Automatic development of deep neural networks for improving numerical meteorological forecast

А.Yu. Doroshenko, R.V. Kushnirenko

Abstract


This paper briefly describes the examples of deep learning applications to scientific and technical problems, as well as the difficulties that may arise with these applications. The paper shows the importance of the automatic development of deep neural networks. The paper verifies the possibility of the application of the neuroevolutionary approach to the post-processing of the results of meteorological forecasting (2m temperature) obtained using numerical hydrodynamic methods. The results show that in half of the cases, both the rootmean-square error value and the percentage of improved predictions are better (and in some cases much better) for the neuroevolutionary approach than the corresponding values for the manually designed architecture. Thus, neural network models obtained automatically can outperform manually designed models while applied to improving numerical meteorological forecasts

Prombles in programming 2024; 1: 57-63


Keywords


deep learning; automatic development of neural networks; neuroevolution; meteorological forecasting

References


Agapiou, A., 2017. Remote sensing heritage in a petabyte-scale: satellite data and heritage Earth Engine© applications. International Journal of Digital Earth, 10(1), pp.85-102. CrossRef

LeCun, Y., Bengio, Y. and Hinton, G., 2015. Deep learning. nature, 521(7553), pp.436-444. CrossRef

Bhimji, W., Farrell, S.A., Kurth, T., Paganini, M., Prabhat and Racah, E., 2018, September. Deep neural networks for physics analysis on low-level whole-detector data at the LHC. In Journal of Physics: Conference Series (Vol. 1085, p. 042034). IOP Publishing. CrossRef

Schütt, K.T., Arbabzadah, F., Chmiela, S., Müller, K.R. and Tkatchenko, A., 2017. Quantum-chemical insights from deep tensor neural networks. Nature communications, 8(1), p.13890. CrossRef

Alipanahi, B., Delong, A., Weirauch, M.T. and Frey, B.J., 2015. Predicting the sequence specificities of DNA-and RNA-binding proteins by deep learning. Nature biotechnology, 33(8), pp.831-838. CrossRef

Liu, Y., Racah, E., Correa, J., Khosrowshahi, A., Lavers, D., Kunkel, K., Wehner, M. and Collins, W., 2016. Application of deep convolutional neural networks for detecting extreme weather in climate datasets. arXiv preprint arXiv:1605.01156.

Racah, E., Beckham, C., Maharaj, T., Ebrahimi Kahou, S., Prabhat, M. and Pal, C., 2017. Extremeweather: A large-scale climate dataset for semi-supervised detection, localization, and understanding of extreme weather events. Advances in neural information processing systems, 30.

LeCun, Y., Bottou, L., Bengio, Y. and Haffner, P., 1998. Gradient-based learning applied to document recognition. Proceedings of the IEEE, 86(11), pp.2278-2324. CrossRef

Sak, H., Senior, A. and Beaufays, F., 2014. Long short-term memory based recurrent neural network architectures for large vocabulary speech recognition. arXiv preprint arXiv:1402.1128. CrossRef

Oh, J., Guo, X., Lee, H., Lewis, R.L. and Singh, S., 2015. Action-conditional video prediction using deep networks in atari games. Advances in neural information processing systems, 28.

Shi, X., Chen, Z., Wang, H., Yeung, D.Y., Wong, W.K. and Woo, W.C., 2015. Convolutional LSTM network: A machine learning approach for precipitation nowcasting. Advances in neural information processing systems, 28.

Che, Z., Purushotham, S., Cho, K., Sontag, D. and Liu, Y., 2018. Recurrent neural networks for multivariate time series with missing values. Scientific reports, 8(1), p.6085. CrossRef

Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J. and Wojna, Z., 2016. Rethinking the inception architecture for computer vision. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 2818-2826). CrossRef

Hoos, H.H., 2012. Programming by optimization. Communications of the ACM, 55(2), pp.70-80. CrossRef

Miikkulainen, R., Liang, J., Meyerson, E., Rawal, A., Fink, D., Francon, O., Raju, B., Shahrzad, H., Navruzyan, A., Duffy, N. and Hodjat, B., 2024. Evolving deep neural networks. In Artificial intelligence in the age of neural networks and brain computing (pp. 269-287). Academic Press. CrossRef

Stanley, K.O. and Miikkulainen, R., 2002. Evolving neural networks through augmenting topologies. Evolutionary computation, 10(2), pp.99-127. CrossRef

Doroshenko, А.Y., Shpyg, V.M. and Kushnirenko, R.V., 2023. Deeplearning-based approach to improving numerical weather forecasts. PROBLEMS IN PROGRAMMING, (3), pp.91-98. CrossRef

Doroshenko, А.Y. and Kushnirenko, R.V., 2023. Recurrent neural networks for the problem of improving numerical meteorological forecasts. PROBLEMS IN PROGRAMMING, (4), pp.90-97. CrossRef

Shpyg, V., Budak, I., Pishniak, D. and Poperechnyi, P., 2013, November. The application of regional NWP models to operational weather forecasting in Ukraine. In CAS Technical Conference (TECO) on" Responding to the Environmental Stressors of the 21st Century" Available from: http://www. wmo. int/pages/prog/arep/ cas/documents/Ukraine-NWPModels. pdf

Doms, G. and Baldauf, M., 2011. A description of the nonhydrostatic regional COSMO-Model Part I: dynamics and numerics. Deutscher Wetterdienst, Offenbach.

Goodfellow, I., Bengio, Y. and Courville, A., 2016. Deep learning. MIT press.

https://keras.io

https://www.tensorflow.org

https://tfne.readthedocs.io/en/latest

https://www.python.org




DOI: https://doi.org/10.15407/pp2024.01.057

Refbacks

  • There are currently no refbacks.