Classical and machine learning modeling of crude oil production in Nigeria: Identification of an eminent model for application

Obite, Chukwudi Paul; Chukwu, Angela; Bartholomew, Desmond Chekwube; Nwosu, Ugochinyere Ihuoma; Esiaba, Gladys Ezenwanyi

doi:10.1016/j.egyr.2021.06.005

Cited by 11 publications

(5 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Precisely, some performed well only on the set used to train it such as the RF and SVR, but when tried on the out-of-sample set, they performed poorly. This conditional variation in performance is also supported by literature (Obite et al, 2021). The ANN and DNN behaved similarly in both the in-sample and out-of-sample sets and are selected as the optimal model.…”

Section: Discussionsupporting

confidence: 73%

“…The time variable, first and second lags of the Brent crude oil prices were used in the model. Most applications of machine learning methods on time series use the lags as explanatory variables (Lee, Kim, Lee, Kim, & Kim, 2018;Obite, Chukwu, Bartholomew, Nwosu, & Esiaba, 2021;Tealab, Hefny, & Badr, 2017). The optimal MLMD will be compared with a classical ARIMA model that was used by Xiang and Zhuang (2013) and Mensah (2015).…”

Section: Methodsmentioning

confidence: 99%

“…The ANN is a machine learning method used for regression problems and has already been explained recently by Obite et al (2021). The ANN model is represented mathematical in Equation 9.…”

Section: Minimizementioning

confidence: 99%

“…The random forest model operates by assembling many decision trees and taking the mode for classification problem or the average for regression problem. Details of the RF method is given in Nwosu et al (2021) and Obite et al (2021). The best feature within a random subset of features is searched for and is used for splitting a node in random forest.…”

Section: Random Forestmentioning

confidence: 99%

See 3 more Smart Citations

The Optimal Machine Learning Modeling of Brent Crude Oil Price

Obite

Bartholomew

Nwosu

et al. 2021

Self Cite

View full text Add to dashboard Cite

The price of Brent crude oil is very important to the global economy as it has a huge influence and serves as one of the benchmarks in how other countries and organizations value their crude oil. Few original studies on modeling the Brent crude oil price used predominantly different classical models but the application of machine learning methods in modeling the Brent crude oil price has been grossly understudied. In this study, we identified the optimal MLMD (MLMD) amongst the Support Vector Regression (SVR), Random Forest (RF), Artificial Neural Network (ANN), and Deep Neural Network (DNN) in modeling the Brent crude oil price and also showed that the optimal MLMD is a better fit to the Brent crude oil price than the classical Autoregressive Integrated Moving Average (ARIMA) model that has been used in original studies. Daily secondary data from the U.S. Energy Information Administration were used in this study. The results showed that the ANN and DNN models behaved alike and both outperformed the SVR and RF models and are chosen as the optimal MLMDs in modeling the Brent crude oil price. The ANN was also better than the classical ARIMA model that performed very poorly. The ANN and DNN models are therefore suggested for a close monitoring of the Brent crude oil price and also for a pre-knowledge of future Brent crude oil price changes.

show abstract

Section: Discussionsupporting

confidence: 73%

Section: Methodsmentioning

confidence: 99%

“…The ANN is a machine learning method used for regression problems and has already been explained recently by Obite et al (2021). The ANN model is represented mathematical in Equation 9.…”

Section: Minimizementioning

confidence: 99%

Section: Random Forestmentioning

confidence: 99%

See 2 more Smart Citations

The Optimal Machine Learning Modeling of Brent Crude Oil Price

Obite

Bartholomew

Nwosu

et al. 2021

Self Cite

View full text Add to dashboard Cite

show abstract

“…As at the year 2021, findings from existing literatures revealed that Nigeria only produced 1.54 million barrels of crude oil per day (bpd) (Akuru and Okoro, 2011). Records from the Nigerian Upstream Petroleum Commission (NUPRC) showed that this value eventually dropped in 2022 to 1.24 million and the daily consumption of crude per barrel in Nigeria is presently at values existing in hundreds of thousands, particularly 483,000, hence this suggests the need to enhance the recovery of more volume of hydrocarbon through EOR (Obite et al, 2021). The geometric increase in Nigeria population Correspondence: Damilare Stephen Adepehin.. Department of Physics, Federal University of Health Sciences, Otukpo, Benue State, Nigeria damilare.adepehin@fuhso.edu.ng; Phone: +234-8133874616 has necessitated an improved way of producing more crude: as the crude produced per day in the country can only sustain the entire citizens for less than three days as about eighty five.…”

Section: Introductionmentioning

confidence: 99%

Estimating Geophysical Parameters Using Petrophysical Algorithm to Enhance Hydrocarbon Recovery in Lokaka Field, Niger Delta, Nigeria

Adepehin

Odudu²,

Adelayi³

et al. 2022

USci

View full text Add to dashboard Cite

Adoption of Enhanced Oil Recovery (EOR) to boost the hydrocarbon saturation (Sh) of reservoirs has caught the interests of many researchers in Geosciences. Evidence from literature shows that both primary and secondary recovery methods have failed to account for about 60% hydrocarbon (HC) that is trapped in the reservoirs and getting to discover large productive new fields has become a herculean task. This study identified the fluid nature and boundaries of reservoirs using some relevant geophysical (petrophysical) parameters and reservoir rocks physical features such as shale volume (Vsh), permeability (K), water and hydrocarbon saturation (Sw& Sh). Petrophysical data were sourced from the data bank of the Department of Geology, Obafemi Awolowo University, Ile-Ife, Nigeria. Analysis of data was done using the PETREL 2010 and OpendTect 4.6.0 versions for quality checking, delineation of identified reservoirs, fluid contacts demarcation and fluid types’ determination. The interpreted data were thereafter loaded into Microsoft Excel environment in order to adopt suitable statistical relations for the estimation of Vsh, K, Sw and Sh. Exploration of about 59.4% HC with NaOH, 64.5% HC with KOH, 69.5% HC with NH4OH and 78.5% HC with LiOH were discovered after the (EOR) flooding process. Comparison of the Vsh, K, Sw and Sh values before EOR with the values after EOR further showed that the reservoirs produced more HC with EOR. This study concluded that more hydrocarbon saturation can be achieved from reservoirs when EOR is carried out.

show abstract

RETRACTED ARTICLE: Crude oil futures price prediction by composite machine learning model

Dong,

Zheng,

2023

Ann Oper Res

View full text Add to dashboard Cite

Classical and machine learning modeling of crude oil production in Nigeria: Identification of an eminent model for application

Cited by 11 publications

References 6 publications

The Optimal Machine Learning Modeling of Brent Crude Oil Price

The Optimal Machine Learning Modeling of Brent Crude Oil Price

Estimating Geophysical Parameters Using Petrophysical Algorithm to Enhance Hydrocarbon Recovery in Lokaka Field, Niger Delta, Nigeria

RETRACTED ARTICLE: Crude oil futures price prediction by composite machine learning model

Contact Info

Product

Resources

About