Predictive Modeling of Coastal Upwelling Features using Artificial Intelligence Approach
DOI:
https://doi.org/10.51459/jostir.2026.2.1.0304Abstract
The Northwest African coastal upwelling is a one of the complex systems that global and regional climate models struggle to capture its features. In this study, the artificial intelligence (AI) statistical models including machine learning and advanced deep learning architectures were used to predict the time series of the interannual variability of coastal upwelling indices, such as Ekman transport and sea surface temperature (SST) based. The results show good performances with high score of the coefficient of determination (R2>70%) and minimum Root Mean Square Error (<0.09) of machine learning and deep learning models, such as Random Forest, Gradient Boosting, Long Short-Term Memory (LSTM) and Convolutional Neural Network (CNN), in simulating monthly Ekman transport and SST-based along the Senegal-Mauritania and Gulf of Guinea coasts. The best performance was obtained with LSTM-CNN hybrid architecture, indicating the capacity of AI technology to capture finesse scale processes such as coastal upwelling features at the interannual scale. However, the spatial representation of coastal upwelling using the AI techniques remains a future challenge.
References
Bonino, G., Galimberti, G., Masina, S., McAdam, R., and Clementi, E. (2024). Machine learning methods to predict sea surface temperature and marine heatwave occurrence: a case study of the Mediterranean Sea. Ocean Science, 20(2), 417-432.
Djakouré, S., Koné, V., Aman, A., Bourlès, B., and Arnault, S. (2017). Coastal upwelling along the northern coast of the Gulf of Guinea. Continental Shelf Research, 141, 1–10. https://doi.org/10.1016/j.csr.2017.03.001
Gupta, S. and Malmgren, B., (2009) Comparison of the accuracy of sst estimates by artificial neural networks (ann) and other quantitative methods using radiolarian data from the antarctic and pacific oceans, Journal of Earth Science India, vol. 2, pp. 52–75.
Hastie, T., Tibshirani, R., and Friedman, J., (2009). The Elements of Statistical Learning: Data Mining, Inference, and Prediction. New York, NY, USA: Springer Series in Statistics.
Kriebel, S. K. T., Brauer, W., & Eifler, W. (1998). Coastal upwelling prediction with a mixture of neural networks. IEEE Transactions on Geoscience and Remote Sensing, 36(5), 1508–1518. https://doi:10.1109/36.718854
Krizhevsky, A., Sutskever, I., and Hinton, G., (2012) Imagenet classification with deep convolutional neural networks,” in Advances in neural information processing systems.
Ling, F., Luo, J. J., Li, Y., Tang, T., Bai, L., Ouyang, W., and Yamagata, T. (2022). Multi-task machine learning improves multi-seasonal prediction of the Indian Ocean Dipole. Nature Communications, 13(1), 7681.
Patil, K. and Deo, M., (2017) Prediction of daily sea surface temperature using efficient neural networks,” Ocean Dynamics, vol. 67, pp. 357–368. https://doi.org/10.1007/s10236-017-1032-9
Reichstein, M., Camps-Valls, G., Stevens, B., Jung, M., Denzler, J., Carvalhais, N., and Prabhat, (2019). Deep learning and process understanding for data-driven earth system science,” Nature, vol. 566, no. 7743, pp.195–204.
Ronneberger, O., Fischer, P., and Brox, T., (2015) U-net: Convolutional networks for biomedical image segmentation, International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 234–241.
Sherstinsky, A., (2020) Fundamentals of recurrent neural network (rnn) and long short-term memory (lstm) network, Physica D: Nonlinear Phenomena, vol. 404, p. 132306.
Shi, X., Chen, Z., Wang, H., Yeung, D., Wong, W., and Woo, W., (2015) Convolutional lstm network: A machine learning approach for precipitation nowcasting, in Advances in Neural Information Processing Systems 28. Curran Associates, Inc.,
Snoussi, M., Tamim, A., El Fellah, S., and Koutti, L. (2024). Spatiotemporal Prediction of Monthly Coastal Upwelling Scenario in SST Fields Using Deep Learning Based Models. IEEE Geoscience and Remote Sensing Letters.
Tang, B., Hsieh, W., Monahan, A., and Tangang, F., (2000) Skill comparisons between neural networks and canonical correlation analysis in predicting the equatorial pacific sea surface temperatures, Journal of Climate, vol. 13, pp. 287–293.
Tangang, F., Hsieh, W., and Tang, B., (1997) Forecasting the equatorial pacific sea surface temperatures by neural network models, Climatic Dynamics, vol. 13, pp. 135–147. https://doi.org/10.1007/s003820050156
Tripathi, K., Das, M., and Sahai, A., (2006). Predictability of sea surface temperature anomalies in the indian ocean using artificial neural networks, Indian Journal of Marine Sciences, vol. 35, no. 3, pp. 210–220
Wu, A., Hsieh, W., and Tang, B., (2006) “Neural network forecasts of the tropical pacific sea surface temperatures, Neural Networks, vol. 19, pp. 145–154. https://doi.org/10.1016/j.neunet.2006.01.004
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Journal of Science, Technology and Innovation Research
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.