Articles | Volume 14, issue 9
Geosci. Model Dev., 14, 5623–5635, 2021
https://doi.org/10.5194/gmd-14-5623-2021
Geosci. Model Dev., 14, 5623–5635, 2021
https://doi.org/10.5194/gmd-14-5623-2021

Development and technical paper 13 Sep 2021

Development and technical paper | 13 Sep 2021

Combining ensemble Kalman filter and reservoir computing to predict spatiotemporal chaotic systems from imperfect observations and models

Futo Tomizawa and Yohei Sawada

Related authors

Socio-hydrological data assimilation: analyzing human–flood interactions by model–data integration
Yohei Sawada and Risa Hanazaki
Hydrol. Earth Syst. Sci., 24, 4777–4791, https://doi.org/10.5194/hess-24-4777-2020,https://doi.org/10.5194/hess-24-4777-2020, 2020
Short summary
Do surface lateral flows matter for data assimilation of soil moisture observations into hyperresolution land models?
Yohei Sawada
Hydrol. Earth Syst. Sci., 24, 3881–3898, https://doi.org/10.5194/hess-24-3881-2020,https://doi.org/10.5194/hess-24-3881-2020, 2020
Short summary
Do surface lateral flows matter for data assimilation of soil moisture observations into hyperresolution land models?
Yohei Sawada
Hydrol. Earth Syst. Sci. Discuss., https://doi.org/10.5194/hess-2019-324,https://doi.org/10.5194/hess-2019-324, 2019
Manuscript not accepted for further review
Short summary

Related subject area

Numerical methods
The Coastline Evolution Model 2D (CEM2D) V1.1
Chloe Leach, Tom Coulthard, Andrew Barkwith, Daniel R. Parsons, and Susan Manson
Geosci. Model Dev., 14, 5507–5523, https://doi.org/10.5194/gmd-14-5507-2021,https://doi.org/10.5194/gmd-14-5507-2021, 2021
Short summary
An iterative process for efficient optimisation of parameters in geoscientific models: a demonstration using the Parallel Ice Sheet Model (PISM) version 0.7.3
Steven J. Phipps, Jason L. Roberts, and Matt A. King
Geosci. Model Dev., 14, 5107–5124, https://doi.org/10.5194/gmd-14-5107-2021,https://doi.org/10.5194/gmd-14-5107-2021, 2021
Short summary
Ocean Plastic Assimilator v0.2: assimilation of plastic concentration data into Lagrangian dispersion models
Axel Peytavin, Bruno Sainte-Rose, Gael Forget, and Jean-Michel Campin
Geosci. Model Dev., 14, 4769–4780, https://doi.org/10.5194/gmd-14-4769-2021,https://doi.org/10.5194/gmd-14-4769-2021, 2021
Short summary
Development of a moving point source model for shipping emission dispersion modeling in EPISODE–CityChem v1.3
Kang Pan, Mei Qi Lim, Markus Kraft, and Epaminondas Mastorakos
Geosci. Model Dev., 14, 4509–4534, https://doi.org/10.5194/gmd-14-4509-2021,https://doi.org/10.5194/gmd-14-4509-2021, 2021
Short summary
Efficient Bayesian inference for large chaotic dynamical systems
Sebastian Springer, Heikki Haario, Jouni Susiluoto, Aleksandr Bibov, Andrew Davis, and Youssef Marzouk
Geosci. Model Dev., 14, 4319–4333, https://doi.org/10.5194/gmd-14-4319-2021,https://doi.org/10.5194/gmd-14-4319-2021, 2021
Short summary

Cited articles

Asanjan, A., Yang, T., Hsu, K., Sorooshian, S., Lin, J., and Peng, Q.: Short-Term Precipitation Forecast Based on the PERSIANN System and LSTM Recurrent Neural Networks, J. Geophys. Res.-Atmos., 123, 12543–12563, https://doi.org/10.1029/2018JD028375, 2018. 
Bannister, R. N.: A review of operational methods of variational and ensemble-variational data assimilation, Q. J. Roy. Meteor. Soc., 143, 607–633, https://doi.org/10.1002/qj.2982, 2017. 
Bocquet, M. and Sakov, P.: Joint state and parameter estimation with an iterative ensemble Kalman smoother, Nonlin. Processes Geophys., 20, 803–818, https://doi.org/10.5194/npg-20-803-2013, 2013. 
Bocquet, M., Brajard, J., Carrassi, A., and Bertino, L.: Data assimilation as a learning tool to infer ordinary differential equation representations of dynamical models, Nonlin. Processes Geophys., 26, 143–162, https://doi.org/10.5194/npg-26-143-2019, 2019. 
Bocquet, M., Farchi, A., and Malartic, Q.: Online learning of both state and dynamics using ensemble Kalman filters, Found. Data Sci., https://doi.org/10.3934/fods.2020015, 2020. 
Download
Short summary
A new method to predict chaotic systems from observation and process-based models is proposed by combining machine learning with data assimilation. Our method is robust to the sparsity of observation networks and can predict more accurately than a process-based model when it is biased. Our method effectively works when both observations and models are imperfect, which is often the case in geoscience. Therefore, our method is useful to solve a wide variety of prediction problems in this field.