Classification of Environmental Materials: A Comparison of Random Forest, Decision Tree, and Support Vector Machine Algorithms
DOI:
https://doi.org/10.33633/joins.v11i2.16747Keywords:
environmental material classification, Decision Tree, Random Forest, SVM, machine learning, Earth Intelligence DatasetAbstract
Soil, air, rocks, minerals, and metals have almost similar material characteristics, so they need to be classified. The classification process is carried out by developing and testing models using Decision Tree, Random Forest, and Support Vector Machine (SVM). The types of materials classified are Air, Metal, Mineral, Organic, Rock, Sediment, Soil, and Water. The dataset is taken from the Earth Intelligence Dataset (EID) with 5,000 samples and 42 features. The dataset contains chemical composition data, physical properties, and environmental data. Data processing uses missing value imputation, Z-score normalization, and coding labels. The data is split 80:20, the evaluation process uses accuracy, recall, and F1-score, while testing uses cross-validation. The results of the study obtained 98% accuracy for Decision Tree, 97% for Random Forest, and 94.60% for SVM. Mineral and rock classes have similar geological characteristics, making the classification process more complicated. There are 5 important features in this classification process, namely density, oxygen content, magnesium content, thermal properties, and calcium content. It is known that the Decision Tree achieved the highest accuracy value, with a standard deviation of 0.0036, indicating good model stability. This research contributes to the literature by providing several combinations of algorithms that have not been widely explored in the process of identifying environmental materials based on chemical composition and physical properties.References
L. Breiman, “Random forests,” Machine Learning, vol. 45, no. 1, pp. 5–32, 2001, doi: 10.1023/A:1010933404324.
T. Hastie, R. Tibshirani, and J. Friedman, The Elements of Statistical Learning: Data Mining, Inference, and Prediction, 2nd ed. New York, NY, USA: Springer, 2009, doi: 10.1007/978-0-387-84858-7.
M. Kuhn and K. Johnson, Feature Engineering and Selection: A Practical Approach for Predictive Models. Boca Raton, FL, USA: CRC Press, 2019, doi: 10.1201/9781315108230
G. James, D. Witten, T. Hastie, and R. Tibshirani, An Introduction to Statistical Learning: With Applications in R, 2nd ed. New York, NY, USA: Springer, 2021, doi: 10.1007/978-1-0716-1418-1.
M. M. Sumon, “Earth Intelligence Dataset: A multi-domain dataset linking material composition & environmental factors.” 2026. [Online]. Available: https://www.kaggle.com/datasets/mdmahfuzsumon/earth-intelligence-dataset
A. Liaw and M. Wiener, “Classification and regression by randomForest,” R News, vol. 2, no. 3, pp. 18–22, Dec. 2002.
F. Pedregosa et al., “Scikit-learn: Machine learning in Python,” Journal of Machine Learning Research, vol. 12, pp. 2825–2830, 2011.
C. M. Bishop, Pattern Recognition and Machine Learning. New York, NY, USA: Springer, 2006.
I. H. Witten, E. Frank, and M. A. Hall, Data Mining: Practical Machine Learning Tools and Techniques, 3rd ed. San Francisco, CA, USA: Morgan Kaufmann, 2011.
A. Karim et al., “Comparison of machine learning algorithms for rice production prediction,” Jurnal RESTI, vol. 8, no. 2, pp. 1–8, 2026.
B. Bijanto, Z. Abidin, F. H. Asy’ari, and R. R. Ali, “An intelligent IoT-based hydroponic irrigation system for strawberry cultivation using extreme gradient boosting decision model,” Jurnal Teknik Informatika (JUTIF), vol. 6, no. 6, pp. 5462–5473, Dec. 2025.
S. Raschka and V. Mirjalili, Python Machine Learning: Machine Learning and Deep Learning with Python, Scikit-learn, and TensorFlow 2, 3rd ed. Birmingham, UK: Packt Publishing, 2019.
A. Géron, Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow, 2nd ed. Sebastopol, CA, USA: O’Reilly Media, 2019.
J. Han, M. Kamber, and J. Pei, Data Mining: Concepts and Techniques, 3rd ed. San Francisco, CA, USA: Morgan Kaufmann, 2011.
S. M. I. Hossain, “Stratified sampling techniques for imbalanced environmental datasets,” Environmental Data Science Journal, vol. 8, no. 1, pp. 34–47, Jun. 2024.
N. K. Dewi and A. H. Pratama, “Label encoding strategies for multi-class environmental material classification,” in Proceedings of the 2025 International Workshop on AI for Earth Sciences, Bandung, Indonesia, Jan. 2025, pp. 112–119.
K. P. Murphy, Machine Learning: A Probabilistic Perspective. Cambridge, MA, USA: MIT Press, 2012.
K. P. Murphy, Probabilistic Machine Learning: Advanced Topics, 2nd ed. Cambridge, MA, USA: MIT Press, 2023.
J. R. Quinlan, C4.5:Programs for Machine Learning. Morgan Kaufmann, 1993.
L. Devroye, L.Györfi, and G. Lugosi, A Probabilistic Theory of Pattern Recognition. New York,NY, USA: Springer, 1996.
C. Cortes and V. Vapnik, “Support-vector networks,” Machine Learning, vol. 20, no. 3, pp. 273–297, 1995, doi: 10.1007/BF00994018.
D. M. W. Powers, “Evaluation: From precision, recall and F-measure to ROC, informedness, markedness and correlation,” Journal of Machine Learning Technologies, vol. 2, no. 1, pp. 37–63, 2011.
C. E. Rasmussen and C. K. I. Williams, Gaussian Processes for Machine Learning. Cambridge, MA, USA: MIT Press, 2006, doi: 10.7551/mitpress/3206.001.0001.
S. Arlot and A. Celisse, “A survey of cross-validation procedures for model selection,” Statistics Surveys, vol. 4, pp. 40–79, 2010, doi: 10.1214/09-SS054
C. Strobl, A.-L. Boulesteix, T. Kneib, T. Augustin, and A. Zeileis, “Conditional variable importance for random forests,” BMC Bioinformatics, vol. 9, Art. no. 307, 2008, doi: 10.1186/1471-2105-9-307.
A. T. W. Min, “Visualization techniques for random forest feature importance in environmental studies,” Journal of Data Visualization and Analytics, vol. 12, no. 1, pp. 1–15, 2024.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 JOINS (Journal of Information System)

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with JOINS (Journal of Information System) agree to the following terms:
- Authors retain copyright and grant JOINS the right of first publication. The work is simultaneously licensed under a Creative Commons Attribution 4.0 International License (CC BY 4.0), which allows others to share and adapt the work, provided they give appropriate credit to the authors and the initial publication in this journal, provide a link to the license, and indicate if changes were made.
- Authors may enter into separate, additional contractual arrangements for the non-exclusive distribution of the published version of the work (e.g., posting it to an institutional repository or publishing it in a book), with an acknowledgement of its initial publication in JOINS.
- Authors warrant that the manuscript is original, has not been published elsewhere, is not under review by another journal, and does not infringe the rights of any third party. Material from other sources must be properly cited, and permission obtained where required.
- Authors may post a preprint of the manuscript, but must inform the editor at the time of submission so that the double-blind review process can be handled appropriately.


















