Machine Learning Models in Ecological Data Analysis: A Comparative Review
88 42
DOI:
https://doi.org/10.5281/zenodo.20326675Keywords:
Machine learning, Ecological data analysis, Environmental monitoring, Predictive modeling, Data miningAbstract
This article provides a comparative review of the effectiveness of machine learning models used in environmental data analysis. The aim of the study is to systematize the areas of application, advantages, limitations, and effectiveness of Linear Regression, Random Forest, Support Vector Machine, Neural Networks, and Deep Learning models in working with environmental data. Since environmental data are often multidimensional, nonlinear, spatial, and temporal, traditional statistical methods do not provide sufficient results in all cases. The results of the literature analysis prove that ensemble models such as Random Forest and XGBoost show high accuracy in many environmental forecasting tasks. While Deep Learning models are effective in analyzing complex data such as satellite imagery, biodiversity, animal movements, and time series, they require large data sets and high computational resources. In addition, the explainability of models remains an important issue. Explainable AI methods such as SHAP and LIME allow us to explain the decision-making logic of complex models. Research results show that model selection should consider explainability, data quality, computational efficiency, and ecological relevance in addition to accuracy.
References
Al-Mukhtar, M. (2019). Random forest, support vector machine, and neural networks to modelling suspended sediment in Tigris River-Baghdad. *Environmental Monitoring and Assessment, 191*, 673. https://doi.org/10.1007/S10661-019-7821-5
Binetti, M. S., Massarelli, C., & Uricchio, V. F. (2024). Machine learning in geosciences: A review of complex environmental monitoring applications. *Machine Learning and Knowledge Extraction*. https://doi.org/10.3390/make6020059
Bonas, M., Datta, A., Wikle, C. K., Boone, E. L., Alamri, F. S., Hari, B. V., Indulekha, K., Simmons, S. J., Jarvis, S., Burr, W. R., Pagendam, D., Chang, W., & Castruccio, S. (2024). Assessing predictability of environmental time series with statistical and machine learning models. *Environmetrics*. https://doi.org/10.1002/env.2864
Chang, J. G. (2023). Biodiversity estimation by environment drivers using machine/deep learning for ecological management. *Ecological Informatics, 78*, 102319. https://doi.org/10.1016/j.ecoinf.2023.102319
Garcia-Quintas, A., Roy, A., Barbraud, C., Demarcq, H., Denis, D., & Bertrand, S. L. (2023). Machine and deep learning approaches to understand and predict habitat suitability for seabird breeding. *Ecology and Evolution, 13*. https://doi.org/10.1002/ece3.10549
Ghafarian, F., Wieland, R., Lüttschwager, D., & Nendel, C. (2022). Application of extreme gradient boosting and Shapley additive explanations to predict temperature regimes inside forests from standard open-field meteorological data. *Environmental Modelling & Software, 156*, 105466. https://doi.org/10.1016/j.envsoft.2022.105466
Hang, H. T., Mallick, J., AlQadhi, S., Bindajam, A. A., & Abdo, H. G. (2024). Exploring forest fire susceptibility and management strategies in western Himalaya: Integrating ensemble machine learning and explainable AI for accurate prediction and comprehensive analysis. *Environmental Technology & Innovation*. https://doi.org/10.1016/j.eti.2024.103655
Huang, C., Chen, B., Sun, C., Wang, Y., Zhang, J., Yang, H., Wu, S., Tu, P., Nguyen, M., Hong, S., & He, C. (2023). Synergistic application of multiple machine learning algorithms and hyperparameter optimization strategies for net ecosystem productivity prediction in Southeast Asia. *Remote Sensing*. https://doi.org/10.3390/rs16010017
Ibrahim, Y., Bagaye, U. Y., & Muhammad, A. I. (2023). Machine learning-based forest type mapping from multi-temporal remote sensing data: Performance and comparative analysis. *Environmental and Climate Remote Sensing*. https://doi.org/10.3390/ecrs2023-15848
Koreň, M., Jakuš, R., Zápotocký, M., Barka, I., Holuša, J., Ďuračiová, R., & Blaženec, M. (2021). Assessment of machine learning algorithms for modeling the spatial distribution of bark beetle infestation. *Forests, 12*(4), 395. https://doi.org/10.3390/F12040395
Kupidura, P., Kępa, A., & Krawczyk, P. (2024). Comparative analysis of the performance of selected machine learning algorithms depending on the size of the training sample. *Reports on Geodesy and Geoinformatics, 118*(1), 53–69. https://doi.org/10.2478/rgg-2024-0015
Liu, J., Zuo, Y., Wang, N., Yuan, F., Zhu, X., Zhang, L., Zhang, J., Sun, Y., Guo, Z., Guo, Y., Song, X., Song, C., & Xu, X. (2021). Comparative analysis of two machine learning algorithms in predicting site-level net ecosystem exchange in major biomes. *Remote Sensing, 13*(12), 2242. https://doi.org/10.3390/RS13122242
Mammides, C., Huang, G., Sree, R. P., Ieronymidou, C., & Papadopoulos, H. (2024). A novel approach for calculating prediction uncertainty when using acoustic indices and machine learning algorithms to monitor animal communities. *Research Square*. https://doi.org/10.21203/rs.3.rs-4494063/v1
Pichler, M., & Hartig, F. (2023). Machine learning and deep learning—A review for ecologists. *Methods in Ecology and Evolution, 14*(4), 994–1016. https://doi.org/10.1111/2041-210X.1406
Southworth, J., Smith, A. C., Safaei, M., Rahaman, M., Alruzuq, A., Tefera, B. B., Muir, C. S., & Herrero, H. V. (2024). Machine learning versus deep learning in land system science: A decision-making framework for effective land classification. *Frontiers in Remote Sensing*. https://doi.org/10.3389/frsen.2024.1374862
Sun, P., Holden, P. B., & Birks, H. J. B. (2024). Can machine-learning algorithms improve upon classical palaeoenvironmental reconstruction models? *Climate of the Past*. https://doi.org/10.5194/cp-20-2373-2024
Yudaputra, A., Robiansyah, I., & Rinandio, D. S. (2019). The implementation of artificial neural network and random forest in ecological research: Species distribution modelling with presence and absence dataset. *Ecological Modelling*.
Zaka, M. M., & Samat, A. (2024). Advances in remote sensing and machine learning methods for invasive plants study: A comprehensive review. *Remote Sensing, 16*(20), 3781. https://doi.org/10.3390/rs16203781
Zbinden, R., Tiel, N. V., Kellenberger, B., Hughes, L. H., & Tuia, D. (2024). On the selection and effectiveness of pseudo-absences for species distribution modeling with deep learning. *Ecological Informatics*, 102623. https://doi.org/10.1016/j.ecoinf.2024.102623
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 International Journal of Environmental Science and Green Technology, ISSN: 3080-8693
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
