Time series modeling of long-memory data for predictive analytics in oil and gas exploration
Journal of Statistical Sciences and Computational Intelligence · 10.06.2026 · 2 (2) · 548-558
DOI: 10.64497/jssci.112 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Statistical Sciences and Computational Intelligence, online erschienen am 10.06.2026. Verfasst von Kennedy Irikefe Ekerikevwe und 1 weiteren Autor:innen. Die Arbeit nennt 23 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
This study develops a robust statistical methodology, the Transformed-ARIMAX (Log-ARIMAX) model, to enhance the prediction accuracy of oil spillage data in Nigeria. Traditional Autoregressive Integrated Moving Average with Covariates (ARIMAX) models often struggle with environmental datasets characterized by heavy-tailed distributions, high kurtosis, and significant outliers. By applying a logarithmic transformation, this research stabilizes variance and reduces skewness, allowing the model to better accommodate long-memory observational series. Utilizing historical datasets comprising 64 observations of oil spills (monthly and yearly) from four major companies from January 2005 to December 2020, the study employs the Augmented Dickey-Fuller (ADF) test for stationarity and compares model performance using the Akaike Information Criterion (AIC) and Diebold-Mariano tests. Results indicate that the Log-ARIMAX model significantly outperforms traditional ARIMAX frameworks, providing a more stable and robust forecasting tool for regional planning and national development.
Zitieren
APA
Ekerikevwe, K. I., & Olatayo, T. O. (2026). Time series modeling of long-memory data for predictive analytics in oil and gas exploration. Journal of Statistical Sciences and Computational Intelligence, 2(2), 548-558. https://doi.org/10.64497/jssci.112
Vancouver
Ekerikevwe KI, Olatayo TO. Time series modeling of long-memory data for predictive analytics in oil and gas exploration. Journal of Statistical Sciences and Computational Intelligence. 2026;2(2):548-558. doi:10.64497/jssci.112
BibTeX
@article{Ekerikevwe2026,
author = {Ekerikevwe, Kennedy Irikefe and Olatayo, Timothy Olabisi},
title = {Time series modeling of long-memory data for predictive analytics in oil and gas exploration},
journal = {Journal of Statistical Sciences and Computational Intelligence},
year = {2026},
volume = {2},
number = {2},
pages = {548--558},
doi = {10.64497/jssci.112}
}
EUVIMED