitability. This study investigates the application of Artificial Intelligence (AI)-driven predictive analytics to optimize drilling operations, with a focus on enhancing drilling efficiency, reducing downtime, and minimizing operational risks. Using a mixed-methods approach, historical drilling data and real-time operational parameters were analyzed through machine learning models, including Random Forest, Support Vector Machine (SVM), and Artificial Neural Networks (ANNs). The results demonstrate that AI models significantly improve key operational metrics, with the ANN model achieving an R² score of 0.91 in predicting rate of penetration (ROP) and an 88% accuracy rate in forecasting NPT events. Additionally, the deployment of AI-enabled real-time monitoring systems reduced safety incidents by 15% and equipment downtime by 26%. These findings highlight AI’s potential to transform drilling operations in the Niger Delta by enabling proactive decision-making, improving operational efficiency, and enhancing safety management. However, challenges such as data integration complexities, high implementation costs, and limited technical expertise were identified as barriers to full-scale adoption. Addressing these challenges requires strategic investments in digital infrastructure, capacity building, and supportive regulatory frameworks. The study concludes that AI-driven predictive analytics can play a critical role in optimizing drilling operations while fostering safer and more sustainable practices in Nigeria’s oil and gas sector.


Full Text:

PDF

References


Almaslukh, B., Alzahrani, A., & Al-Ghamdi, M. (2021). A machine learning framework for drilling performance prediction using real-time sensor data. Journal of Petroleum Science and Engineering, 200, 108214. https://doi.org/10.1016/j.petrol.2021.108214

Cash Platform. (2024). NNPC embraces AI for risk management and operational efficiency. Retrieved from https://www.cashplatform.io/nnpc-ai-analytics

Friedman, J., Hastie, T., & Tibshirani, R. (2001). The elements of statistical learning: Data mining, inference, and prediction. Springer.

Ibrahim, A. D., & Suleiman, Y. A. (2023). Barriers to digital transformation in the Nigerian petroleum industry: The role of infrastructure and regulation. African Journal of Energy & Technology, 8(2), 65–78.

International Energy Agency (IEA). (2023). Digitalization and energy: Technological innovation in oil and gas. https://www.iea.org/reports/digitalisation-and-energy

Khosravanian, R., & Shahbazi, K. (2020). Machine learning-based approaches for drilling rate of penetration prediction: A comprehensive review. Journal of Petroleum Science and Engineering, 195, 107611. https://doi.org/10.1016/j.petrol.2020.107611

Li, X., Wang, Z., & Gao, W. (2022). Predictive analytics in drilling: An overview of models, applications, and challenges. Journal of Natural Gas Science and Engineering, 100, 104490. https://doi.org/10.1016/j.jngse.2021.104490

Mokhtari, M., & Nik, A. (2021). Real-time prediction of drilling parameters using artificial intelligence: A case study from Iranian oilfields. Energy Reports, 7, 2276–2286. https://doi.org/10.1016/j.egyr.2021.04.017

Nwankwo, C. D., Okoro, E. E., & Obasi, C. J. (2023). Digital transformation and data analytics adoption in Nigerian oil and gas operations: An empirical assessment. Nigerian Journal of Technological Development, 20(1), 42–51.

Reuters. (2024). Schlumberger's autonomous drilling system achieves breakthrough in Brazil. Retrieved from https://www.reuters.com/technology/schlumberger-ai-drilling-brazil

Science Publishing Group. (2024). The impact of AI and IoT on offshore oilfield efficiency. Journal of Oil and Gas Research, 12(1), 21–29. https://www.sciencepublishinggroup.com/journal/paperinfo?journalid=355&doi=10.11648/j.jogr.20241201.13

Tang, Y., & He, J. (2022). Machine learning applications in well control and hazard detection for offshore platforms. Journal of Petroleum Technology, 74(5), 40–46. https://doi.org/10.2118/0622-0040-JPT

Tao, Z., Wang, X., & Jin, Z. (2022). Data-driven drilling optimization using ensemble machine learning algorithms. Journal of Energy Resources Technology, 144(8), 083002. https://doi.org/10.1115/1.4053715

Vanguard. (2022). AI and IoT boosting oilfield safety in Nigeria’s offshore operations. Retrieved from https://www.vanguardngr.com/2022/08/ai-iot-oilfield-safety-nigeria

VROC. (2024). VROC and Habrams Energy partner to digitalize Nigerian oilfields. Retrieved from https://www.vroc.ai/news/nigeria-oilfields-ai-vroc-habrams

Wang, Y., Zhou, L., & Wang, H. (2021). Optimization of drilling performance using hybrid AI techniques. Journal of Petroleum Exploration and Production Technology, 11(1), 221–232. https://doi.org/10.1007/s13202-020-01042-2

World Journal of Advanced Research and Reviews. (2025). Challenges in adopting artificial intelligence in African oil sectors. 17(3), 19–25. https://wjarr.com/content/challenges-ai-african-oil-sectors

Zhang, H., Liu, Q., & Chen, Y. (2020). AI-based scheduling to reduce non-productive time in offshore drilling. Journal of Petroleum Science and Engineering, 193, 107351. https://doi.org/10.1016/j.petrol.2020.107351

Zhou, J., & Goh, M. (2020). Application of predictive analytics in upstream oil and gas supply chains: A case study of drilling operations. Energy Economics, 91, 104889. https://doi.org/10.1016/j.eneco.2020.104889

Zolfaghari, A., & Saboori, R. (2021). Artificial intelligence in oil and gas: Past, present, and future. Petroleum, 7(1), 1–12. https://doi.org/10.1016/j.petlm.2020.10.001


Refbacks

  • There are currently no refbacks.