Abstract
We perform a comparative study of different supervised machine learning time-series methods for short-term and long-term temperature forecasts on a real world dataset for the daily maximum temperature over North America given by DayMET. DayMET showcases a stochastic and high-dimensional spatio-temporal structure and is available at exceptionally fine resolution (a 1 km grid). We apply projection-based reduced order modeling to compress this high dimensional data, while preserving its spatio-temporal structure. We use variants of time-series specific neural network models on this reduced representation to perform multi-step weather predictions. We also use a Gaussian-process based error correction model to improve the forecasts from the neural network models. From our study, we learn that the recurrent neural network based techniques can accurately perform both short-term as well as long-term forecasts, with minimal computational cost as compared to the convolution based techniques. We see that the simple kernel based Gaussian-processes can also predict the neural network model errors, which can then be used to improve the long term forecasts.
This material was based upon work supported by the U.S. Department of Energy, Office of Science, Office of Advanced Scientific Computing Research (ASCR) under Contract DE-AC02-06CH11347.
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
Ciscar, J.-C., et al.: Physical and economic consequences of climate change in Europe. Proc. Natl. Acad. Sci. 108(7), 2678–2683 (2011)
Gosling, S.N., Lowe, J.A., McGregor, G.R., Pelling, M., Malamud, B.D.: Associations between elevated atmospheric temperature and human mortality: a critical review of the literature. Clim. Change 92(3), 299–341 (2009)
Gentine, P., Pritchard, M., Rasp, S., Reinaudi, G., Yacalis, G.: Could machine learning break the convection parameterization deadlock? Geophys. Res. Lett. 45(11), 5742–5751 (2018)
Brenowitz, N.D., Bretherton, C.S.: Prognostic validation of a neural network unified physics parameterization. Geophys. Rese. Lett. 45(12), 6289–6298 (2018)
Rasp, S., Pritchard, M.S., Gentine, P.: Deep learning to represent subgrid processes in climate models. Proc. Natl. Acad. Sci. 115(39), 9684–9689 (2018)
Nooteboom, P.D., Feng, Q.Y., López, C., Hernández-García, E., Dijkstra, H.A.: Using network theory and machine learning to predict el niño. Earth Syst. Dyn. 9(3), 969–983 (2018)
Moosavi, A., Rao, V., Sandu, A.: Machine learning based algorithms for uncertainty quantification in numerical weather prediction models. J. Comput. Sci. 101295 (2021)
Liu, Y., et al.: Application of deep convolutional neural networks for detecting extreme weather in climate datasets. arXiv:1605.01156 (2016)
Scher, S.: Toward data-driven weather and climate forecasting: Approximating a simple general circulation model with deep learning. Geophys. Res. Lett. 45(22), 12–616 (2018)
Weyn, J.A., Durran, D.R., Caruana, R.: Improving data-driven global weather prediction using deep convolutional neural networks on a cubed sphere. J. Adv. Model. Earth Syst. 12(9), e2020MS002109 (2020)
Rasp, S., Thuerey, N.: Purely data-driven medium-range weather forecasting achieves comparable skill to physical models at similar resolution. arXiv:2008.08626 (2020)
Chattopadhyay, A., Nabizadeh, E., Hassanzadeh, P.: Analog forecasting of extreme-causing weather patterns using deep learning. J. Adv. Model. Earth Syst. 12(2), e2019MS001958 (2020)
Rodrigues, E.R., Oliveira, I., Cunha, R., Netto, M.: Deepdownscale: a deep learning strategy for high-resolution weather forecast. In: 2018 IEEE 14th International Conference on e-Science (e-Science), pp. 415–422. IEEE (2018)
Shi, X., Chen, Z., Wang, H., Yeung, D.-Y. Wong, W.-K., Woo, W.-C.: Convolutional lstm network: a machine learning approach for precipitation nowcasting. arXiv:1506.04214 (2015)
Maulik, R., Egele, R., Lusch, B., Balaprakash, P.: Recurrent Neural Network Architecture Search for Geophysical Emulation. IEEE Press (2020)
Skinner, D.J., Maulik, R.: Meta-modeling strategy for data-driven forecasting. arXiv:2012.00678 (2020)
Karpatne, A., Ebert-Uphoff, I., Ravela, S., Babaie, H.A., Kumar, V.: Machine learning for the geosciences: challenges and opportunities. IEEE Trans. Knowl. Data Eng. 31(8), 1544–1554 (2018)
Dueben, P.D., Bauer, P.: Challenges and design choices for global weather and climate models based on machine learning. Geosci. Model Dev. 11(10), 3999–4009 (2018)
Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997)
Rahman, S.M., Pawar, S., San, O., Rasheed, A., Iliescu, T.: Nonintrusive reduced order modeling framework for quasigeostrophic turbulence. Phys. Rev. E 100(5), 053306 (2019)
Mohan, A.T., Gaitonde, D.V.: A deep learning based approach to reduced order modeling for turbulent flow control using lSTM neural networks. arXiv:1804.09269 (2018)
Maulik, R., Lusch, B., Balaprakash, P.: Non-autoregressive time-series methods for stable parametric reduced-order models. Phys. Fluids 32(8), 087115 (2020)
Taira, K.: Modal analysis of fluid flows: applications and outlook. AIAA J. 1–25 (2019)
Benner, P., Gugercin, S., Willcox, K.: A survey of projection-based model reduction methods for parametric dynamical systems. SIAM Rev. 57(4), 483–531 (2015)
Holmes, P., Lumley, J.L., Berkooz, G., Rowley, C.W.: Turbulence, Coherent Structures, Dynamical Systems and Symmetry, vol. 36. Princeton University, New Jersey (1998)
Chatterjee, A.: An introduction to the proper orthogonal decomposition. Curr. Sci. 78, 808–817 (2000)
Maulik, R., Mohan, A., Lusch, B., Madireddy, S., Balaprakash, P., Livescu, D.: Time-series learning of latent-space dynamics for reduced-order model closure. Phys. D: Nonlinear Phenom. 405, 132368 (2020)
Ma, C., Wang, J., et al.: Model reduction with memory and the machine learning of dynamical systems. arXiv:1808.04258 (2018)
Yu, Y., Si, X., Hu, C., Zhang, J.: A review of recurrent neural networks: LSTM cells and network architectures. Neural Comput. 31(7), 1235–1270 (2019)
Petneházi, G.: Recurrent Neural Networks for Time Series Forecasting. arXiv:1901.00069 (2018)
Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997)
Karevan, Z., Suykens, J.A.K.: Transductive lstm for time-series prediction: an application to weather forecasting. Neural Netw. 125, 1–9 (2020)
Zhang, Q., Wang, H., Dong, J., Zhong, G., Sun, X.: Prediction of sea surface temperature using long short-term memory. IEEE Geosci. Remote Sens. Lett. 05 (2017)
Broni-Bediako, C., Katsriku, F., Unemi, T., Shinomiya, N., Abdulai, J.-D., Atsumi, M.: El niño-southern oscillation forecasting using complex networks analysis of lstm neural networks. vol. 01 (2018)
Schuster, M., Paliwal, K.K.: Bidirectional recurrent neural networks. IEEE Trans. Signal Process. 45(11), 2673–2681 (1997)
Namini, S.S., Tavakoli, N., Namin, A.S.: The performance of LSTM and biLSTM in forecasting time series. vol. 12, pp. 3285–3292 (2019)
Socher, R., Lin, C., Ng, A., Manning, C.: Parsing natural scenes and natural language with recursive neural networks, vol. 01, pp. 129–136 (2011)
Shen, G., Kurths, J., Yuan, Y.: Sequence-to-sequence prediction of spatiotemporal systems. Chaos: Interdiscip. J. Nonlinear Sci. 30(2), 023102 (2020)
Ciresan, D., Meier, U., Masci, J., Gambardella, L.M., Schmidhuber, J.: Flexible, high performance convolutional neural networks for image classification, vol. 07, pp. 1237–1242 (2011)
Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. Commun. ACM 60(6), 84–90 (2017)
Bai, S., Kolter, J., Koltun, V.: An empirical evaluation of generic convolutional and recurrent networks for sequence modeling, vol. 03 (2018)
Yan, J., Mu, L., Wang, L., Ranjan, R., Zomaya, A.Y.: Temporal convolutional networks for the advance prediction of ENSO. Sci. Rep. 10(1), 1–15 (2020)
Remy, P.: Temporal convolutional networks for keras. https://github.com/philipperemy/keras-tcn (2020)
Bai, S., Kolter, J.Z., Koltun, V.: An empirical evaluation of generic convolutional and recurrent networks for sequence modeling. arXiv:1803.01271 (2018)
Sapsis, T.P., Majda, A.J.: Blending modified gaussian closure and non-gaussian reduced subspace methods for turbulent dynamical systems. J. Nonlinear Sci. 23(6), 1039–1071 (2013)
Rasmussen, C.E.: Gaussian processes in machine learning. In Summer School on Machine Learning, pp. 63–71. Springer, Berlin (2003)
Thornton, M.M., Thornton, P.E., Wei, Y., Mayer, B.W., Cook, R.B., Vose, R.S.: Daymet: Annual climate summaries on a 1-km grid for north America, version 3. Ornl Daac, Oak Ridge, Tennessee, USA (2016)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Sastry, V.K., Maulik, R., Rao, V., Lusch, B., Renganathan, S.A., Kotamarthi, R. (2021). Data-Driven Deep Learning Emulators for Geophysical Forecasting. In: Paszynski, M., Kranzlmüller, D., Krzhizhanovskaya, V.V., Dongarra, J.J., Sloot, P.M. (eds) Computational Science – ICCS 2021. ICCS 2021. Lecture Notes in Computer Science(), vol 12746. Springer, Cham. https://doi.org/10.1007/978-3-030-77977-1_35
Download citation
DOI: https://doi.org/10.1007/978-3-030-77977-1_35
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-77976-4
Online ISBN: 978-3-030-77977-1
eBook Packages: Computer ScienceComputer Science (R0)