+91-9561854529 editorinchief.ijama@gmail.com submitpaper@ijama.in Contact Form

Predicting the Biodegradability of Base Oils Using Data Mining Techniques

Author(s):Ahmadou B. Harouna1, Mariama D. Youssouf2, and Ibrahim S. Ali2

Affiliation: 1Department of Electrical Engineering, Abdou Moumouni University, Niamey, Niger 2Department of Computer Science, Abdou Moumouni University, Niamey, Niger 3Department of Mechanical Engineering, Abdou Moumouni University, Niamey, Niger

Page No: 51-60

Volume issue & Publishing Year: Volume 1 Issue 4-Dec 2024

Journal: International Journal of Advanced Multidisciplinary Application.(IJAMA)

ISSN NO: 3048-9350

DOI:

Download PDF

Abstract:
This study investigates the application of various data mining and machine learning techniques to predict the biodegradability of base oils. Both continuous numeric prediction models and discrete classification models were evaluated, with a focus on enhancing prediction accuracy. Results indicate that numeric prediction models outperform classification models in identifying highly biodegradable oils, providing more precise biodegradability estimates. Among the tested classification techniques, most achieved high prediction accuracy, except for Memory-Based Reasoning and Decision Trees. However, Decision Trees proved instrumental in identifying the most critical predictors of biodegradability. A simplified classification rule derived from these predictors demonstrated robust classification performance, efficiently categorizing base oils into low or high biodegradability classes. Additionally, continuous modeling techniques provided refined precision for predicting biodegradability within the high category. These findings highlight the complementary roles of classification and numeric prediction models in biodegradability assessment, offering a practical framework for environmental and industrial applications.

Keywords: base oils; biodegradability prediction; machine learning models; data mining techniques; classification models; Decision Trees; multiple linear regression; predictive analytics; Memory-Based Reasoning; environmental sustainability

Reference:

  • [1] F. Haus, O. Boissel, and J. A. Junter, “Multivariate regression modeling of mineral base oil biodegradability based on their physical properties and overall chemical composition,” Chemosphere, vol. 50, pp. 993–948, 2003.
  • [2] G. S. Kapur, M. I. S. Sastry, A. K. Jaiswal, and A. S. Sarpal, “Establishing structure-property correlations and classification of base oils using statistical techniques and artificial neural networks,” Analytica Chimica Acta, vol. 506, pp. 57–69, 2004.
  • [3] S. Zeroski, H. Blockeel, P. Kompare, B. Pfahringer, and W. Van Laer, “Experiments in predicting biodegradability,” in Proc. 9th Int. Workshop on Inductive Logic Programming, Bled, Slovenia, 1999, pp. 80–91.
  • [4] B. Cambon and J. Devillers, “New trends in structure-biodegradability relationships,” Quantitative Structure–Activity Relationships, vol. 12, pp. 49–56, 1993.
  • [5] R. S. Boethling and A. Sabljic, “Screening-level model for aerobic biodegradability based on a survey of expert knowledge,” Environmental Science & Technology, vol. 23, pp. 672–679, 1989.
  • [6] D. Amberger, S. Sekusak, and A. Sabljic, “Modelling biodegradation by an example-based learning system,” Informatica, vol. 17, pp. 157–166, 1993.
  • [7] D. Amberger, D. Horvatic, S. Sekusak, and A. Sabljic, “Application of expert judgment to derive structure–biodegradation relationships,” Environmental Science and Pollution Research, vol. 3, pp. 224–228, 1996.
  • [8] R. Baker, D. Gamberger, J. R. Mihelsic, and A. Sabljic, “Evaluation of artificial intelligence-based models for chemical biodegradability prediction,” Molecules, vol. 2, pp. 989–1004, 2004.
  • [9] A. Sabljic and W. Peijnenburg, “Recommendations on modeling lifetime and degradability of organic compounds in air, soil, and water systems,” Pure and Applied Chemistry, vol. 73, pp. 1331–1348, 2001.
  • [10] B. Basu et al., “Prediction of biodegradability of mineral base oils from chemical composition using artificial neural networks,” Tribology International, vol. 31, pp. 159–168, 1998.
  • [11] E. Rorije, H. Loonen, M. Müller, G. Klopman, and W. J. G. Peijnenburg, “Evaluation and application of models for the prediction of ready biodegradability in the MITI-I test,” Chemosphere, vol. 38, pp. 1409–1417, 1999.
  • [12] A. Achari and S. Bhattacharyya, “A comprehensive review of biodegradability prediction methods,” Environmental Modelling & Software, vol. 25, no. 3, pp. 421–432, 2019.
  • [13] T. Adams and J. Birkett, “Machine learning approaches in environmental applications,” Journal of Environmental Science and Technology, vol. 14, no. 5, pp. 67–82, 2020.
  • [14] M. Ahmad and S. Khan, “Data mining techniques for oil classification: A review,” Journal of Petroleum Science, vol. 35, no. 2, pp. 114–129, 2018.
  • [15] S. Alavi and B. Esfahani, “Biodegradability of oils: A machine learning perspective,” Computational Materials Science, vol. 57, no. 4, pp. 232–245, 2021.
  • [16] R. Anitha and K. Suresh, “Prediction of material properties using regression techniques,” Applied Computational Intelligence and Soft Computing, vol. 29, no. 6, pp. 210–222, 2017.
  • [17] D. Barua and S. Pal, “Using decision trees for oil biodegradability classification,” Journal of Biochemistry & Biotechnology, vol. 17, no. 3, pp. 45–61, 2019.
  • [18] R. Bernard and D. Joshi, “Data-driven methods for environmental sustainability,” Environmental Science and Policy, vol. 12, no. 7, pp. 54–63, 2020.
  • [19] R. Bhattacharyya and K. Agarwal, “Linear regression and its applications in biodegradability studies,” Industrial Chemistry Journal, vol. 23, no. 3, pp. 99–113, 2018.
  • [20] J. Brown and C. Davis, “Advanced machine learning models for classification tasks in the oil industry,” AI in Environmental Science, vol. 14, no. 2, pp. 131–145, 2021.
  • [21] T. Burke and A. Wilson, “Oil biodegradation in simulated environments,” International Journal of Environmental Technology, vol. 9, no. 4, pp. 89–102, 2017.
  • [22] R. Chandra and D. Kumar, “Environmental applications of predictive models,” Journal of Ecology and Environment, vol. 18, no. 3, pp. 97–110, 2020.
  • [23] L. Chen and P. Li, “Integrating data mining with biodegradability prediction,” Chemistry Today, vol. 32, no. 2, pp. 145–152, 2019.
  • [24] S. Das and R. Gupta, “Classification algorithms for sustainable oil production,” Journal of Environmental Research, vol. 21, no. 5, pp. 103–120, 2018.
  • [25] J. Davis and M. Walker, “Multiple linear regression models in biodegradability prediction,” Journal of Petroleum and Environmental Studies, vol. 19, no. 3, pp. 77–88, 2020.
  • [26] K. Dutta and A. Mukherjee, “Biodegradation modeling of hydrocarbon compounds,” Environmental Monitoring and Assessment, vol. 34, no. 6, pp. 67–81, 2017.
  • [27] B. Evans and Y. Zhang, “Applications of machine learning in environmental sustainability,” Artificial Intelligence for Environmental Solutions, vol. 10, no. 3, pp. 123–138, 2019.
  • [28] P. Fischer and T. Klein, “Using decision trees for biodegradability prediction,” Computational Environmental Science, vol. 8, no. 2, pp. 45–60, 2021.
  • [29] S. Ghosh and A. Basu, “Review of biodegradability testing methods for oils,” Journal of Environmental Science & Technology, vol. 33, no. 4, pp. 95–109, 2018.
  • [30] A. Gupta and S. Verma, “Data-driven approaches to oil classification,” Journal of Computational Chemistry, vol. 27, no. 2, pp. 71–89, 2019.
  • [31] L. Han and M. Zhou, “Predictive analytics for base oil biodegradability,” Environmental Science Advances, vol. 14, no. 1, pp. 111–125, 2020.
  • [32] P. Hernandez and M. Garcia, “Machine learning models in oil biodegradation,” Journal of Petroleum Engineering, vol. 22, no. 3, pp. 78–95, 2017.
  • [33] Z. Huang and Y. Feng, “Role of machine learning in environmental studies,” AI and Data Science in Environmental Research, vol. 11, no. 6, pp. 93–107, 2018.
  • [34] M. Islam and N. Hassan, “Applications of regression models for sustainability,” Environmental Studies Journal, vol. 25, no. 7, pp. 67–84, 2020.
  • [35] C. James and R. Stone, “Oil biodegradation prediction models,” Journal of Sustainable Chemistry, vol. 19, no. 5, pp. 122–134, 2021.
  • [36] R. Khan and S. Patel, “Biodegradability testing using machine learning,” Environmental Research Letters, vol. 15, no. 4, pp. 67–78, 2018.
  • [37] A. Kumar and S. Sharma, “Linear regression techniques for predicting environmental data,” Journal of Green Technology, vol. 13, no. 3, pp. 89–105, 2021.
  • [38] W. Li and R. Zhang, “Classification techniques in biodegradability prediction,” Journal of Computational Environmental Science, vol. 21, no. 6, pp. 72–85, 2019.
  • [39] C. Lin and H. Yang, “Enhancing prediction accuracy with machine learning,” Sustainability and AI, vol. 8, no. 4, pp. 145–160, 2017.
  • [40] X. Liu and J. Wu, “Data mining applications in oil biodegradability,” Journal of Environmental Technology, vol. 7, no. 2, pp. 53–68, 2020.
  • [41] S. Mishra and P. Mohanty, “Environmental sustainability through predictive modeling,” Ecological Research Journal, vol. 12, no. 4, pp. 94–108, 2019.
  • [42] K. Patel and D. Roy, “Biodegradation models for sustainable industry,” Journal of Sustainable Industrial Practices, vol. 17, no. 2, pp. 75–91, 2021.
  • [43] J. Robinson and G. White, “Predictive models for industrial applications,” AI in Environmental Engineering, vol. 14, no. 5, pp. 112–127, 2018.
  • [44] R. Sharma and S. Dutta, “Classification and regression models for environmental data,” Journal of Applied AI, vol. 29, no. 1, pp. 88–101, 2019.
  • [45] P. Singh and S. Mehta, “Machine learning in oil biodegradability prediction,” Journal of Environmental Solutions, vol. 16, no. 3, pp. 61–75, 2020.
  • [46] T. Wang and X. Zhang, “Advancements in predictive models for environmental research,” Sustainability Journal, vol. 18, no. 6, pp. 93–111, 2021.