banner
Home > Open Journal Systems

Principle of Machine Learning and Its Potential Application in Climate Prediction

Shengping He, Huijun Wang, Hua Li, Jiazhen Zhao

Abstract


After two “cold winters of artificial intelligence”, machine learning has once again entered the public’s vision in recent ten years, and has a momentum of rapid development. It has achieved great success in practical applications such as image recognition and speech recognition system. It is one of the main tasks and objectives of machine learning to summarize key information and main features from known data sets, so as to accurately identify and predict new data. From this perspective, the idea of integrating machine learning into climate prediction is feasible. Firstly, taking the adjustment of linear fitting parameters (i.e. slope and intercept) as an example, this paper introduces the process of machine learning optimizing parameters through gradient descent algorithm and finally obtaining linear fitting function. Secondly, this paper introduces the construction idea of neural network and how to apply neural network to fit nonlinear function. Finally, the framework principle of convolutional neural network for deep learning is described, and the convolutional neural network is applied to the return test of monthly temperature in winter in East Asia, and compared with the return results of climate dynamic model. This paper will help to understand the basic principle of machine learning and provide some reference ideas for the application of machine learning to climate prediction.

Keywords


Machine Learning; Neural Network; Convolutional Neural Network; Climate Prediction; Winter Temperature in East Asia

Full Text:

PDF

References


1. Bauer P, Thorpe A, Brunet G. The quiet revolution of numerical weather prediction. Nature 2015; 525(7567) : 47–55. doi: 10. 1038/nature14956.

2. Behringer D, Xue Y. Evaluation of the global ocean data assimilation system at NCEP: The Pacific Ocean. Proc. Eighth Symp. on Integrated Observing and Assimilation Systems for Atmosphere, Oceans, and Land Surface, Seattle, WA, AMS. 2014 Jan 1. Washington. Washington: Washington State Con-vention and Trade Center. 2014.

3. Copernicus Climate Change Service (C3S). ERA5: Fifth generation of ECMWF atmospheric reanal-yses of the global climate. 2017. Available from: https://cds.climate.copernicus.eu/cdsapp#!/home.

4. Dougherty J, Kohavi R, Sahami M. Supervised and unsupervised discretization of continuous features. Machine Learning Proceedings Amsterdam: Else-vier. 1995. p. 194–202. doi: 10. 1016/b978-1-55860-377-6. 50032-3.

5. Goodfellow I, Bengio Y, Courville A. Deep learning. Cambridge: MIT Press. 2016.

6. Ham YG, Kim JH, Luo JJ. Deep learning for multi-year ENSO forecasts. Nature 2019; 573(7775) : 568–572. doi: 10. 1038/s41586-019-1559-7.

7. Hantson S, Arneth A, Harrison SP, et al. The status and challenge of global fire odeling. Biogeosciences 2016; 13(11): 3359–3375. doi: 10. 5194 /bg-13-3359-2016.

8. Hasselmann K. Linear and nonlinear signatures. Nature 1999; 398(6730): 755–756. doi: 10. 1038/19635.

9. He S, Wang H, Xu X, et al. Impact of Arctic warm-ing and the super El Nino in winter 2015/2016 on the East Asian climate anomaly (in Chinese). Transactions of Atmospheric Sciences 2016; 39(6): 735–743. doi: 10. 13878/j.cnki.dqkxxb.20161008002.

10. He S, Xu X, Furevik T, et al. Eurasian cooling linked to the vertical distribution of arctic warming. Geo-physical Research Letters 2020; 47(10). doi: 10. 1029/2020gl087212.

11. Huntingford C, Jeffers ES, Bonsall MB, et al. Ma-chine learning and artificial intelligence to aid cli-mate change research and preparedness. Environ-mental Research Letters 2019; 14(12): 124007. doi: 10. 1088/1748-9326/ab4e55.

12. Kuang Z, Song Z, Dong C. Global sea surface tem-perature over 21st century using a biases correction model based on machine learning (in Chinese). Climate Chang Research Letters 2020; 9(4): 270–284.

13. Lagerquist R, McGovern A, Gagne DJ. Deep learn-ing for spatially explicit prediction of synoptic-scale fronts. Weather Forecast 2019; 34(4): 1137–1160. doi: 10. 1175/waf-d-18-0183. 1.

14. Liu Y J, Racah E, Prabhat, et al. Application of deep convolutional neural networks for detecting extreme weather in climate datasets. 2016. Availa-ble from: https://arxiv.org/abs/1605. 01156.

15. McCarthy J, Minsky ML, Rochester N, et al. A pro-posal for the Dartmouth summer research project on artificial intelligence. 1956. Available from: http://www.formal.stanford.edu/jmc/history/dartmouth/dartmouth.html.

16. Men X, Jiao R, Wang D, et al. A temperature correc-tion method for multi-model ensemble forecast in North China based on machine learning (in Chi-nese). Climatic and Environmental Research 2019; 24(1): 116–124. doi: 10. 3878/j.issn.1006-9585. 2018. 18049.

17. Pörtner HO, Roberts DC, Masson-Delmotte V. IPCC special report on the ocean and cryosphere in a changing climate. 2019. In press.

18. Ruder S. An overview of gradient descent optimiza-tion algorithms. 2016. Available from: https://arxiv.org/abs/1609. 04747.

19. Samuel AL. Some studies in machine learning using the game of checkers. IBM Journal of Research and Development 1959; 3(3): 210–229. doi: 10. 1147/rd.33. 0210.

20. Specht DF. A general regression neural network. IEEE Transactions on Neural Networks and Learn-ing Systems 1991; 2(6): 568–576. doi: 10. 1109/72. 97934.

21. Stockhause M, Lautenschlager M. CMIP6 data citation of evolving data. Data Science Journal 2017; 16. doi: 10. 5334/dsj-2017-030.

22. Toms BA, Barnes EA, Ebert-Uphoff I. Physically interpretable neural networks for the geosciences: Applications to earth system variability. Journal of Advances in Modeling Earth Systems 2020; 12(9). doi: 10. 1029/2019ms002002.

23. Weyn JA, Durran DR, Caruana R. Can machines learn to predict weather? Using deep learning to predict gridded 500-hPa geopotential height from historical weather data.Journal of Advances in Modeling Earth Systems 2019; 11(8): 2680–2693. doi: 10. 1029/2019ms001705.




DOI: https://doi.org/10.32629/jai.v4i1.483

Refbacks

  • There are currently no refbacks.


Copyright (c) 2021 Shengping He, Huijun Wang, Hua Li, Jiazhen Zhao

License URL: https://creativecommons.org/licenses/by-nc/4.0