Article Details

Abstract

In view of the drastic increase in the scale and dimension of meteorological time series data, and the problems such as insufficient utilization of data information, relatively long training time, low prediction accuracy and weak generalization ability of existing models, a Bidirectional Long Short-Term Memory Network integrated with the Attention Mechanism (BiLSTM-attention) based on Graph Convolutional Neural Network (GCN) is proposed to predict meteorological data. When this model predicts the air temperature of Tongling meteorological station in Anhui province for the consecutive next week, the average RMSE error is 1.88 and the average MSE is 1.64. Compared with other models, it has the highest accuracy. At the same time, when predicting the air temperature of the four representative regions, the error differences among the various regions are not significant, which proves that this model has good generalization performance and high prediction accuracy.

Keywords

Bidirectional Long Short-Term Memory Neural Network; Graph Convolutional Neural Network; Attention Mechanism; air temperature prediction

References

1. [1] Sun Haoxiang The impact of adjacent daytime temperature changes and apparent temperature on the number of epilepsy outpatient visits in Hefei City [D]. Hefei: Anhui Medical University, 2023
2. [2] Zhang Kuan Research on the Impact of Temperature Changes on Cardiovascular Diseases and Prevention Management [D]. Lanzhou: Lanzhou University of Technology, 2023
3. [3] Fang Wen, Lin Ziqiang, Meng Ruilin, etc A study on the combined effects of summer temperature and humidity exposure on non accidental mortality in the population [J]. Journal of Environmental Health, 2024, 14 (9): 736-744
4. [4] Li Yong, Tong Shaoyu Research on the Impact and Adaptation of Climate Change on Agriculture in China [J]. Anhui Agricultural Science Bulletin, 2023, 29 (5): 151-157+175
5. [5] Liu Yong, He Meiling The correlation mechanism between temperature change and energy consumption [J]. Western China, 2023 (3): 80-91
6. [6] Liu Xueli A review of research on the impact of special meteorological conditions on transportation safety [J]. Smart Cities, 2017, 3 (7): 29-31
7. [7] Liu Xin, Zhao Ning, Guo Jinyun, etc Monthly precipitation prediction on the Qinghai Tibet Plateau based on LSTM neural network [J]. Journal of Earth Information Science, 2020, 22 (8): 1617-1629
8. [8] Zhao Mingzhu, Wang Dan, Fang Jie, etc Temperature prediction of subway stations based on LSTM neural network [J]. Journal of Beijing Jiaotong University, 2020, 44 (4): 94-101
9. [9] Ma Donglin, Ma Sizhou, Wang Weijie Multi site temperature prediction model based on graph convolutional network and gated recurrent unit [J]. Computer Applications, 2022, 42 (1): 287-293
10. [10] Wang Yanjuan Temperature spatiotemporal prediction based on CNN-LSTM and meteorological element correlation [D]. Yinchuan: Ningxia University, 2023
11. [11] SAHA A，SINGH K N，RAY M，et al. Fuzzy Rule-Based Weighted Space–Time Autoregressive Moving Average Models for Temperature Forecasting [J].Theoretical and Applied Climatology，2022，150（3）：1321-1335.
12. [12] VICTOR S O，ALEXANDRE P R C，JOHN S，et al. Spatiotemporal Analysis of Bidimensional Wind Speed Forecasting：Development and Thorough Assessment of LSTM and Ensemble Graph Neural Networks on the Dutch Database [J].Energy，2023，278：1-16.

Funding

Science Research Project Funding from Hebei Provincial Department of Education (ZD2021043)

About the authors

Wang Yujie (2000-), female, Han ethnicity, from Hengshui, Hebei Province, assistant lecturer, master's student, research direction: mathematics; Wang Qianying (1984-), female, Han ethnicity, from Baoding, Hebei Province, associate professor, doctoral student, research direction: deep learning.