ABSTRACT
Accurate prediction of temperature is an important part of fine weather forecast services (such as heating energy consumption in winter, Winter Olympic Games, etc.). Therefore, the accurate prediction of hourly temperature is very significant in the management of human health and the decision-making of government. In this study, a long short term (LSTM) memory model was proposed and used to predict the next hour's temperature in mega-cites in North China. It was fully considered for the historic temperature and meteorological condition. As a result, the predictor secured a fast and accurate prediction performance by fully reflecting the long-term historic process of input time series data through LSTM. The meteorological data from Beijing, Tianjin, Shijiazhuang and Taiyuan which represents the mega-cites of North China during October 1 to December 31 in 2016-2018 were used to verify the validity of the proposed method. In conclusion, the proposed method was proved to have a good prediction performance in cooling and turning warming processes, making up for the poor performance of turning weather prediction in the previous research. It confirmed that the forward supplement LSTM model has the best prediction ability for hourly temperature prediction in Beijing among mega-cites in North China. The results also indicate great potential of the machine learning method in improving local weather forecast and the potential to serve the 2022 Winter Olympics.
- FangMei Ma, L.Y Jin, K.F Zhang. An Hourly Air Temperature Equation, J.Huazhong Univ. of Sci &Tech, 1995, 23 (8): 46--49. (in Chinese)Google Scholar
- Ruhua Lu, C.Y Xu, L. Zhang, et al., Calculation method for initial value of kalman filter and its application. QUARTERLY JOURNAL OF APPLIED METEOROLOGY, 1997, 8 (1): 34--42.(in Chinese)Google Scholar
- Deshan Zhang, Y.W Dou, G. Bai et al., Hourly Temperature Forecast Based on Diurnal Temperature Range in Beijing [J]. Meteorological Monthly, 1999, 25(5): 54--57. (in Chinese)Google Scholar
- Yajie Qi, C. Qian, Z.W Yan; An alternative multi-model ensemble mean approach for near-term projection, INTERNATIONAL JOURNAL OF CLIMATOLOGY, 2017, 31(1): 109--122.Google ScholarCross Ref
- Braakmann-Folgmann A, Roscher R, Wenzel S, et al. Sea level anomaly prediction using recurrent neural networks [J]. Proceedings of the 2017 conference on Big Data from Space, 2017Google Scholar
- Qing X, Niu Y. Hourly day-ahead solar irradiance prediction using weather forecasts by LSTM [J]. Energy, 2018, 148: 461--468Google ScholarCross Ref
- Junxiang Fan, Q.Li, Y.J Zhu, et al. A spatio-temporal prediction framework for air pollution based on deep RNN. Science of Surveying and Mapping, 2017, 42(7): 76--83, 120. (in Chinese)Google Scholar
- Xiao Shi, JL Pei, X.H Jiang et al. The Hourly Surface Temperature Forecasting Techniques Basedon Circulation Types, Desert and Oasis Meteorology, 2013, 7(3): 17--20 (in Chinese)Google Scholar
- Men Xiaolei, Jiao Ruili, Wang Ding, et al. 2019. A temperature correction method for multi-model ensemble forecast in North China based on machine learning [J]. Climatic and Environmental Research (in Chinese), 24 (1): 116--124, doi:10.3878/j.issn.1006-9585.2018.18049.Google Scholar
- U. Pak, J. Ma, U. Ryu, et al., Deep learning-based PM2.5 prediction considering the spatiotemporal correlations: A case study of Beijing, China, Science of the Total Environment, https://doi.org/10.1016/j.scitotenv.2019.07.367Google Scholar
Index Terms
- Deep Learning-based Hourly Temperature Prediction: A Case Study of Mega-cites in North China
Recommendations
Prediction of daily average seawater temperature using data-driven and deep learning algorithms
AbstractLarge amounts of cooling water are required for the cooling process in coal-fired or nuclear power plants. Because the primary use of water in a power plant is to condense steam and remove waste heat as part of a Rankine cycle, seawater ...
A Hybrid Deep Learning Approach for Forecasting Air Temperature
Artificial Neural Networks in Pattern RecognitionAbstractForecasting the weather is a great scientific challenge. Physics-based, numerical weather prediction (NWP) models have been developed for decades by large research teams and the accuracy of forecasts has been steadily increased. Yet, recently, ...
Deep Learning and Sentiment Analysis-Based Cryptocurrency Price Prediction
Advances in Visual InformaticsAbstractThe rapid growth of Cryptocurrency dramatically influences the social and economic climate that has developed the trends for investors to seek opportunities for generating income from cryptocurrency investment trading. Cryptocurrency is volatile ...
Comments