Exploratory Analysis of Machine Learning Methods for Total Organic Carbon Prediction Using Well-Log Data of Kolmani Field

Longman, F.S., Balogun, H., Ojulari, R.O., Balarabe, H.J., Olatomiwa, O.J., Edeh, I.S. and Joshua, O.O. 2024. Exploratory Analysis of Machine Learning Methods for Total Organic Carbon Prediction Using Well-Log Data of Kolmani Field. IEEE 14th International Conference on Pattern Recognition Systems (ICPRS). Cavendish Street Campus, University of Westminster, Central London 15 - 18 Jul 2024 IEEE .

TitleExploratory Analysis of Machine Learning Methods for Total Organic Carbon Prediction Using Well-Log Data of Kolmani Field
AuthorsLongman, F.S., Balogun, H., Ojulari, R.O., Balarabe, H.J., Olatomiwa, O.J., Edeh, I.S. and Joshua, O.O.
TypeConference paper
Abstract

Machine Learning methods have shown significance
in automating the prediction of Total organic carbon (TOC) for determining source rock potential in oil and gas exploration. Higher TOC contents could indicate greater potential for oil and gas generation. Making accurate TOC predictions, therefore, is crucial in measuring hydrocarbon deposits for a prospective geological formation. Automating this procedure can save time and resources compared to conventional geochemical methods.
This study explores machine learning methods on Frontier-Basin well-log data for TOC Prediction. Firstly, we employ feature selection methods to ensure optimal feature usage in regression and classification tasks. Additionally, we compare several supervised Machine Learning methods including Logistic Regression,Decision Tree, K-Nearest Neighbor, Gradient Boosting, and Naive Bayes Methods to categorize the quality of TOC using its defined standard ranges on the well-log data of Kolmani River 2 and 3, respectively. Furthermore, the Random Forest method was utilized for the regression task on both data. A 5 fold nested cross-validation was utilized for classification and regression tasks. We show an exploratory analysis and the prospect of using Machine Learning methods to effectively classify TOC distribution using continuous well log data. Results show that Machine Learning methods are efficient for TOC prediction for non-geochemical approaches. The regression analysis shows an acceptable R2 value of 0.62 and 0.76 for the respective well-logs with an MSE score of 0.05 and 0.07, respectively. For the classification task, evaluation metrics including F1 score, Precision, Accuracy, and Recall were investigated for the different ML classification methods, and Naive Bayes’ was concluded to outperform others using standard metrics.

KeywordsMachine Learning
Frontier Basin
Total Organic Carbon (TOC)
Data Analysis
Oil and Gas
Source Rock Determination
Year2024
ConferenceIEEE 14th International Conference on Pattern Recognition Systems (ICPRS)
PublisherIEEE
Accepted author manuscript
License
CC BY 4.0
File Access Level
Open (open metadata and files)
Publisher's version
File Access Level
Open (open metadata and files)
Publication dates
Published26 Apr 2024
ISBN9798350375657

Related outputs

Artificial Intelligence in the Construction Industry: A Systematic Review of the Entire Construction Value Chain Lifecycle
Christian Nnaemeka Egwim,, Hafiz Alaka,, Eren Demir, Habbeb Balogun, Razak Olu-Ajayi, Ismail Sulaimon, Godoyon Wusu, Wasiu Yusuf and Adegoke A. Muideen 2024. Artificial Intelligence in the Construction Industry: A Systematic Review of the Entire Construction Value Chain Lifecycle. Energies. 17 (1) 182. https://doi.org/10.3390/en17010182

Extraction of underlying factors causing construction projects delay in Nigeria
Egwim, C.N., Alaka, H., Toriola-Coker, L.O., Balogun, H., Ajayi, S. and Oseghale, R. 2023. Extraction of underlying factors causing construction projects delay in Nigeria. Journal of Engineering, Design and Technology. 21 (5), pp. 1323-1342. https://doi.org/10.1108/jedt-04-2021-0211

Systematic review of drivers influencing building deconstructability: Towards a construct-based conceptual framework
Balogun, H., Alaka, H., Egwim, C.N. and Ajayi, S. 2023. Systematic review of drivers influencing building deconstructability: Towards a construct-based conceptual framework. Waste Management and Research. 41 (3), pp. 512-530. https://doi.org/10.1177/0734242x221124078

Ensemble of ensembles for fine particulate matter pollution prediction using big data analytics and IoT emission sensors
Christian Nnaemeka Egwim, Hafiz Alaka, Youlu Pan, Balogun, H., Saheed Ajayi, Abdul Hye and Oluwapelumi Oluwaseun Egunjobi 2023. Ensemble of ensembles for fine particulate matter pollution prediction using big data analytics and IoT emission sensors. Journal of Engineering, Design and Technology. Advanced online publication. https://doi.org/10.1108/JEDT-07-2022-0379

Building energy performance prediction: A reliability analysis and evaluation of feature selection methods
Olu-Ajayi, R., Alaka, H., Sulaimon, I., Balogun, H., Wusu, G., Yusuf, W. and Adegoke, M. 2023. Building energy performance prediction: A reliability analysis and evaluation of feature selection methods. Expert Systems with Applications. 225 120109. https://doi.org/10.1016/j.eswa.2023.120109

Applied artificial intelligence for predicting construction projects delay
Christian Nnaemeka Egwim, Hafiz Alaka, Luqman Olalekan Toriola-Coker, Habeeb Balogun and Funlade Sunmola 2021. Applied artificial intelligence for predicting construction projects delay. Machine Learning with Applications. 6 100166. https://doi.org/10.1016/j.mlwa.2021.100166

Boruta-grid-search least square support vector machine for NO2 pollution prediction using big data analytics and IoT emission sensors
Balogun, H., Alaka, H. and Egwim, C.N. 2021. Boruta-grid-search least square support vector machine for NO2 pollution prediction using big data analytics and IoT emission sensors. Applied Computing and Informatics. Advanced online publication. https://doi.org/10.1108/aci-04-2021-0092

Permalink - https://westminsterresearch.westminster.ac.uk/item/wq397/exploratory-analysis-of-machine-learning-methods-for-total-organic-carbon-prediction-using-well-log-data-of-kolmani-field


Share this

Usage statistics

24 total views
32 total downloads
These values cover views and downloads from WestminsterResearch and are for the period from September 2nd 2018, when this repository was created.