Exploring Hybrid Models For Short-Term Local Weather Forecasting in IoT Environment
Abstract
This paper explores using and hybridizing simple prediction models to maximize the accuracy of local weather prediction while maintaining low computational effort and the need to process and acquire large volumes of data. A hybrid RF-LSTM model is proposed and evaluated in this research paper for the task of short-term local weather forecasting. The local weather stations are built within an acceptable radius of the measured area and are designed to provide a short period of forecasting - usually within one hour. The lack of local weather data might be problematic for an accurate short-term valuable prediction in sustainable applications like agriculture, transportation, energy management, and daily life. Weather forecasting is not trivial because of the non-linear nature of time series. Thus, traditional forecasting methods cannot predict the weather accurately. The advantage of the ARIMA model lies in forecasting the linear part, while the SVR model indicates the non-linear characteristic of the weather data. Both non-linear and linear approaches can represent the combined model. The hybrid ARIMA-SVR model strengthens the matched points of the ARIMA model and the SVR model in weather forecasting. The LSTM and random forest are both popular algorithms used for regression problems. LSTM is more suitable for tasks involving sequential data with long-term dependencies. Random Forest leverages the wisdom of crowds by combining multiple decision trees, providing robust predictions, and reducing overfitting. Hybrid Random forest-LSTM potentially leverages the robustness and feature importance of Random Forest along with the ability of LSTM to capture sequential dependencies. The comparison results show that the hybrid RF-LSTM model reduces the forecasting errors in metrics of MAE, R-squared, and RMSE. The proposed hybrid model can also capture the actual temperature trend in its prediction performance, which makes it even more relevant for many other possible decision-making steps in sustainable applications. Furthermore, this paper also proposes the design of a weather station based on a real-time edge IoT system. The RF-LSTM leverages the parallelized characteristics of each decision tree in the forest to accelerate the training process and faster inferences. Thus, the hybrid RF-LSTM model offers advantages in terms of faster execution speed and computational efficiency in both PC and Raspberry Pi boards. However, the RF-LSTM consumes the highest peak memory usage due to being a combination of two different models.
References
Adhikari, R., and Agrawal, R. K. An introductory study on time series modeling and forecasting. arXiv preprint arXiv:1302.6613 (2013).
Amami, R., et al. A robust voice pathology detection system based on the combined bilstm–cnn architecture. MENDEL 29, 2 (2023), 202–210.
Baboo, S. S., and Shereef, I. K. An efficient weather forecasting system using artificial neural network. International journal of environmental science and development 1, 4 (2010), 321.
Babu, C. N., and Reddy, B. E. A movingaverage filter based hybrid arima–ann model for forecasting time series data. Applied Soft Computing 23 (2014), 27–38.
Biswas, M., Dhoom, T., and Barua, S. Weather forecast prediction: an integrated approach for analyzing and measuring weather data. International Journal of Computer Applications 182, 34 (2018), 20–24.
Cadenas, E., and Rivera, W. Wind speed forecasting in the south coast of oaxaca, mexico. Renewable energy 32, 12 (2007), 2116–2128.
Chang, W. C., and Sangodiah, A. Automated semantic annotation deploying machine learning approaches: A systematic review. MENDEL 29, 2 (2023), 111–130.
Chen, L., and Lai, X. Comparison between arima and ann models used in short-term wind speed forecasting. In Asia-Pacific power and energy engineering conference (2011), pp. 1–4.
Chih, H.-C., et al. Implementation of edge computing platform in feeder terminal unit for smart applications in distribution networks with distributed renewable energies. Sustainability 14, 20 (2022), 13042.
Codeluppi, G., Davoli, L., and Ferrari, G. Forecasting air temperature on edge devices with embedded ai. Sensors 21, 12 (2021), 3973.
Corne, D., et al. Accurate localized short term weather prediction for renewables planning. In 2014 IEEE symposium on computational intelligence applications in smart grid (CIASG) (2014), IEEE, pp. 1–8.
Cuzzocrea, A., Gaber, M. M., Fadda, E., and Grasso, G. M. An innovative framework for supporting big atmospheric data analytics via clustering-based spatio-temporal analysis. Journal of Ambient Intelligence and Humanized Computing 10 (2019), 3383–3398.
Dhoot, R., Agrawal, S., and Kumar, M. S. Implementation and analysis of arima model and kalman filter for weather forecasting in spark computing environment. In Proceedings of the 3rd ICCCT (2019), IEEE, pp. 105–112.
Fieri, B., and Suhartono, D. Offensive language detection using soft voting ensemble model. MENDEL 29, 1 (2023), 1–6.
Fuadah, Y. N., Pramudito, M. A., and Lim, K. M. An optimal approach for heart sound classification using grid search in hyperparameter optimization of machine learning. Bioengineering 10, 1 (2022), 45.
Hochreiter, S., and Schmidhuber, J. Long short-term memory. Neural computation 9, 8 (1997), 1735–1780.
Hou, J., Wang, Y., Hou, B., Zhou, J., and Tian, Q. Spatial simulation and prediction of air temperature based on cnn-lstm. Applied Artificial Intelligence 37, 1 (2023), 2166235.
Kanagaraj, E., Kamarudin, L., Zakaria, A., Gunasagaran, R., and Shakaff, A. Cloud-based remote environmental monitoring system with distributed wsn weather stations. In 2015 IEEE SENSORS (2015), IEEE, pp. 1–4.
Krishnaveni, N., and Padma, A. Weather forecast prediction and analysis using sprint algorithm. Journal of Ambient Intelligence and humanized computing 12 (2021), 4901–4909.
Kung, H.-Y., Kuo, T.-H., Chen, C.-H., and Tsai, P.-Y. Accuracy analysis mechanism for agriculture data using the ensemble neural network method. Sustainability 8, 8 (2016), 735.
Liaw, A., Wiener, M., et al. Classification and regression by randomforest. R news 2, 3 (2002), 18–22.
Mahmood, M. R., et al. A novel approach for weather prediction using forecasting analysis and data mining techniques. In Proceedings of the 7th ICIECE (2019), Springer, pp. 479–489.
Manandhar, S., Lee, Y. H., and Meng, Y. S. Gps-pwv based improved long-term rainfall prediction algorithm for tropical regions. Remote Sensing 11, 22 (2019), 2643.
Mei, W., Xu, P., Liu, R., and Liu, J. Stock price prediction based on arima-svm model. In International Conference on Big Data and Artificial Intelligence (2018), p. 4.
Mei, W., Xu, P., Liu, R., and Liu, J. Stock price prediction based on arima-svm model. In International Conference on Big Data and Artificial Intelligence (2018), p. 4.
Mendoza Uribe, I. Predictive model of the enso phenomenon based on regression trees. MENDEL 29, 1 (2023), 7–14.
Mohd-Safar, N. Z., Ndzi, D., Kagalidis, I., Yang, Y., and Zakaria, A. Short-term localized weather forecasting by using different artificial neural network algorithm in tropical climate. In Proceedings of SAI Intelligent Systems Conference (2018), Springer, pp. 463–476.
Nashwan, M. S., Shahid, S., and Wang, X. Assessment of satellite-based precipitation measurement products over the hot desert climate of egypt. Remote Sensing 11, 5 (2019), 555.
Nawi, W., et al. Improved of forecasting sea surface temperature based on hybrid arima and support vector machines models. Malaysian Journal of Fundamental and Applied Sciences 17, 5 (2021), 609–620.
Nurunnahar, S., et al. A short term wind speed forecasting using svr and bp-ann: A comparative analysis. In 20th International Conference of Computer and Information Technology (ICCIT) (2017), IEEE, pp. 1–6.
Ord´o˜nez, C., et al. A hybrid arima–svm model for the study of the remaining useful life of aircraft engines. Journal of Computational and Applied Mathematics 346 (2019), 184–191.
Pai, P.-F., and Lin, C.-S. A hybrid arima and support vector machines model in stock price forecasting. Omega 33, 6 (2005), 497–505.
Prachyachuwong, K., and Vateekul, P. Stock trend prediction using deep learning approach on technical indicator and industrial specific information. Information 12, 6 (2021), 250.
Rasel, R. I., Sultana, N., and Meesad, P. An application of data mining and machine learning for weather forecasting. In Recent Advances in Information and Communication Technology 2017: Proceedings of the 13th International Conference on Computing and Information Technology (IC2IT) (2018), Springer, pp. 169–178.
Reyniers, M. Quantitative precipitation forecasts based on radar observations: Principles, algorithms and operational systems. Institut Royal M´et´eorologique de Belgique Brussel, Belgium, 2008.
Rezapour, S., et al. Forecasting rainfed agricultural production in arid and semi-arid lands using learning machine methods: A case study. Sustainability 13, 9 (2021), 4607.
Shahi, T. B., et al. Stock price forecasting with deep learning: A comparative study. Mathematics 8, 9 (2020), 1441.
Suthar, M., and Aggarwal, P. Modeling CBR value using RF and M5P techniques. MENDEL 25, 1 (2019), 73–78.
Tektas¸, M. Weather forecasting using anfis and arima models. Environmental Research, Engineering and Management 51, 1 (2010), 5–10.
Toai, T. K., et al. Arima for short-term and lstm for long-term in daily bitcoin price prediction. In International Conference on Artificial Intelligence and Soft Computing (2022), Springer, pp. 131–143.
Wang, P., Zhang, H., Qin, Z., and Zhang, G. A novel hybrid-garch model based on arima and svm for pm2. 5 concentrations forecasting. Atmospheric Pollution Research 8, 5 (2017), 850–860.
Wang, Z., and Mujib, A. M. The weather forecast using data mining research based on cloud computing. In Journal of Physics: Conference Series (2017), vol. 910, IOP Publishing, p. 012020.
Wardana, I. N. K., Gardner, J. W., and Fahmy, S. A. Optimising deep learning at the edge for accurate hourly air quality prediction. Sensors 21, 4 (2021), 1064.
Wilson, B., et al. High-resolution estimation of monthly air temperature from joint modeling of in situ measurements and gridded temperature data. Climate 10, 3 (2022), 47.
Wilson, J. W., and Brandes, E. A. Radar measurement of rainfall—a summary. Bulletin of the American Meteorological Society 60, 9 (1979), 1048–1060.
Yonekura, K., Hattori, H., and Suzuki, T. Short-term local weather forecast using dense weather station by deep neural network. In 2018 IEEE international conference on big data (big data) (2018), IEEE, pp. 1683–1690.
Zhang, K., Huo, X., and Shao, K. Temperature time series prediction model based on time series decomposition and bi-lstm network. Mathematics 11, 9 (2023), 2060.
Zhang, Y., and Hanby, V. I. Short-term prediction of weather parameters using online weather forecasts. Proceedings: Building Simulation 2007 (2007).
Copyright (c) 2023 MENDEL
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
MENDEL open access articles are normally published under a Creative Commons Attribution-NonCommercial-ShareAlike (CC BY-NC-SA 4.0) https://creativecommons.org/licenses/by-nc-sa/4.0/ . Under the CC BY-NC-SA 4.0 license permitted 3rd party reuse is only applicable for non-commercial purposes. Articles posted under the CC BY-NC-SA 4.0 license allow users to share, copy, and redistribute the material in any medium of format, and adapt, remix, transform, and build upon the material for any purpose. Reusing under the CC BY-NC-SA 4.0 license requires that appropriate attribution to the source of the material must be included along with a link to the license, with any changes made to the original material indicated.
