Abstract
For series problems in the meteorological field, the long-short-term memory neural network (LSTM) model is applied to the visibility forecast in the Beijing, Tianjin and Hebei region. First of all, the historical meteorological data during the months (Oct.-to-Dec. and Jan.-to-Feb.) of years 2015–2016 in the Beijing, Tianjin and Hebei region is selected as a dataset. Then, the Pearson Correlation Coefficient method is applied to select meteorological factors that have main influence on visibility to construct the training set, and adjust the network model parameters to train the neural network, and establish the input meteorological factors and the visibility of the output. Finally, European Centre for Medium-Range Weather Forecasts (ECMWF) data of the Beijing, Tianjin and Hebei region from October to December in 2017 is used to test the forecast effect of the LSTM model, and compared with the prediction results of the BP neural network. The result shows the visibility forecast based on the LSTM model is significantly better than BP neural network. The TS score in 0–1 km is 0.22, and its error is 0.34 km. The TS score in 1–10 km is 0.51, and its error is 2.18 km. The TS score above 10 km is 0.38, and its error is 6.07 km
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Wang, Z., Li, J., Wang, Z., et al.: Numerical simulation and control countermeasures of strong haze pollution in central and eastern China in January 2013. Chin. Sci. Earth Sci. 1, 3–14 (2014)
Yin, S., He, L.: Analysis of atmospheric circulation and weather in January 2015. Meteorological 4, 514–520 (2015)
Zhai, X., Long, Y., Xiao, Z.: Haze weather feature analysis and visibility forecast based on support vector machine in Wuhan. Resour. Environ. Yangtze River Basin 12, 1754–1761 (2014)
Zhang, W., Wang, Z., An, J., et al.: Using BP neural network to improve the prediction effect of real-time forecasting system for air quality of Olympic games. Climatic Environ. Res. 5, 595–601 (2010)
Li, Y., Liu, D., Jin, L., Gao, Y.: Application of BP neural network model in Chongqing drought forecast. Meteorology 12, 14–18 (2003)
Cai, Z., Han, S., Yao, Q., Zhang, M.: Study on weather visibility prediction of Tianjin based on BP neural network, pp. 2848–2854. Chinese Academy of Environmental Sciences (2016)
Liu, D., Hu, B., Yuan, Y., Zhang, H.: Application of least squares support vector machine in visibility prepackage, pp. 1386–1391. Meteorological Society of China (2009)
Han, W., Wu, Y., Ren, F.: Air pollution prediction based on full connection and LSTM neural network. Geogr. Inf. World 3, 34–40 (2018)
Jiang, J., Zhang, G., Gao, J.: Main influencing factors of atmospheric visibility in Beijing. J. Appl. Meteorol. 2, 188–199 (2018)
Fan, J., Li, Q., Zhu, Y., Hou, J., Feng, W.: Research on space-time prediction model of air pollution based on RNN. Sci. Mapp. Sci. 7, 76–83 (2017)
Acknowledgments
This work has been supported in part by the National Natural Science Foundation of China (Grant No. 61773220), the National Key Research Program of China (Grant No. 2016YFC0203301), the Nature Science Foundation of Jiangsu Province under Grant (No. BK20150523).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Dai, Y., Lu, Z., Zhang, H., Zhan, T. (2019). Research on Visibility Forecast Based on LSTM Neural Network. In: Sun, S., Fu, M., Xu, L. (eds) Signal and Information Processing, Networking and Computers. ICSINC 2018. Lecture Notes in Electrical Engineering, vol 550. Springer, Singapore. https://doi.org/10.1007/978-981-13-7123-3_64
Download citation
DOI: https://doi.org/10.1007/978-981-13-7123-3_64
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-13-7122-6
Online ISBN: 978-981-13-7123-3
eBook Packages: EngineeringEngineering (R0)