Temperature Time Series Prediction Model Based on Time Series Decomposition and Bi-LSTM Network

被引:7
作者
Zhang, Kun [1 ]
Huo, Xing [1 ]
Shao, Kun [2 ]
机构
[1] Hefei Univ Technol, Sch Math, Hefei 230009, Peoples R China
[2] Hefei Univ Technol, Sch Software, Hefei 230009, Peoples R China
基金
中国国家自然科学基金;
关键词
time-series decomposition; deep learning; neural network; time-series prediction;
D O I
10.3390/math11092060
中图分类号
O1 [数学];
学科分类号
0701 ; 070101 ;
摘要
Utilizing a temperature time-series prediction model to achieve good results can help us to accurately sense the changes occurring in temperature levels in advance, which is important for human life. However, the random fluctuations occurring in a temperature time series can reduce the accuracy of the prediction model. Decomposing the time-series data prior to performing a prediction can effectively reduce the influence of random fluctuations in the data and consequently improve the prediction accuracy results. In the present study, we propose a temperature time-series prediction model that combines the seasonal-trend decomposition procedure based on the loess (STL) decomposition method, the jumps upon spectrum and trend (JUST) algorithm, and the bidirectional long short-term memory (Bi-LSTM) network. This model can achieve daily average temperature predictions for cities located in China. Firstly, we decompose the time series into trend, seasonal, and residual components using the JUST and STL algorithms. Then, the components determined by the two methods are combined. Secondly, the three components and original data are fed into the two-layer Bi-LSTM model for training purposes. Finally, the prediction results achieved for both the components and original data are merged by learnable weights and output as the final result. The experimental results show that the average root mean square and average absolute errors of our proposed model on the dataset are 0.2187 and 0.1737, respectively, which are less than the values 4.3997 and 3.3349 attained for the Bi-LSTM model, 2.5343 and 1.9265 for the EMD-LSTM model, and 0.9336 and 0.7066 for the STL-LSTM model.
引用
收藏
页数:16
相关论文
共 34 条
  • [1] Spatiotemporal trend and abrupt change analysis of temperature in Iran
    Ahmadi, Farshad
    Tahroudi, Mohammad Nazeri
    Mirabbasi, Rasoul
    Khalili, Keivan
    Jhajharia, Deepak
    [J]. METEOROLOGICAL APPLICATIONS, 2018, 25 (02) : 314 - 321
  • [2] Remote Sensing-Based Assessment of Fire Danger Conditions Over Boreal Forest
    Akther, M. Shammi
    Hassan, Quazi K.
    [J]. IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING, 2011, 4 (04) : 992 - 999
  • [3] Behera RK, 2020, J UNIVERS COMPUT SCI, V26, P1128
  • [4] Global non-linear effect of temperature on economic production
    Burke, Marshall
    Hsiang, Solomon M.
    Miguel, Edward
    [J]. NATURE, 2015, 527 (7577) : 235 - +
  • [5] Forecasting the Short-Term Metro Ridership With Seasonal and Trend Decomposition Using Loess and LSTM Neural Networks
    Chen, Dewang
    Zhang, Jianhua
    Jiang, Shixiong
    [J]. IEEE ACCESS, 2020, 8 : 91181 - 91187
  • [6] Forecasting Seasonal Tourism Demand Using a Multiseries Structural Time Series Method
    Chen, Jason Li
    Li, Gang
    Wu, Doris Chenguang
    Shen, Shujie
    [J]. JOURNAL OF TRAVEL RESEARCH, 2019, 58 (01) : 92 - 103
  • [7] Empirical mode decomposition based long short-term memory neural network forecasting model for the short-term metro passenger flow
    Chen, Quanchao
    Wen, Di
    Li, Xuqiang
    Chen, Dingjun
    Lv, Hongxia
    Zhang, Jie
    Gao, Peng
    [J]. PLOS ONE, 2019, 14 (09):
  • [8] Chen X., 2011, P 2011 INT C MULT TE
  • [9] Time series forecasting of COVID-19 transmission in Canada using LSTM networks
    Chimmula, Vinay Kumar Reddy
    Zhang, Lei
    [J]. CHAOS SOLITONS & FRACTALS, 2020, 135
  • [10] Contreras J., 2002, IEEE Power Eng. Rev., V22, P57, DOI [10.1109/MPER.2002.4312577, DOI 10.1109/MPER.2002.4312577]