Deep Markov Models for Data Assimilation in Chaotic Dynamical Systems
- 225 Downloads
This is an extension from a selected paper from JSAI2019. Recently, the use of deep learning in data assimilation has been gaining research attention. For instance, the time-series deep Markov model has been proposed along with an inference network trained using variational inference. However, the original proposal did not fully leverage the model ability for data assimilation. Therefore, we aim to evaluate the suitability of a deep Markov model and its inference network for a chaotic dynamical system, which is a common problem in data assimilation. We evaluate the model under various generative conditions. The results show that when information about part of the target model is known, the model has comparable performance to a smoothed unscented Kalman filter, even under the presence of process and observation noise.
KeywordsData assimilation Chaotic system Deep Markov model Variational inference
This work was supported by JSPS KAKENHI under Grant Number JP16K00231.
- 5.Gu, S.S., Ghahramani, Z., Turner, R.E.: Neural adaptive sequential Monte Carlo. In: Advances in Neural Information Processing Systems, vol. 28, pp. 2629–2637. Curran Associates, Inc. (2015)Google Scholar
- 6.Kutschireiter, A., Surace, S.C., Sprekeler, H., Pfister, J.-P.: Nonlinear Bayesian filtering and learning: a neuronal dynamics for perception. Sci. Rep. 7(1), 8722-1–8722-13 (2017)Google Scholar
- 7.Cintra, R.S., Campos Velho, H.F.: Data assimilation by artificial neural networks for an atmospheric general circulation model. In: Advanced Applications for Artificial Neural Networks, chap. 14 (2018)Google Scholar
- 8.Loh, K., Omrani, P.S., Linden, R.V.: Deep learning and data assimilation for real-time production prediction in natural gas wells. arXiv:1802.05141 [cs.LG] (2018)
- 9.Krishnan, R.G., Shalit, U., Sontag, D.: Structured inference networks for nonlinear state space model. In: AAAI (2017)Google Scholar
- 11.Cho, K., van Merriënboer, B., Gülçehre, Ç., Bahdanau, D., Bougares, F., Schwenk, H., Bengio, Y.: Learning phrase representations using RNN encoder-decoder for statistical machine translation. In: Proceedings of the 2014 Conference on EMNLP, pp. 1724–1734 (2014)Google Scholar
- 12.Lorenz, E.N.: Predictability: a problem partly solved. Semin. Predict. 1(1), 1–18 (1995)Google Scholar