THERMAL SCIENCE

International Scientific Journal

Authors of this Paper

External Links

Ihsan Tugal

,

Fatih Sevgin

ANALYSIS AND FORECASTING OF TEMPERATURE USING TIME SERIES FORECASTING METHODS A CASE STUDY OF MUS

ABSTRACT
The aim of this study is to forecast the daily average temperature of Mus province in Turkey using time series methods. The performance of three time series forecasting models is compared: LSTM, PROPHET, and ARIMA. The behavior of these models in temperature data is also investigated. It is found that these methods give accurate results according to the MAE, MSE, and RMSE error metrics. However, LSTM produces slightly better results. The temperature data used in this study was obtained from the Mus Meteorology Provincial Directorate. Accurate temperature forecasting is important for many different areas, from energy, agriculture to water resource management. This study is an important research step in temperature analysis and forecasting, and it will contribute to relevant decision-making processes.
KEYWORDS
time series, prophet, LSTM, ARIMA, temperature forecasting
PAPER SUBMITTED: 2022-09-11
PAPER REVISED: 2023-02-16
PAPER ACCEPTED: 2023-03-03
PUBLISHED ONLINE: 2023-09-17
DOI REFERENCE: https://doi.org/10.2298/TSCI2304081T
CITATION EXPORT: view in browser or download as text file
THERMAL SCIENCE YEAR 2023, VOLUME 27, ISSUE Issue 4, PAGES [3081 - 3088]
REFERENCES
  1. Sardans, J., et al., Warming And Drought Alter Soil Phosphatase Activity and Soil P Availability in a Mediterranean Shrubland, Plant Soil, 289 (2006), 1-2, pp. 227-238
  2. Smith, B. A., et al., Improving Air Temperature Prediction With Artificial Neural Networks., Int. J. Comput. Intell., 3 (2006), 3, pp. 179-186
  3. Malakouti, S. M., Utilizing Time Series Data From 1961 To 2019 Recorded Around the World and Machine Learning to Create a Global Temperature Change Prediction Model, Case Stud. Chem. Environ. Eng., 7 (2023), June, 100312
  4. Tran, T. T. K., et al., Increasing Neurons or Deepening Layers in Forecasting Maximum Temperature Time Series?, Atmosphere (Basel)., 11 (2020), 10, 1072
  5. Abhishek, K., et al., Weather Forecasting Model Using Artificial Neural Network, Procedia Technol., 4 (2012), Dec., pp. 311-318
  6. Qiu, R., et al., River Water Temperature Forecasting Using a Deep Learning Method, J. Hydrol., 595 (2021), Apr., 126016
  7. Zhengxin, L., Yue, Z., Application of Fuzzy Control Based on Time Series Prediction Algorithm in Main Steam Temperature System, Proceedings, Chinese Automation Congress (CAC), Xi'an, China, 2018, Nov., pp. 116-121
  8. Wei, K., Du, M., A Temperature Prediction Method of IGBT Based on Time Series Analysis, Proceedings, The 2nd International Conference on Computer and Automation Engineering (ICCAE), Singapore, 2010, pp. 154-157
  9. Zhang, W. Y., et al., Single-Step and Multi-Step Time Series Prediction for Urban Temperature Based on LSTM Model of TensorFlow, Proceedings, 2021 Photonics & Electromagnetics Research Symposium (PIERS), Hangzhou, China, 2021, pp. 1531-1535
  10. Hochreiter, S., Schmidhuber, J., Long Short-Term Memory, Neural Comput., 9 (1997), 8, pp. 1735-1780
  11. Gers, F. A., Learning to Forget: Continual Prediction with LSTM, Proceedings, 9th International Conference on Artificial Neural Networks: ICANN '99, Edinburg, UK, 1999, Vol. 1999, pp. 850-855
  12. Wang, X., et al., LSTM-Based Broad Learning System For Remaining Useful Life Prediction, Mathematics, 10 (2022), 12, 2066
  13. Kara, A., Global Solar Irradiance Time Series Estimation Using Long-Short-Term Memory Network, Gazi Univ. Nat. Sci. J. Part C Des. ve Technol., 7 (2019), 4, pp. 882-892
  14. Hu, B., Research on Natural Language Processing Problems Based on LSTM Algorithm, Proceedings, 3rd Asia-Pacific Conference on Image Processing, Electronics and Computers, New York, USA, 2022, pp. 259-263
  15. Tombaloğlu, B., Erdem, H., Turkish Speech Recognition Techniques and Applications of Recurrent Units (LSTM And GRU), Gazi Univ. J. Sci., 34 (2021), 4, pp. 1035-1049
  16. Shibuya, E., Hotta, K., Cell Image Segmentation by Using Feedback and Convolutional LSTM, Vis. Comput., 38 (2022), 11, pp. 3791-3801
  17. ***, PROPHET, PROPHET Time Series Model, facebook.github.io/prophet/docs/quick_start.html
  18. Taylor, S. J., Letham, B., Forecasting at Scale, Am. Stat., 72 (2018), 1, pp. 37-45
  19. Ning, Y., et al., A Comparative Machine Learning Study for Time Series Oil Production Forecasting: ARIMA, LSTM, And PROPHET, Comput. Geosci., 164 (2022), July, 105126
  20. ArunKumar, K. E., et al., Forecasting the Dynamics of Cumulative COVID-19 Cases (Confirmed, Recovered and Deaths) For Top-16 Countries Using Statistical Machine Learning Models: Auto-Regressive Integrated Moving Average (ARIMA) and Seasonal Auto-Regressive Integrated Moving Averag, Appl. Soft Comput., 103 (2021), May, 107161
  21. van der Meer, D., et al., Energy Management System with PV Power Forecast to Optimally Charge EVs At The Workplace, IEEE Trans. Ind. Informatics, 14 (2018), 1, pp. 311-320
PDF VERSION [DOWNLOAD]
Analysis and forecasting of temperature using time series forecasting methods a case study of Mus

© 2024 Society of Thermal Engineers of Serbia. Published by the Vinča Institute of Nuclear Sciences, National Institute of the Republic of Serbia, Belgrade, Serbia. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution-NonCommercial-NoDerivs 4.0 International licence