AI and Climate Change: Emissions Scenarios and Rainfall Patterns
Article Sidebar
Main Article Content
Abstract
Improving regional climate projections is fundamental for adaptation and resource management. This study aimed to develop a robust, AI-based model to project future precipitation trends in Villa Clara province, Cuba, up to the year 2099. Daily and monthly historical data from five meteorological stations (1960–2004) and outputs from the HadRCM regional climate model under the RCP2.6, RCP4.5, and RCP8.5 scenarios were used. The methodology consisted of time series analysis and decomposition, followed by training an LSTM neural network model, whose hyperparameters were optimized with Keras Tuner and validated using walk-forward cross-validation. The LSTM model projected precipitation with a mean absolute error (MAE) of 0.15 and a mean squared error (MSE) of 0.03. Using a KNN algorithm, the generated projections were identified as having the greatest similarity to the high-emissions scenario RCP8.5. It was concluded that the hybrid LSTM-climate model approach constitutes a robust and adaptable framework that overcomes limitations of conventional methods, providing accurate projections that point to a high-emissions climate trajectory for the region—crucial information for sector planning.
Downloads
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Those authors who have publications with this journal accept the following terms of the License Attribution-NonCommercial 4.0 International (CC BY-NC 4.0):
You are free to:
- Share — copy and redistribute the material in any medium or format
- Adapt — remix, transform, and build upon the material
The licensor cannot revoke these freedoms as long as you follow the license terms.
Under the following terms:
- Attribution — You must give appropriate credit, provide a link to the license, and indicate if changes were made. You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use.
- NonCommercial — You may not use the material for commercial purposes.
- No additional restrictions — You may not apply legal terms or technological measures that legally restrict others from doing anything the license permits.
The journal is not responsible for the opinions and concepts expressed in the works, they are the sole responsibility of the authors. The Editor, with the assistance of the Editorial Committee, reserves the right to suggest or request advisable or necessary modifications. They are accepted to publish original scientific papers, research results of interest that have not been published or sent to another journal for the same purpose.
The mention of trademarks of equipment, instruments or specific materials is for identification purposes, and there is no promotional commitment in relation to them, neither by the authors nor by the publisher.
References
Alvarez, M. M., Morlot, A. B., Artola, A. C., & Llano, A. V. (2022). Proyección de extremos climáticos futuros en Cuba bajo escenarios de geoingeniería. Revista Cubana de Meteorología, 28(2), e617.
Atwan, T. A. (2022). Time Series Analysis with Python Cookbook: Practical recipes for exploratory data analysis, data preparation, forecasting, and model evaluation. Packt Publishing Limited.
Bada Diaz, R., Gómez Martín, M. B., Matos Pupo, F., & Escalante Pérez, D. (2023). Escenarios bioclimáticos de futuro y gestión de destinos turísticos en la región de Jardines del Rey (Cuba). Revista de Geografía Norte Grande, 86, 1-23. https://doi.org/10.4067/S0718-34022023000300106
Bernstein, L. (2008). IPCC Cambio climático 2007: Informe de síntesis (1st ed.). Grupo Intergubernamental de Expertos sobre Cambio Climático.
Box, G. E. P., Jenkins, G. M., & Reinsel, G. C. (2015). Time Series Analysis: Forecasting and Control (5th ed.). Wiley.
Brownlee, J. (2019). How to use Data Scaling Improve Deep Learning Model Stability and Performance. https://www.machinelearningmastery.com/how-to-improve-neural-network-stability-and-modeling-performance-with-data-scaling/
Brownlee, J. (2020a). Hyperparameter Optimization With Random Search and Grid Search. https://www.machinelearningmastery.com/hyperparameter-optimization-with-random-search-and-grid-search/
Brownlee, J. (2020b). LOOCV for Evaluating Machine Learning Algorithms. https://www.machinelearningmastery.com/loocv-for-evaluating-machine-learning-algorithms/
Cárdenas, R. (1970). Informe Climático Anual de Cuba. Instituto de Meteorología de Cuba.
Cerqueira, V., & Roque, L. (2024). Deep Learning for Time Series Cookbook: Use PyTorch and Python recipes for forecasting, classification, and anomaly detection. Packt Publishing.
Chávez, A., & González, D. (2015). El impacto de los caudales medioambientales en la satisfacción de la demanda de agua bajo escenarios de cambio climático. Ribagua, 2(1), 3-13. https://doi.org/10.1016/j.riba.2015.04.001
Cleveland, R. B., Cleveland, W. S., McRae, J. E., & Terpenning, I. (1990). STL: A Seasonal-Trend Decomposition Procedure Based on Loess. Journal of Official Statistics, 6(1), 3-73.
Durruthy, Y. C., Díaz, C. D., Marrero, L. H. R., & Herrera, E. Z. (2022). Caracterización a futuro de las precipitaciones y la evapotranspiración de referencia, en diferentes zonas de Cuba.
Gallatin, K. (2023). Machine Learning with Python Cookbook. O’Reilly Media.
Géron, A. (2023). Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow (3rd ed.). O’Reilly Media.
Hyndman, R. J., & Athanasopoulos, G. (2021). Forecasting: Principles and Practice (3rd ed.). OTexts. https://otexts.com/fpp3/
Knutson, T. R. (2010). Tropical Cyclones and Climate Change. Nature Geoscience, 3(3), 157-163.
Ljung, G. M., & Box, G. E. P. (1978). On a Measure of Lack of Fit in Time Series Models. Biometrika, 65(2), 297-303.
Queiroz, V. (2023). Using Keras Tuner to Find the Best Hyperparameters for Your Neural Network Model. https://medium.com/@viniciusqroz/using-keras-tuner-to-find-the-best-parameters-for-your-neural-network-model-2dc02e0a1203
Suastegui Cruz, S. (2021). Estrategias para la seguridad hídrica ante los cambios de precipitación por efectos del cambio climático. RIDE. Revista Iberoamericana para la Investigación y el Desarrollo Educativo, 12(23). https://doi.org/10.23913/ride.v12i23.1039
Trenberth, K. E. (1997). The Definition of El Niño. Bulletin of the American Meteorological Society, 78(12), 2771-2777.
Virtanen, P. (2020). SciPy 1.0: Fundamental Algorithms for Scientific Computing in Python. Nature Methods, 17(3), 261-272.
Weidman, S. (2019). Deep Learning from Scratch. O’Reilly Media.