CGPR: A Study on a Spatiotemporal Temperature Prediction Model for Henan Based on Improved PredRNN with ChebConv

Zhongcai Li

doi:10.54097/dxsdrc50

Authors

Zhongcai Li

DOI:

https://doi.org/10.54097/dxsdrc50

Keywords:

Temperature prediction; PredRNN; Chebyshev graph convolution; ConvLSTM.

Abstract

As a major agricultural province, accurate temperature prediction in Henan is of great importance. This paper proposes a new model called ChebConv PredRNN (CGPR), which combines a graph neural network with a spatiotemporal recurrent neural network. First, the original gridded meteorological data is modeled as a graph structure to capture complex spatial correlations. Second, the PredRNN architecture is improved by replacing the traditional spatial convolutional layers with Chebyshev graph convolution (ChebConv). Experiments based on historical data from 2015 to 2018 demonstrate that the model significantly outperforms baseline models such as LSTM, ConvLSTM, and the original PredRNN in prediction accuracy, proving the effectiveness of graph structure modeling in spatiotemporal temperature sequence prediction.

References

[1]Menon, S. P., Bharadwaj, R., Shetty, P., Sanu, P. & Nagendra, S. Prediction of temperature using linear regression. in 2017 International Conference on Electrical, Electronics, Communication, Computer, and Optimization Techniques (ICEECCOT) 1–6 (2017). doi:10.1109/ICEECCOT.2017.8284588.

[2]Gupta, I., Mittal, H., Rikhari, D. & Singh, A. K. MLRM: A Multiple Linear Regression based Model for Average Temperature Prediction of A Day. Preprint at https://doi.org/10.48550/arXiv.2203.05835 (2022).

[3]Pang, Z. & Wang, Z. Temperature trend analysis and extreme high temperature prediction based on weighted Markov Model in Lanzhou. Nat Hazards 108, 891–906 (2021).

[4]Johnson, S. D., Battisti, D. S. & Sarachik, E. S. Empirically Derived Markov Models and Prediction of Tropical Pacific Sea Surface Temperature Anomalies. Journal of Climate 13, 3–17 (2000).

[5]Stajkowski, S., Kumar, D., Samui, P., Bonakdari, H. & Gharabaghi, B. Genetic-Algorithm-Optimized Sequential Model for Water Temperature Prediction. Sustainability 12, (2020).

[6]Ren, J., Wang, Z., Pang, Y. & Yuan, Y. Genetic algorithm-assisted an improved AdaBoost double-layer for oil temperature prediction of TBM. Advanced Engineering Informatics 52, 101563 (2022).

[7]Venkadesh, S., Hoogenboom, G., Potter, W. & McClendon, R. A genetic algorithm to refine input data selection for air temperature prediction using artificial neural networks. Applied Soft Computing 13, 2253–2260 (2013).

[8]Quan, Q., Hao, Z., Xifeng, H. & Jingchun, L. Research on water temperature prediction based on improved support vector regression. Neural Comput & Applic 34, 8501–8510 (2022).

[9]Paniagua-Tineo, A. et al. Prediction of daily maximum temperature using a support vector regression algorithm. Renewable Energy 36, 3054–3060 (2011).

[10]Ni, Y. Q., Hua, X. G., Fan, K. Q. & Ko, J. M. Correlating modal properties with temperature using long-term monitoring data and support vector machine technique. Engineering Structures 27, 1762–1773 (2005).

[11]Liu, J. et al. TD-LSTM: Temporal Dependence-Based LSTM Networks for Marine Temperature Prediction. Sensors 18, (2018).

[12]Xiao, C. et al. Short and mid-term sea surface temperature prediction using time-series satellite data and LSTM-AdaBoost combination approach. Remote Sensing of Environment 233, 111358 (2019).

[13]Yang, Y. et al. A CFCC-LSTM Model for Sea Surface Temperature Prediction. IEEE Geoscience and Remote Sensing Letters 15, 207–211 (2018).

[14]Mashaly, A. F. & Alazba, A. A. MLP and MLR models for instantaneous thermal efficiency prediction of solar still under hyper-arid environment. Computers and Electronics in Agriculture 122, 146–155 (2016).

[15]Ghritlahre, H. K. & Prasad, R. K. Exergetic performance prediction of solar air heater using MLP, GRNN and RBF models of artificial neural network technique. Journal of Environmental Management 223, 566–575 (2018).

[16]Chen, Q. et al. TemproNet: A transformer-based deep learning model for seawater temperature prediction. Ocean Engineering 293, 116651 (2024).

[17]Schuster, M. & Paliwal, K. K. Bidirectional recurrent neural networks. IEEE Transactions on Signal Processing 45, 2673–2681 (1997).

[18]Beck, M. et al. xLSTM: Extended Long Short-Term Memory. Preprint at https://doi.org/10.48550/arXiv.2405.04517 (2024).

[19]Shi, X. et al. Convolutional LSTM Network: a machine learning approach for precipitation nowcasting. in Proceedings of the 29th International Conference on Neural Information Processing Systems - Volume 1 vol. 1 802–810 (MIT Press, Cambridge, MA, USA, 2015).

[20]Zhao, L. et al. T-GCN: A Temporal Graph Convolutional Network for Traffic Prediction. IEEE Transactions on Intelligent Transportation Systems 21, 3848–3858 (2020).

[21]Higashiyama, K., Fujimoto, Y. & Hayashi, Y. Feature Extraction of NWP Data for Wind Power Forecasting Using 3D-Convolutional Neural Networks. Energy Procedia 155, 350–358 (2018).

[22]Chang, Z. et al. MAU: A Motion-Aware Unit for Video Prediction and Beyond. in Advances in Neural Information Processing Systems vol. 34 26950–26962 (Curran Associates, Inc., 2021).

[23]Wang, Y. et al. PredRNN: A Recurrent Neural Network for Spatiotemporal Predictive Learning. IEEE Transactions on Pattern Analysis and Machine Intelligence 45, 2208–2225 (2023).