Density Well Log Prediction in X Field Niger Delta using Ensemble Learning Models and Artificial Neural Network

Patient K. Mulekya; Olugbenga A. Boboye; Moruffdeen A. Adabanija; Kasongo Numbi Numbi; Tomisin B. Baba

doi:10.52562/injoes.2024.1021

Authors

Patient K. Mulekya Petroleum Geoscience Program, Pan African University Life and Earth Sciences Institute, University of Ibadan, Ibadan, Nigeria | Department of Exploration and Production, University of Kinshasa, Kinshasa, DR Congo
Olugbenga A. Boboye Petroleum Geoscience Program, Pan African University Life and Earth Sciences Institute, University of Ibadan, Ibadan, Nigeria | Department of Geology, University of Ibadan, Ibadan, Nigeria
Moruffdeen A. Adabanija Petroleum Geoscience Program, Pan African University Life and Earth Sciences Institute, University of Ibadan, Ibadan, Nigeria | Department of Earth Sciences, Ladoke Akintola University of Technology, Ogbomoso, Nigeria
Kasongo Numbi Department of Exploration and Production, University of Kinshasa, Kinshasa, DR Congo
Tomisin B. Baba Petroleum Geoscience Program, Pan African University Life and Earth Sciences Institute, University of Ibadan, Ibadan, Nigeria

DOI:

https://doi.org/10.52562/injoes.2024.1021

Keywords:

RHOB, ensemble learning, ANN, Niger Delta

Abstract

Performing reservoir characterization in exploration with limited data can be very is challenging. Various approaches are used to estimate values away from the well location. In this study, the density log, which is important for porosity analysis, was missed in one of the five available well log datasets. To solve this problem, an artificial neural network (ANN) approach was used to synthesise a density log (RHOB) from available and measured Gamma Ray (GR) log, Sonic (DT), water saturation (SW), and related Depth of 3 wells in the field. The performance of the prediction was evaluated using the fourth well. Five models were constructed with different optimizers from machine learning with a neural network made of an input layer with 5 neurons, a hidden dense layer with 32 neurons and an output dense layer with 1 neuron. The models were constructed based on Nesterov-accelerated Adaptive Moment Estimation (NADAM), Adaptive Moment Estimation (ADAM), Stochastic Gradient Descent (SGD), and Root Mean Square Propagation (RMSP) optimizers, and an Ensemble model which combined the four optimizers. The test on actual data showed very low mean absolute errors of 0.0262, 0.0278, 0.0270, 0.0309, and 0.0248 and high coefficients of determination (R2) of 0.8832, 0.8746, 0.8986, 0.8858, and 0.9051 between the predicted and the actual data obtained for NADAM, ADAM, SGD, RMSP, and the Ensemble model, respectively, after 25 epochs. These indicated high performance of the Ensemble Learning model, suggesting that the constructed model can be used to predict the well that lacks RHOB.

Downloads

Download data is not yet available.

References

Abuh, F. A., Akpabio, J. U., & Okon, A. N. (2023). Machine Learning-Based Models for Basic Sediment & Water and Sand-Cut Prediction in Matured Niger Delta Fields. Journal of Energy Research and Reviews, 15(2), 70-93. https://doi.org/10.9734/jenrr/2023/v15i2310

Adegoke, O. S., Oyebamiji, A. S., Edet, J. J., Osterloff, P. L., & Ulu, O. K. (2017). Chapter 2 - Geology of the Niger Delta Basin (pp. 25–66). Elsevier. https://doi.org/10.1016/B978-0-12-812161-0.00002-8

Adhari, M. R., & Kardawi, M. Y. (2022). Estimation of density log and sonic log using artificial intelligence: an example from the Perth Basin, Australia. Journal of Geoscience, Engineering, Environment, and Technology, 7(4), 158-166. https://doi.org/10.25299/jgeet.2022.7.4.10050

Aggrey, G. H., & Davies, D. R. (2007, September). Tracking the state and diagnosing downhole permanent sensors in intelligent-well completions with artificial neural network. In SPE Offshore Europe Conference and Exhibition (pp. SPE-107198). SPE. https://doi.org/10.2118/107198-MS

Ahmadi, M., & Chen, Z. (2020). Machine learning-based models for predicting permeability impairment due to scale deposition. Journal of Petroleum Exploration and Production Technology, 10, 2873-2884. https://doi.org/10.1007/s13202-020-00941-1

Al-Bulushi, N., King, P. R., Blunt, M. J., & Kraaijveld, M. (2009). Development of artificial neural network models for predicting water saturation and fluid distribution. Journal of Petroleum Science and Engineering, 68(3-4), 197-208. https://doi.org/10.1016/j.petrol.2009.06.017

Chen, H. H., Huang, B., Liu, F., & Chen, W. G. (2017). Principles and applications of machine learning. Chengdu: University of Electronic Science and Technology Pres, 2-19.

Fagbemi, O. I., Olayinka, A. I., Oladunjoye, M. A., & Edigbue, P. I. (2024). Focused reservoir characterization: analysis of selected sand units using well log and 3-D seismic data in'Kukih'field, Onshore Niger Delta, Nigeria. Scientific Reports, 14(1), 13763. https://doi.org/10.1038/s41598-024-56100-7

Kim, S., Kim, K. H., Min, B., Lim, J., & Lee, K. (2020). Generation of synthetic density log data using deep learning algorithm at the Golden field in Alberta, Canada. Geofluids, 2020(1), 5387183. https://doi.org/10.1155/2020/5387183

Lim, J-S. (2005). Reservoir properties determination using fuzzy logic and neural networks from well data in offshore Korea. Journal of Petroleum Science and Engineering, 49(3-4), 182-192. https://doi.org/10.1016/j.petrol.2005.05.005

Liu, J-J. & Liu, J-C. (2021). An intelligent approach for reservoir quality evaluation in tight sandstone reservoir using gradient boosting decision tree algorithm - A case study of the Yanchang Formation, mid-eastern Ordos Basin, China. Marine and Petroleum Geology, 126, 104939. https://doi.org/10.1016/j.marpetgeo.2021.104939

Long, W., Chai, D., & Aminzadeh, F. (2016, May). Pseudo density log generation using artificial neural network. In SPE Western Regional Meeting (pp. SPE-180439). SPE. https://doi.org/10.2118/180439-MS

Maju-Oyovwikowhe, E. G., & Osayande, A. D. (2023). Hydrocarbon evaluation and distribution in Well-X and Well-Y in the Niger Delta Basin: Findings and validation through porosity comparison. Scientia Africana, 22(1), 255-278. https://doi.org/10.4314/sa.v22i1.22

Miri, R., Sampaio, J., Afshar, M., & Lourenco, A. (2007, June). Development of artificial neural networks to predict differential pipe sticking in iranian offshore oil fields. In SPE International Oil Conference and Exhibition in Mexico (pp. SPE-108500). SPE. https://doi.org/10.2118/108500-MS

Mohaghegh, S. (2000). Virtual-intelligence applications in petroleum engineering: Part 1—Artificial neural networks. Journal of Petroleum Technology, 52(09), 64-73. https://doi.org/10.2118/58046-JPT

Ogbamikhumi, A., & Omorogieva, O. M. (2021). Rock property modelling and sensitivity analysis for hydrocarbon exploration in OSSY field, Niger Delta Basin. Journal of Petroleum Exploration and Production, 11(4), 1809-1822. https://doi.org/10.1007/s13202-021-01130-4

Origbo, O. A., & Mbachu I. I. (2024) Forecasting Dead Oil Viscosity Using Machine Learning Processes for Niger Delta Region, International Journal of Current Science Research and Review, 7(1), 820-830. https://doi.org/10.47191/ijcsrr/V7-i1-81

Ozbayoglu, E. M., & Ozbayoglu, M. A. (2007). Flow pattern and frictional-pressure-loss estimation using neural networks for UBD operations. In SPE/IADC Managed Pressure Drilling and Underbalanced Operations Conference and Exhibition (pp. SPE-108340). SPE. https://doi.org/10.2118/108340-MS

Rajabi, M., Beheshtian, S., Davoodi, S., Ghorbani, H., Mohamadian, N., Radwan, A. E., & Alvar, M. A. (2021). Novel hybrid machine learning optimizer algorithms to prediction of fracture density by petrophysical data. Journal of Petroleum Exploration and Production Technology, 11(12), 4375-4397. https://doi.org/10.1007/s13202-021-01321-z

Saeedi, A., Camarda, K. V., & Liang, J. T. (2007). Using neural networks for candidate selection and well performance prediction in water-shutoff treatments using polymer gels—a field-case study. SPE Production & Operations, 22(04), 417-424. https://doi.org/10.2118/101028-PA

Saikia, P., & Baruah, R. D. (2023). Stacked ensemble model for reservoir characterisation to predict log properties from seismic signals. Computational Geosciences, 27(6), 1067-1086. https://doi.org/10.1007/s10596-023-10248-9

Saikia, P., Baruah, R. D., Singh, S. K., & Chaudhuri, P. K. (2020). Artificial Neural Networks in the domain of reservoir characterization: A review from shallow to deep models. Computers & Geosciences, 135, 104357. https://doi.org/10.1016/j.cageo.2019.104357

Saporetti, C. M., Goliatt, L., & Pereira, E. (2021). Neural network boosted with differential evolution for lithology identification based on well logs information. Earth Science Informatics, 14(1), 133-140. https://doi.org/10.1007/s12145-020-00533-x

Tamhane, D., Wong, P. M., Aminzadeh, F., & Nikravesh, M. (2000, April). Soft computing for intelligent reservoir characterization. In SPE Asia Pacific conference on integrated modelling for asset management (pp. SPE-59397). SPE. https://doi.org/10.2118/59397-MS

Tugwell, K. W., & Livinus, A. (2023). Predictive models for oil in place for oil rim reservoirs in the Niger Delta using machine learning approach. Petroleum & Petrochemical Engineering Journal, 7(3), 000361. https://doi.org/10.23880/ppej-16000361

Tuttle, M. L., Charpentier, R. R., & Brownfield, M. E. (1999). The Niger Delta Petroleum System: Niger Delta Province, Nigeria, Cameroon, and Equatorial Guinea, Africa (pp. 99-50). US Department of the Interior, US Geological Survey. https://doi.org/10.3133/ofr9950H