A station-data-based model residual machine learning method for fine-grained meteorological grid prediction

Chuansai ZHOU, Haochen LI, Chen YU, Jiangjiang XIA, Pingwen ZHANG

doi:10.1007/s10483-022-2822-9

Applied Mathematics and Mechanics >

2022 , Vol. 43 >Issue 2: 155 - 166

DOI: https://doi.org/10.1007/s10483-022-2822-9

Articles

A station-data-based model residual machine learning method for fine-grained meteorological grid prediction

Expand

1. School of Mathematical Sciences, Peking University, Beijing 100871, China;
2. School of Science, Beijing University of Posts and Telecommunications, Beijing 100876, China;
3. Institute of Atmospheric Physics, Chinese Academy of Sciences, Beijing 100029, China

Received date: 2021-10-20

Revised date: 2021-12-16

Online published: 2022-01-25

Supported by

Project supported by the National Natural Science Foundation of China (Nos. 12101072 and 11421101), the National Key Research and Development Program of China (No. 2018YFF0300104), the Beijing Municipal Science and Technology Project (No. Z201100005820002), and the Open Research Fund of Shenzhen Research Institute of Big Data (No. 2019ORF01001)

Fold

Abstract

Fine-grained weather forecasting data, i.e., the grid data with high-resolution, have attracted increasing attention in recent years, especially for some specific applications such as the Winter Olympic Games. Although European Centre for Medium-Range Weather Forecasts (ECMWF) provides grid prediction up to 240 hours, the coarse data are unable to meet high requirements of these major events. In this paper, we propose a method, called model residual machine learning (MRML), to generate grid prediction with high-resolution based on high-precision stations forecasting. MRML applies model output machine learning (MOML) for stations forecasting. Subsequently, MRML utilizes these forecasts to improve the quality of the grid data by fitting a machine learning (ML) model to the residuals. We demonstrate that MRML achieves high capability at diverse meteorological elements, specifically, temperature, relative humidity, and wind speed. In addition, MRML could be easily extended to other post-processing methods by invoking different techniques. In our experiments, MRML outperforms the traditional downscaling methods such as piecewise linear interpolation (PLI) on the testing data.

Key words： machine learning (ML); post-processing; fine-grained weather forecasting; model residual machine learning (MRML)

Cite this article

Chuansai ZHOU, Haochen LI, Chen YU, Jiangjiang XIA, Pingwen ZHANG . A station-data-based model residual machine learning method for fine-grained meteorological grid prediction[J]. Applied Mathematics and Mechanics, 2022 , 43(2) : 155 -166 . DOI: 10.1007/s10483-022-2822-9

References

[1] NIES, H., BEHNER, F., REUTER, S., MECKEL, S., and LOFFELD, O. Radar imaging and tracking using geostationary communication satellite systems - a project description. Proceedings of EUSAR 2016: 11th European Conference on Synthetic Aperture Radar, IEEE, Piscataway, 1-4 (2016)
[2] LUOJUS, K. P., PULLIAINEN, J. T., METSAMAKI, S. J., and HALLIKAINEN, M. T. Snow-covered area estimation using satellite radar wide-swath images. IEEE Transactions on Geoscience and Remote Sensing, 45(4), 978-989 (2007)
[3] SALTIKOFF, E., FRIEDRICH, K., SODERHOLM, J., LENGFELD, K., NELSON, B., BECKER, A., HOLLMANN, R., URBAN, B., HEISTERMANN, M., and TASSONE, C. An overview of using weather radar for climatological studies: successes, challenges, and potential. Bulletin of the American Meteorological Society, 100(9), 1739-1752 (2021)
[4] JOSH, M. and TAHMEED, A. Evaluating meteorological data from weather stations, and from satellites and global models for a multi-site epidemiological study. Environmental Research, 165, 91-109 (2018)
[5] BEONG, I. Y. A smoothening method for the piecewise linear interpolation. Journal of Applied Mathematics, 2015, 376362 (2015)
[6] FOTHERINGHAM, S. and O'KELLY, M. Spatial Interaction Models: Formulations and Applications, 5th ed., Kluwer, Dordrecht, 62-84 (1989)
[7] LOPEZ, P., IMMERZEEL, W., RODRIGUEZ, S., STERK, G., and SCHELLEKENS, J. Spatial downscaling of satellite-based precipitation and its impact on discharge simulations in the magdalena river basin in Colombia. Frontiers in Earth Science, 6, 68 (2018)
[8] PATRICK, M. B. and PETER, C. K. Multivariate interpolation to incorporate thematic surface data using inverse distance weighting (IDW). Computers & Geosciences, 22(7), 795-799 (1996)
[9] NAM, D. H., KEIKO, U., and AKIRA, M. Downscaling global weather forecast outputs using ANN for flood prediction. Journal of Applied Mathematics, 2011, 246286 (2011)
[10] SCHOOF, J. T. and PRYOR, S. C. Downscaling temperature and precipitation: a comparison of regression-based methods and artificial neural networks. International Journal of Climatology, 21(7), 773-790 (2001)
[11] JACOB, D., CHANG, M. W., KENTON, L., and KRISTINA, T. BERT: pre-training of deep bidirectional transformers for language understanding. arXiv: 1810.04805 (2018) http://arxiv.org/abs/1810.04805
[12] MIKOLOV, T., SUTSKEVER, I., CHEN, K., CORRADO, G., and DEAN, J. Distributed representations of words and phrases and their compositionality. Proceedings of the 26th International Conference on Neural Information Processing Systems, Curran Associates Inc., New York, 3111-3119 (2013)
[13] MIKOLOV, T., CHEN, K., CORRADO, G., and DEAN, J. Efficient estimation of word representations in vector space. International Conference on Learning Representations, Scottsdale, Arizona, 2-4 (2013)
[14] YU, C., LI, H. C., XIA, J. J., WEN, H. Q. Z., and ZHANG, P. W. A data-driven random subfeature ensemble learning algorithm for weather forecasting. Communications in Computational Physics, 28(4), 1305-1320 (2020)
[15] SHI, X., CHEN, Z., WANG, H., YEUNG, D. Y., WONG, W. K., and WOO, W. C. Convolutional LSTM network: a machine learning approach for precipitation nowcasting. Neural Information Processing Systems, 9, 802-810 (2015)
[16] ROZAS, L. P., RENZULLO, L. J., INZA, I., and LOZANO, J. A. A data-driven approach to precipitation parameterizations using convolutional encoder-decoder neural networks. arXiv: 1903.10274 (2019) https://arxiv.org/abs/1903.10274
[17] WEYN, J. A., DURRAN, D. R., and 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, 11, 2680-2693 (2019)
[18] CASPER, K. S., LASSE, E., JONATHAN, H., MOSTAFA, D., AVITAL, O., TIM, S., SHREYA, A., JASON, H., and NAL, K. A neural weather model for precipitation forecasting. arXiv: 2003.12140 (2020) https://arxiv.org/abs/2003.12140
[19] BREIMAN, L. Random forests. Machine Learning, 45, 5-32 (2001)
[20] JAMES, G. An Introduction to Statistical Learning, 2nd ed., Springer, New York, 316-332 (2017)
[21] HASTIE, T. The Elements of Statistical Learning, 2nd ed., Springer, New York, 587-622 (2009)
[22] CHEN, T. Q. and CARLOS, G. XGBoost: a scalable tree boosting system. Association for Computing Machinery, 10, 785-794 (2016)
[23] LI, H. C., YU, C., and XIA, J. J. A model output machine learning method for grid temperature forecasts in the Beijing area. Advances in Atmospheric Sciences, 36, 1156-1170 (2019)
[24] HE, K. M., ZHANG, X., REN, S., and SUN, J. Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, IEEE, Piscataway, 770-778 (2016)

Options

Outlines

模态框（Modal）标题

Abstract

Cite this article

References