Zihan Zhao
ABSTRACT
Traditional time series models have often been used to predict temperature trends. However, they may not be suitable for handling non-linear relationships in data. To address this limitation, this paper proposes a new two-step hybrid prediction model for ocean temperature forecasting, which integrates the Autoregressive Moving Average Model (ARIMA) and Long Short Term Memory Model (LSTM).The proposed model first employs the ARIMA model to capture the linear relationship in the original data. It then uses the LSTM model to correct the non-linear component of the ARIMA model's predictions, such as residuals. This approach effectively enhances the accuracy of temperature prediction. Experimental results demonstrate that the ARIMA-LSTM model outperforms both the ARIMA and LSTM models in terms of prediction accuracy. Specifically, the ARIMA-LSTM model yields lower values of normalized mean square root error and normalized mean absolute deviation. The application of this hybrid prediction model can significantly improve ocean temperature forecasting.
- Xiu ZHANG , Xiaole LU . Study on Surface Temperature of Antarctica Based on ARIMA Time Series Model[J]. Journal of Lanzhou University of Arts and Science(Natural Sciences),2016,30(5):32∼38,64.Google Scholar
- Bin CHEN, Yue LIU , Kailang YIN Runway Temperature Prediction Based on LSTM Multivariate Time Series-Mechanism under Ice and Snow[J]. Journal of BEIJING University of Aeronautics and Astronautics: 1-16[2023-01-31]. DOI:10.13700/j.bh.1001-5965.2022.0579.Google ScholarCross Ref
- Yuanhao WANG . Forecast and Analysis of Global Temperature Based on ARIMA Model and LSTM Neural Network[J]. Scientific and Technological Innovation,2021,(35):166∼170.Google Scholar
- Hejing CHEN ,Chengli Wu ,Hanxu Li Prediction of Ash Fusion Point Based on BP-AdaBoost Algorithm[J]. Shandong Chemical Industry,2022,51(19):183∼186,192.Google Scholar
- Yi WANG, Yunwei PU. Atmospheric Temperature Prediction Based on CNN-BiLSTM-Attention Fusion Neural Network[J]. China Water Transport,2023,23(1):25∼27.Google Scholar
- Jianguo CUI ,Pengcheng LI ,Xiao CUI Aircraft Hydraulic Pump Performance Trend Prediction Method Based on ARIMA-LSTM[J]. Journal of Vibraton,Measurement&Diagnosis,2021,41(4):735∼740, 832.Google Scholar
- Amit P,Subhashis M,Will F,et al. 2-D ocean temperature and salinity images from pre-stack seismic waveform inversion methods: an example from the South China Sea[J].Geophysical Journal InternationalVolume 202, Issue 2. 2015. PP 800-810.Google Scholar
- Jiakang LI , Qijie LI,Ying ZHAO etal. Sea Surface Temperature Anomaly Forecast Research Based on CEEMD-BP Neural Network[J]. Mathematics in Practice and Theory,2017,47(24):163∼171.Google Scholar
- H. Salehinejad and S. Rahnamayan, "Customer shopping pattern prediction: A recurrent neural network approach,"in Proc. IEEE Symposium Series on Computational Intelligence,2016,pp.1-6.Google Scholar
- Md. Ashrafuzzaman, Suman Saha, and Kamruddin Nur, "Prediction of Stroke Disease Using Deep CNN Based Approach," Journal of Advances in Information Technology, Vol. 13, No. 6, pp. 604-613, December 2022.Google Scholar
- D. Meenakshi and A. R. Mohamed Shanavas, "Novel Shared Input Based LSTM for Semantic Similarity Prediction," Journal of Advances in Information Technology, Vol. 13, No. 4, pp. 387-392, August 2022.Google ScholarCross Ref
- XinWANG,Angui LI,Yang Li etal. Multivariate Load Prediction and Wind-solar Resource Characteristic Quantity Prediction of Integrated Energy System Based on ARIMA-LSTM Model[J]. Journal of Xi'an University of Architecture & Technology(Natural Science Edition),2022,54(5):762∼769.Google Scholar
- Bicong CI,Pinyi ZHANG. Financial Time Series Forecasting Based on ARIMA-LSTM[J]. Statistics & Decision,2022,38(11):145∼149.Google Scholar
Index Terms
- Research of Global Ocean Temperature Prediction Method Based on ARIMA-LSTM
Recommendations
ARIMA for Short-Term and LSTM for Long-Term in Daily Bitcoin Price Prediction
Artificial Intelligence and Soft ComputingAbstractThe goal of this paper is the insight into the forecasting of Bitcoin price using machine learning models like AutoRegressive Integrated Moving Average (ARIMA), Support vector machines (SVM), hybrid ARIMA-SVM, and Long short-term memory (LSTM). ...
Research on sales forecasting based on ARIMA and BP neural network combined model
ICIIP '16: Proceedings of the 1st International Conference on Intelligent Information ProcessingA single ARIMA model cannot meet higher standards of prediction accuracy. Moreover, it can only deal with small prediction periods in the forecasting work. For the sake of prediction accuracy, we combined an ARIMA model with BP neural network. Firstly, ...
Research on Tool Wear Prediction Based on LSTM and ARIMA
BDET 2018: Proceedings of the 2018 International Conference on Big Data Engineering and TechnologyPrecise tool wear prediction is the key to improving the productivity of the entire workpiece. Reliable tool wear prediction technology can reduce the machine downtime caused by the tool change process, and can also make the entire machining process more ...
Comments