Home / Current Issue / Paper 1720339
Artificial Intelligence-Based Prediction of Bioremediation of Crude Oil-Contaminated Soil
Subject area: Science,Engineering and Technology · Area of research: Machine Learning, Artificial Intelligence
DOI: https://doi.org/10.64388/IREV10I2-1720339
Abstract
Crude oil contamination of soil remains a critical environmental challenge, particularly across petroleum-producing regions of the developing world. Although biological remediation strategies have attracted considerable research interest over the past decade, the empirical monitoring of remediation processes is constrained by the labor-intensive nature of laboratory measurements and the absence of reliable predictive frameworks. This work introduces a data-driven, machine-learning framework for forecasting bioremediation efficiency (BE%) in crude oil-contaminated soil, using a dataset of 14 monitored field samples measured fortnightly across an eight-week remediation cycle. To overcome the data scarcity challenge, a kinetic spline augmentation protocol expanded the original 56-observation dataset to 2,114 temporally dense records. Six supervised regression algorithms, namely Linear, Ridge, and Lasso Regression, Support Vector Regression, Gradient Boosting Regression, and a Multilayer Perceptron Artificial Neural Network (MLP-ANN), were trained and assessed using a five-fold cross-validation scheme. Among the six architectures tested, the MLP-ANN delivered the strongest predictive accuracy, returning a coefficient of determination (R²) of 0.9803, an adjusted R² of 0.9802, a root-mean-square error (RMSE) of 2.9613%, a mean absolute error (MAE) of 2.0970%, and a mean absolute percentage error (MAPE) of 4.29%, surpassing every other model evaluated. When deployed as a binary classifier at a regulatory compliance threshold of BE% of at least 70%, the ANN achieved a classification accuracy of 96.45%. SHapley Additive exPlanations (SHAP) analysis identified oil and grease concentration as the dominant predictor of remediation outcome, contributing a mean absolute SHAP value of 16.89, followed by moisture content (1.33), microbial count (1.11), and elapsed treatment time (0.39). Residual diagnostic analyses confirmed approximate normality and homoscedasticity of model errors. These findings establish the ANN as a robust, interpretable, and practically deployable tool for real-time monitoring and decision support in soil bioremediation programmes.
Keywords
bioremediation efficiency, artificial neural network, machine learning, crude oil contamination, SHAP interpretability, soil remediation prediction.
References
[1] [1] B. A. Mekonnen, T. A. Aragaw, and M. B. Genet, “Bioremediation of petroleum hydrocarbon contaminated soil: a review on principles, degradation mechanisms, and advancements,” Frontiers in Environmental Science, vol. 12, p. 1354422, 2024, doi: 10.3389/fenvs.2024.1354422.
[2] [2] I. E. Miriogu, U. I. Uchendu, H. C. Nwanekezi, and E. M. Okoro, “Remediating crude oil polluted sites using integrated bioremediation technologies: a review,” Nigerian Journal of Environmental Sciences and Technology, vol. 8, no. 2, pp. 97–116, 2024.
[3] [3] Z. Ashkanani, R. Mohtar, S. Al-Enezi, P. K. Smith, S. Calabrese, X. Ma, and M. Abdullah, “AI-assisted systematic review on remediation of contaminated soils with PAHs and heavy metals,” Journal of Hazardous Materials, vol. 468, p. 133813, 2024, doi: 10.1016/j.jhazmat.2024.133813.
[4] [4] I. M. S. Anekwe and Y. M. Isa, “Bioremediation of crude oil-contaminated soils: a review,” Petroleum and Coal, vol. 64, no. 3, pp. 665–681, 2022.
[5] [5] O. M. Agbogidi and O. Ogbe, “Performance of cassava (Manihot esculenta Crantz) as affected by crude oil contamination of soil,” Journal of Science Research and Reviews, vol. 2, no. 2, pp. 63–69, 2025.
[6] [6] C. M. Camacho-Montealegre, E. M. Rodrigues, D. K. Morais, and M. R. Totola, “Prokaryotic community diversity during bioremediation of crude oil contaminated oilfield soil: effects of hydrocarbon concentration and salinity,” Brazilian Journal of Microbiology, vol. 52, no. 2, pp. 787–800, 2021.
[7] [7] S. Ramesh, “Utilizing bacteria for crude oil-contaminated soil bioremediation and monitoring through tomato plant growth,” Nature Environment and Pollution Technology, vol. 24, no. 2, 2025.
[8] [8] C. E. Okafor, O. P. Nwwabueze, C. P. Uzuegbu, S. C. Okeke, and R. C. Okarfor, “Bioremediation efficacy and total petroleum hydrocarbon reduction in crude oil contaminated soil using cow dung,” Journal of Applied Sciences and Environmental Management, vol. 29, no. 2, pp. 555–561, 2025.
[9] [9] S. Hosseini, R. Sharifi, and A. Habibi, “Efficient bioremediation of crude oil contaminated soil by a consortium of in-situ biosurfactant producing hydrocarbon-degraders,” Scientific Reports, vol. 15, no. 1, p. 19852, 2025, doi: 10.1038/s41598-025-05035-8.
[10] [10] A. B. Stanojevic, M. Vrvic, J. Szakova, and S. Miletic, “Evaluation of the ex-situ bioremediation of the petroleum hydrocarbons contaminated soil,” Bioremediation Journal, vol. 28, no. 4, pp. 553–563, 2024, doi: 10.1080/10889868.2023.2283580.
[11] [11] R. K. Douglas, P. P. Araka, A. Fou, and A. Hart, “Evaluation of the potential of agricultural wastes-cattle manure and poultry manure for bioremediation of crude oil-contaminated soil,” Bioremediation Journal, vol. 29, no. 1, pp. 96–103, 2025.
[12] [12] B. M. Younus, M. S. Alenazi, and M. M. Akba, “Bioremediation of petroleum-contaminated soil using earthworms: a study on hydrocarbon reduction in Iraq,” Journal of Education for Pure Science, vol. 15, no. 1, 2025.
[13] [13] O. E. Oludele, M. E. Wyse, O. K. Odeniyi, P. O. Ali, and M. Kugbogbenmowei, “Bioremediation of crude oil contaminated soil using cow dung,” International Journal of Sciences, vol. 10, no. 1, pp. 37–45, 2021.
[14] [14] J. C. Ogbu, G. Etuk-Udo, O. C. Prince, and D. Luka, “Bioremediation of crude oil contaminated agricultural soil using cow dung,” Journal of Infectious Diseases and Treatment, vol. 3, no. 2, pp. 1–4, 2025.
[15] [15] J. O. Williams, R. R. Nrior, R. Renner, and E. J. Nkpornwi, “Synergistic bioremediation of crude oil contaminated soil: role of bioreactor and pigeon droppings,” Journal of Advances in Microbiology Research, vol. 6, no. 1, pp. 23–33, 2025.
[16] [16] G. Menon and A. Mane, “Analysis of diesel spill bioremediation by bacterial isolates in batch culture using Monod and Haldane kinetic model,” Journal of Advanced Scientific Research, vol. 12, no. 03 Suppl 2, pp. 270–275, 2021.
[17] [17] K. A. Ani and C. M. Agu, “Predictive comparison and assessment of ANFIS and ANN, as efficient tools in modeling degradation of total petroleum hydrocarbon (TPH),” Cleaner Waste Systems, vol. 3, p. 100052, 2022, doi: 10.1016/j.clwas.2022.100052.
[18] [18] S. E. Uwadiae and C. D. Obasi, “Modelling of bioremediation of oil-contaminated soil using chicken droppings as biostimulant,” Journal of Applied Sciences and Environmental Management, vol. 25, no. 11, pp. 1895–1898, 2021.
[19] [19] P. O. Ehiomogue, I. I. Ahuchaogu, and U. I. Udoumoh, “Remediation of crude oil-contaminated soil using vermicompost in the Niger Delta area of Nigeria,” Arid Zone Journal of Engineering, Technology and Environment, vol. 19, no. 4, pp. 719–732, 2023.
[20] [20] D. Shadrin, M. Pukalchik, E. Kovaleva, and M. Fedorov, “Artificial intelligence models to predict acute phytotoxicity in petroleum contaminated soils,” Ecotoxicology and Environmental Safety, vol. 194, p. 110410, 2020.
[21] [21] R. Morovati, F. Abbasi, M. R. Samaei, H. Mehrazmay, and A. R. Lari, “Modelling of n-hexadecane bioremediation from soil by slurry bioreactors using artificial neural network method,” Scientific Reports, vol. 12, no. 1, p. 19662, 2022, doi: 10.1038/s41598-022-21996-6.
[22] [22] C. Di Marcantonio, L. Passatore, M. Zacchini et al., “Advancements in biopile-based sustainable soil remediation: a decade of improvements, integrating bioremediation technologies and AI-based innovative tools,” Environmental Science and Pollution Research, 2025, doi: 10.1007/s11356-025-37002-1.
[23] [23] I. K. Egbuna, H. Agboro, O. O. Nwachukwu, F. E. George, J. B. Asere, and S. A. Ogunkanmi, “Artificial intelligence for predictive analysis, efficiency improvement and reduction in carbon footprint during decommissioning and site remediation in oil and gas fields,” World Journal of Advanced Research and Reviews, vol. 26, no. 2, pp. 3394–3405, 2025.
[24] [24] M. H. Ali, M. T. Sattar, M. I. Khan, M. Naveed, M. Rafique, S. Alamri, and M. H. Siddiqui, “Enhanced growth of mungbean and remediation of petroleum hydrocarbons by Enterobacter sp. MN17 and biochar addition in diesel contaminated soil,” Applied Sciences, vol. 10, no. 23, p. 8548, 2020.
[25] [25] W. A. Ali, W. A. Farid, and A. N. K. Al-Salman, “Bioremediation of agricultural soil contaminated by a crude oil spill,” Applied Ecology and Environmental Research, vol. 18, no. 1, 2020.
[26] [26] R. Babalola, V. E. Efeovbokhan, Y. O. Atiku, U. E. Usoro, M. A. Ibeh, E. E. Alagbe, and O. G. Abatan, “Slurry-phase bioremediation of Ogoni land crude oil contaminated soil,” IOP Conference Series: Materials Science and Engineering, vol. 1107, no. 1, p. 012167, 2021.
[27] [27] P. Behdarvandan, R. Jalilzadeh Yengejeh, S. Sabzalipour, L. Roomiani, and K. Payandeh, “Bioremediation of crude oil by indigenous species isolated from oil sludge contaminated soil: a case study of Karun Gas Oil Production Company, Iran,” Journal of Advances in Environmental Health Research, vol. 8, no. 4, pp. 234–241, 2020.
[28] [28] M. Ejaz, B. Zhao, X. Wang, S. Bashir, F. U. Haider, Z. Aslam, M. I. Khan, M. Shabaan, M. Naveed, and A. Mustafa, “Isolation and characterization of oil-degrading Enterobacter sp. from naturally hydrocarbon-contaminated soils and their potential use against the bioremediation of crude oil,” Applied Sciences, vol. 11, no. 8, p. 3504, 2021.
[29] [29] W. H. Tsai, T. W. Chen, Y. H. Liu, S. M. Shen, C. S. Chen, and C. J. Tien, “A field-scale assessment of the efficacy of bioremediation of petroleum hydrocarbon-contaminated soils using two biostimulants,” International Biodeterioration and Biodegradation, vol. 196, p. 105942, 2025, doi: 10.1016/j.ibiod.2024.105942.
[30] [30] E. Atai, R. B. Jumbo, T. Cowley, I. Azuazu, F. Coulon, and M. Pawlett, “Efficacy of bioamendments in reducing the influence of salinity on the bioremediation of oil-contaminated soil,” Science of the Total Environment, vol. 892, p. 164720, 2023.
[31] [31] P. E. Edekor and S. E. Uwadiae, “Bioremediation of crude oil-contaminated soil using compost as bio-stimulant,” Journal of Applied Sciences and Environmental Management, vol. 25, no. 11, pp. 1855–1858, 2021.
[32] [32] O. K. Jimoh-Hamza and A. T. Ajao, “Bioremediation of crude oil-polluted soil with a consortium of Pseudomonas aeruginosa and soybean hull,” UNIOSUN Journal of Engineering and Environmental Sciences, vol. 6, no. 2, pp. 1–10, 2024.
[33] [33] A. T. Ajao and O. K. Jimoh-Hamza, “Exploring the effectiveness of Pseudomonas aeruginosa isolates for bioremediation of crude oil-contaminated soils using soybean hull as a biostimulant: a focus on ETPH and PAHs,” Fudma Journal of Sciences, vol. 8, no. 4, pp. 296–302, 2024.
[34] [34] T. V. Funtikova, L. I. Akhmetov, I. F. Puntus, P. A. Mikhailov, N. O. Appazov, R. A. Narmanova, A. E. Filonov, and I. P. Solyanikova, “Bioremediation of oil-contaminated soil of the Republic of Kazakhstan using a new biopreparation,” Microorganisms, vol. 11, no. 2, p. 522, 2023.
[35] [35] G. E. Agu, “Bioremediation of a crude oil contaminated soil using water hyacinth (Eichhornia crassipes),” World Journal of Advanced Research and Reviews, vol. 18, no. 3, pp. 880–888, 2023.
[36] [36] G. E. Agu and A. I. Hart, “Bioremediation of a crude oil contaminated soil using water lettuce (Pistia stratiotes),” Scientia Africana, vol. 22, no. 2, pp. 167–176, 2023.
[37] [37] C. Emeka, R. N. Okparanma, and O. W. Achinike, “Bioremediation of total polycyclic aromatic hydrocarbon in crude oil-contaminated soil using Costus afer plant,” Research Journal of Ecology and Environmental Sciences, vol. 3, no. 1, pp. 26–36, 2023.
[38] [38] F. G. Evans, U. H. Nkalo, D. Amachree, and M. O. Raimi, “From killer to solution: evaluating bioremediation strategies on microbial diversity in crude oil-contaminated soil over three to six months in Port Harcourt, Nigeria,” Advances in Environmental and Engineering Research, vol. 5, no. 4, pp. 1–26, 2024.
[39] [39] M. C. Maduwuba, “Bacteriological and physicochemical analysis of a crude oil-polluted soil undergoing laboratory-scale bioremediation,” Animal Research International, vol. 21, no. 2, pp. 5443–5452, 2024.
[40] [40] Atiku, Y. M., “Biostimulation of soil contaminated with spent motor oil using cow dung and poultry litter in land farming microcosm,” IOSR Journal of Environmental Science, Toxicology and Food Technology, vol. 12, no. 3, pp. 1–10, 2018.
How to cite this paper
@article{1720339,
author = {Gaius Iliya, Abdulsalam Surajudeen, Kabiru Ibrahim Musa},
title = {Artificial Intelligence-Based Prediction of Bioremediation of Crude Oil-Contaminated Soil},
journal = {Iconic Research And Engineering Journals},
year = {2026},
volume = {10},
number = {2},
pages = {3073-3086},
issn = {2456-8880},
url = {https://www.irejournals.com/formatedpaper/1720339.pdf},
abstract = {Crude oil contamination of soil remains a critical environmental challenge, particularly across petroleum-producing regions of the developing world. Although biological remediation strategies have attracted considerable research interest over the past decade, the empirical monitoring of remediation processes is constrained by the labor-intensive nature of laboratory measurements and the absence of reliable predictive frameworks. This work introduces a data-driven, machine-learning framework for forecasting bioremediation efficiency (BE%) in crude oil-contaminated soil, using a dataset of 14 monitored field samples measured fortnightly across an eight-week remediation cycle. To overcome the data scarcity challenge, a kinetic spline augmentation protocol expanded the original 56-observation dataset to 2,114 temporally dense records. Six supervised regression algorithms, namely Linear, Ridge, and Lasso Regression, Support Vector Regression, Gradient Boosting Regression, and a Multilayer Perceptron Artificial Neural Network (MLP-ANN), were trained and assessed using a five-fold cross-validation scheme. Among the six architectures tested, the MLP-ANN delivered the strongest predictive accuracy, returning a coefficient of determination (R²) of 0.9803, an adjusted R² of 0.9802, a root-mean-square error (RMSE) of 2.9613%, a mean absolute error (MAE) of 2.0970%, and a mean absolute percentage error (MAPE) of 4.29%, surpassing every other model evaluated. When deployed as a binary classifier at a regulatory compliance threshold of BE% of at least 70%, the ANN achieved a classification accuracy of 96.45%. SHapley Additive exPlanations (SHAP) analysis identified oil and grease concentration as the dominant predictor of remediation outcome, contributing a mean absolute SHAP value of 16.89, followed by moisture content (1.33), microbial count (1.11), and elapsed treatment time (0.39). Residual diagnostic analyses confirmed approximate normality and homoscedasticity of model errors. These findings establish the ANN as a robust, interpretable, and practically deployable tool for real-time monitoring and decision support in soil bioremediation programmes.},
keywords = {bioremediation efficiency, artificial neural network, machine learning, crude oil contamination, SHAP interpretability, soil remediation prediction.},
month = {August},
doi = {https://doi.org/10.64388/IREV10I2-1720339}
}