Dự báo chuỗi thời gian dựa trên học máy: Trường hợp nghiên cứu về dự báo nhiệt độ ở một số trạm Việt Nam
217 lượt xemDOI:
https://doi.org/10.54939/1859-1043.j.mst.85.2023.152-162Từ khóa:
Học máy; Dự báo nhiệt độ; Học sâu; Chuỗi thời gian; SARIMA; XGBoost.Tóm tắt
Trong những năm gần đây, sử dụng các mô hình học máy để dự báo ngày càng được quan tâm. Trong nghiên cứu này, chúng tôi sẽ sử dụng dữ liệu nhiệt độ ở các trạm của Việt Nam để dự báo nhiệt độ. Nghiên cứu có sử dụng một số mô hình dự báo. Đầu tiên, phương pháp dự báo theo chuỗi thời gian truyền thống như ARIMA theo mùa (SARIMA). Sau đó, các phương pháp tiếp cận phức tạp hơn như XGBoost, Encoder-Decoder và Prophet được sử dụng. Hiệu suất của các mô hình được so sánh với nhau sử dụng một số độ đo đánh giá độ chính xác (ví dụ: sai số toàn phương trung bình (RMSE) và sai số trung bình tuyệt đối (MAE)). Các kết quả đã khẳng định tính ưu việt của phương pháp học sâu so với các phương pháp khác.
Tài liệu tham khảo
[1]. IFRC, "World Disaster Report 2020," International Federation of Red Cross and Red Crescent Societies, (2020).
[2]. N. L. Duc et. al., "Research and quantitative ranifall forecasting from HRM and GSM model products," Vietnam Journal of Hydrometerorology, vol. 592, pp. 17-27, (2010).
[3]. G. P. Z. a. D. M. Kline, "Quarterly Time-Series Forecasting With Neural Networks," IEEE Transactions on Neural Networks, vol. 18, pp. 1800-1814, (2007). DOI: https://doi.org/10.1109/TNN.2007.896859
[4]. S. M. P. Chopra, “Supply Chain Management”. Strategy, Planning & Operation, German: Gabler, (2007).
[5]. K. H. M. J. B. A. Ahmad Hasan Nury, "Comparative study of wavelet-ARIMA and wavelet-ANN models for temperature time series data in northeastern Bangladesh," Journal of King Saud University - Science, vol. 29, no. 1, pp. 47-61, (2017). DOI: https://doi.org/10.1016/j.jksus.2015.12.002
[6]. C. N. B. a. B. E. Reddy, "Predictive data mining on Average Global Temperature using variants of ARIMA models," in IEEE-International Conference On Advances In Engineering, Science And Management (ICAESM -2012), (2012).
[7]. X. L. W. Q. Y. Z. W. Z. C. T. H. Yang, "A network traffic forecasting method based on SA optimized ARIMA–BP neural network," Computer Networks, vol. 193, (2021). DOI: https://doi.org/10.1016/j.comnet.2021.108102
[8]. S. R. H. P. S. S. P. C. Tandon, "How can we predict the impact of the social media messages on the value of cryptocurrency? Insights from big data analytics," International Journal of Information Management Data Insights, vol. 1, no. 2, (2021). DOI: https://doi.org/10.1016/j.jjimei.2021.100035
[9]. R. L. Carey Goh, "Modeling and forecasting tourism demand for arrivals with stochastic nonstationary seasonality and intervention,," Tourism Management, vol. 22, no. 5, pp. 499-510, (2002). DOI: https://doi.org/10.1016/S0261-5177(02)00009-2
[10]. L. A. H. Billy M. Williams, "Modeling and Forecasting Vehicular Traffic Flow as a Seasonal ARIMA Process: Theoretical Basis and Empirical Results," Journal of Transportation Engineering, vol. 129, no. 6, pp. 664-672, (2003). DOI: https://doi.org/10.1061/(ASCE)0733-947X(2003)129:6(664)
[11]. C. Hamzaçebi, "Improving artificial neural networks’ performance in seasonal time series forecasting," Information Sciences, vol. 178, no. 23, pp. 4550-4559, (2008). DOI: https://doi.org/10.1016/j.ins.2008.07.024
[12]. T. Miyano and F. Girosi, "Forecasting Global Temperature Variations by Neural Networks," Cambridge Artificial Intelligence Laboratory: Cambridge, MA,, USA, (1994). DOI: https://doi.org/10.21236/ADA290081
[13]. H. Hippert, C. Pedreira and R. Souza, "Combining neural networks and ARIMA models for hourly temperature forecast," in The IEEE-INNS-ENNS International Joint Conference on Neural Networks, Como, Italy, (2000). DOI: https://doi.org/10.1109/IJCNN.2000.860807
[14]. I. Tasadduq, S. Rehman and Bubshait, "Application of neural networks for the prediction of hourly mean surface temperatures in Saudi Arabia," Renew. Energy, vol. 11, pp. 71-77, (2001).
[15]. Maqsood, M. Khan and A. Abraham, "An ensemble of neural networks for weather forecasting," Neural Computing Application, vol. 13, pp. 112-122, (2004). DOI: https://doi.org/10.1007/s00521-004-0413-4
[16]. B. Smith, R. McClendon and G. Hoogenboom, "Improving air temperature prediction with artificial neural networks," Internaiontal Journal Computing Intelligent , vol. 3, pp. 179-186, (2006).
[17]. K. Abhishek, M. Singh, S. Ghosh and A. Anand, "Weather Forecasting Model using Artificial Neural Network," Procedia Technology, pp. 311-318, (2012). DOI: https://doi.org/10.1016/j.protcy.2012.05.047
[18]. H. Mori and D. Kanaoka, "Application of support vector regression to temperature forecasting for short-term load forecasting," in Proceedings of the 2007 International Joint Conference on Neural Networks, Orlando, Fl, USA, (2017). DOI: https://doi.org/10.1109/IJCNN.2007.4371109
[19]. E. Ortiz-García, S. Salcedo-Sanz, C. Casanova-Mateo, A. Paniagua-Tineo and J. Portilla-Figueras, "Accurate local very short-term temperature prediction based on synoptic situation Support Vector Regression banks," Atmos. Res., (2012). DOI: https://doi.org/10.1016/j.atmosres.2011.10.013
[20]. R. Chevalier, G. Hoogenboom, R. McClendon and J. Paz, "Support vector regression with reduced training sets for air temperature prediction: A comparison with artificial neural networks," Neural Computing Application, vol. 20, pp. 151-159, (2010). DOI: https://doi.org/10.1007/s00521-010-0363-y
[21]. A. Paniagua-Tineo, S. Salcedo-Sanz, C. Casanova-Mateo, E. Ortiz-García, M. Cony and E. Hernández-Martín, "Prediction of daily maximum temperature using a support vector regression algorithm," Renew. Energy, vol. 36, pp. 3054-3060, (2011). DOI: https://doi.org/10.1016/j.renene.2011.03.030
[22]. I. Abubakar, H. Chiroma, A. Zeki and M. Uddin, "Utilising key climate element variability for the prediction of future climate change using a support vector machine model," Int. J. Glob. Warm., vol. 9, pp. 129-151, (2016). DOI: https://doi.org/10.1504/IJGW.2016.074952
[23]. Z. Z. H. Wai Yan Nyein Naing, "Forecasting of monthly temperature variations using random forests," Asian Research Publishing Network Journal of Engineering and Applied Sciences, vol. 10, no. 21, pp. 10109-10112, (2015).
[24]. P. Hewage, M. Trovati, E. Pereira and Behera, "A. Deep learning-based effective fine-grained weather forecasting," Pattern Analysis, pp. 1-24, (2020). DOI: https://doi.org/10.1007/s10044-020-00898-1
[25]. I. Roesch and T. Günther, "Visualization of Neural Network Predictions for Weather Forecasting," Comput. Graph. Forum, pp. 209-220, (2018). DOI: https://doi.org/10.1111/cgf.13453
[26]. S. J. a. L. B. Taylor, "Forecasting at Scale," The American Statistician, vol. 72, no. 1, pp. 37-45, (2018). DOI: https://doi.org/10.1080/00031305.2017.1380080
[27]. K.-P. L. C.-S. L. P.-T. C. Ping-Feng Pai, "Time series forecasting by a seasonal support vector regression model," Expert Systems with Applications, vol. 37, no. 6, pp. 4261-4265, (2010). DOI: https://doi.org/10.1016/j.eswa.2009.11.076
[28]. T. H. M. Jr, A. M. Pellegrini and R. H. Perlis, "Assessment of Time-Series Machine Learning Methods for Forecasting Hospital Discharge Volume," JAMA Network Open, (2018).
[29]. A. S. K. S. S. a. U. H. Sandhiya, "Forecasting Website Traffic Using Prophet Time Series Model," International Research Journal of Multidisciplinary Technovation, vol. 1, no. 2, pp. 1-8, (2019).
[30]. W. D. B. U. N. N. H. Christophorus Beneditto Aditya Satrio, "Time series analysis and forecasting of coronavirus disease in Indonesia using ARIMA model and PROPHET," Procedia Computer Science, vol. 179, pp. 524-532, (2021). DOI: https://doi.org/10.1016/j.procs.2021.01.036
[31]. G. A. Rob J Hyndman, “Forecasting: principles and practice”, OTexts, (2018).
[32]. Y. B. J. Q. J. W. P. Y. S. W. Mingju Gong, "Gradient boosting machine for predicting return temperature of district heating system: A case study for residential buildings in Tianjin," Journal of Building Engineering, vol. 27, (2020). DOI: https://doi.org/10.1016/j.jobe.2019.100950
