Predicting aquatic ecosystem health using machine learning algorithms
Main Article Content
Abstract
Water is one of the most essential natural resources on Earth. Predicting water levels and taking appropriate measures to prevent water shortages are crucial tasks for hydrological researchers in order to avoid future water crises. Several hydrological studies have demonstrated the potential of Artificial Neural Networks (ANNs) as an effective technology for forecasting groundwater levels. However, extended features and imperfect datasets often lead to inconsistent and unpredictable prediction results. Therefore, strict groundwater management strategies are necessary to prevent water-related crises.
Recent research has shown that Artificial Neural Networks are highly effective in handling very large datasets, solving complex computational problems, and performing training at discrete levels of representation. Deep learning simulations require powerful and high-speed hardware for efficient processing. A single-core CPU may not generate reliable predictions when working with flawed or inaccurate input datasets, whereas multi-core CPUs can perform predictions more efficiently. In addition, a Graphics Processing Unit (GPU), which consists of thousands of processing cores, significantly improves computational performance and accelerates deep learning tasks related to water level prediction and hydrological analysis.
Article Details
Section
How to Cite
References
Arrighi, C. and Castelli, F., 2023. Prediction of ecological status of surface water bodies with supervised machine learning classifiers. *Science of the Total Environment*, 857, p.159655. [https://doi.org/10.1016/j.scitotenv.2022.159655](https://doi.org/10.1016/j.scitotenv.2022.159655)
Deng, T., Chau, K.W. and Duan, H.F., 2021. Machine learning based marine water quality prediction for coastal hydro-environment management. *Journal of Environmental Management*, 284, p.112051. [https://doi.org/10.1016/j.jenvman.2021.112051](https://doi.org/10.1016/j.jenvman.2021.112051)
Gambín, Á.F., Angelats, E., González, J.S., Miozzo, M. and Dini, P., 2021. Sustainable marine ecosystems: Deep learning for water quality assessment and forecasting. *IEEE Access*, 9, pp.121344-121365. [https://doi.org/10.1109/ACCESS.2021.3109216](https://doi.org/10.1109/ACCESS.2021.3109216)
Jaiswal, H. and Pradhan, S., 2023. The economic significance of ecosystem services in developing urban areas for aquatic ecosystems. *Aquatic Ecosystems and Environmental Frontiers*, 1(1), pp.1-5.
Kwon, Y.S., Kang, H. and Pyo, J., 2024. Estimation of aquatic ecosystem health using deep neural network with nonlinear data mapping. *Ecological Informatics*, 81, p.102588. [https://doi.org/10.1016/j.ecoinf.2024.102588](https://doi.org/10.1016/j.ecoinf.2024.102588)
Lee, S., Kim, J., Lee, G., Hong, J., Bae, J.H. and Lim, K.J., 2021. Prediction of aquatic ecosystem health indices through machine learning models using the WGAN-based data augmentation method. *Sustainability*, 13(18), p.10435. [https://doi.org/10.3390/su131810435](https://doi.org/10.3390/su131810435)
Uddin, M.G., Nash, S., Diganta, M.T.M., Rahman, A. and Olbert, A.I., 2022. Robust machine learning algorithms for predicting coastal water quality index. *Journal of Environmental Management*, 321, p.115923. [https://doi.org/10.1016/j.jenvman.2022.115923](https://doi.org/10.1016/j.jenvman.2022.115923)
Uddin, M.G., Nash, S., Rahman, A., Dabrowski, T. and Olbert, A.I., 2024. Data-driven modelling for assessing trophic status in marine ecosystems using machine learning approaches. *Environmental Research*, 242, p.117755. [https://doi.org/10.1016/j.envres.2023.117755](https://doi.org/10.1016/j.envres.2023.117755)
Zhu, M., Wang, J., Yang, X., Zhang, Y., Zhang, L., Ren, H., Wu, B. and Ye, L., 2022. A review of the application of machine learning in water quality evaluation. *Eco-Environment & Health*, 1(2), pp.107-116. [https://doi.org/10.1016/j.eehl.2022.06.001](https://doi.org/10.1016/j.eehl.2022.06.001)