Exploring Hybrid Approaches for Weather Forecasting Domain: A Review
Keywords:
weather forecast; literature review; hybrid methods; performance metricsAbstract
Weather forecasting is considered one of the most important areas of forecasting as a result of the decisive role it has in different sectors of a country's economy from agriculture to aviation and from disaster management to daily planning. Taking into account the complex and dynamic nature of atmospheric conditions, forecasting through traditional methods does not complete the full panorama of an accurate and qualitative forecast and the approach has turned towards hybrid methodologies. In this paper, we performed a literature review in the domain of weather forecast, with a focus on some of its most important metrological fields, looking at the performance of hybrid approaches for each category. From the entire review process, starting with the selection of databases, defining search keywords, and exclusion criteria and up to the selection of works that would be part of the analysis, 67 papers were selected, referring to the title and abstract of the paper, and then with complete quality analysis, 14 papers were selected to be reviewed and be the main part of the analysis. A detailed review was made, where for each category the effectiveness and quality of the hybrid approaches are demonstrated and highlighting some of the most hybrid models used.
References
Alencar, D. B.; Affonso, C. M.; Oliveira, R. C. L. & Filho, J. C. R. (2018). Hybrid Approach Combining SARIMA and Neural
Networks for Multi-Step Ahead Wind Speed Forecasting in Brazil. IEEE Access, Volume 6, pp. 55986-55994.
Goswami, K.; Hazarika, J. & Patowary, A. N. (2017). Monthly Temperature Prediction Based On Arima Model: A Case Study
In Dibrugarh Station Of Assam, India. International Journal of Advanced Research in Computer Science, 8(8), pp. 292-298.
Gowri, L.; Manjula, K.; Sasireka, K. & Deepa, D. (2022). Assessment of Statistical Models for Rainfall Forecasting Using
Machine Learning Technique. Journal of Soft Computing in Civil Engineering, 6(2), pp. 51-67.
Hajirahimi, Z. & Khashei, M. (2019). Hybrid structures in time series modeling and forecasting: A review. Engineering
Applications of Artificial Intelligence, Volume i 86, pp. 83-106.
Jiao, J. (2018). A Hybrid Forecasting Method for Wind Speed. International Conference on Electronic Information Technology
and Computer Engineering, 232(2).
K, V. Et. Al. (2021). A Review on Rainfall Prediction using Machine Learning and Neural Network. International Research
Journal of Engineering and Technology (IRJET), 8(3), pp. 2763-2769.
Kumar, H.; Arora, P. & Panigrahi, B. K. (2018). Wind Forecasting:Hybrid Statistical and Deep Neural Network Approaches.
Gurgaon, India, pp. 62-67.
Latif, S. D.; Mohammed, D. O. & Jaafar, A. (2024). Developing an innovative machine learning model for rainfall prediction
in a Semi-Arid region. Journal of Hydroinformatics, Volume 14.
Lee, S.; Lee, Y.-S. & Son, Y. (2020). Forecasting Daily Temperatures with Different Time Interval Data Using Deep Neural
Networks. applied sciences, 10(5), p. 1609.
Li, G. & Yang, N., 2022. A Hybrid Sarima-LSTM Model for Air Temperature Forecasting. Advanced Theory and Simulations,
Volume 6, p. 2200502.
Nair, K. R.; Vanitha, V. & Jisma, M. (2017). Forecasting of wind speed using ANN, ARIMA and Hybrid models. Kerala, India,
s.n.
Parasyris, A. et. Al. (2022). Predicting Meteorological Variables on Local Level with SARIMA, LSTM and Hybrid Techniques.
Atmosphere, 13(6), p. 878.
Pérez-Alarcón, A.; Garcia-Cortes, D.; Fernández-Alvarez, J. C. & Martínez-González, Y. (2022). Improving Monthly Rainfall
Forecast in a Watershed by Combining Neural Networks and Autoregressive Models. Environmental Processes, 9(53).
Permata, R. P.; Muhaimin, A. & Hidayati, S. (2024). Rainfall Forecasting With An Intermittent Approach Using Hybrid
Exponential Smoothing Neural Network. Journal of Mathematics and Its Applications, 18(1), pp. 0457–0466.
Schweidtmann, A. M.; Zhang, D. & Stosch, M. V. (2014). A review and perspective on hybrid modeling methodologies. Digital
Chemical Engineering, Volume 10, p. 100136.
Sina, L. B.; Secco, C. A.; Blazevic, M. & Nazemi, K. (2023). Hybrid Forecasting Methods—A Systematic Review. Electronics,
(9), p. 2019.
Singh, P.; Singh, N. & Negi, R. (2019). Wind Power Forecasting Using Hybrid ARIMA-ANN Technique. Advances in
Intelligent Systems and Computing, Volume 904.
Slater, L. J. et. Al. (2022). Hybrid forecasting: using statistics and machine learning to integrate predictions from dynamical
models. Hydrology and Earth System Sciences, 27(9).
Shafaei, M. Et. Al. (2016). A wavelet-SARIMA-ANN hybrid model for precipitation forecasting. Journal of Water and Land
Development, Volume 28, pp. 27–36.
Wu, X. Et. Al. (2021). The Development of a Hybrid Wavelet-ARIMA-LSTM Model for Precipitation Amounts and Drought
Analysis. Atmosphere, 12(1), p. 74.
Wu, Z. (2021). The comparison of forecasting analysis based on the ARIMA-LSTM hybrid models. International Conference
on E-Commerce and E-Management, pp. 185-188.
Xhabafti, M.; Vika, B. & Sinaj, V. (2024). A comparative study of Statistical and Deep Learning Model-Base Weather Prediction
in Albania. Computer Research , Volume 12, pp. 151-160.
Y., Y. Et. Al. (2023). Global Temperature Prediction Models Based on ARIMA and LSTM. Communications in Computer and
Information Science, Volume 1910.
Zhao, J.; Nie, G. & Wen, Y. (2022. Monthly precipitation prediction in Luoyang city based on EEMD-LSTM-ARIMA mode.
Water Science & Technology, 87(1), pp. 318–335.
Downloads
Published
Issue
Section
License
Copyright (c) 2024 EIRP Proceedings
This work is licensed under a Creative Commons Attribution 4.0 International License.
You are free to:
- Share — copy and redistribute the material in any medium or format
- Adapt — remix, transform, and build upon the material
- for any purpose, even commercially.
- 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.
- No additional restrictions — You may not apply legal terms or technological measures that legally restrict others from doing anything the license permits.