×

Semiparametric modeling: correcting low-dimensional model error in parametric models. (English) Zbl 1351.62175

Summary: In this paper, a semiparametric modeling approach is introduced as a paradigm for addressing model error arising from unresolved physical phenomena. Our approach compensates for model error by learning an auxiliary dynamical model for the unknown parameters. Practically, the proposed approach consists of the following steps. Given a physics-based model and a noisy data set of historical observations, a Bayesian filtering algorithm is used to extract a time-series of the parameter values. Subsequently, the diffusion forecast algorithm is applied to the retrieved time-series in order to construct the auxiliary model for the time evolving parameters. The semiparametric forecasting algorithm consists of integrating the existing physics-based model with an ensemble of parameters sampled from the probability density function of the diffusion forecast. To specify initial conditions for the diffusion forecast, a Bayesian semiparametric filtering method that extends the Kalman-based filtering framework is introduced. In difficult test examples, which introduce chaotically and stochastically evolving hidden parameters into the Lorenz-96 model, we show that our approach can effectively compensate for model error, with forecasting skill comparable to that of the perfect model.

MSC:

62M20 Inference from stochastic processes and prediction
62F15 Bayesian inference
62G05 Nonparametric estimation

Software:

CRCP
PDFBibTeX XMLCite
Full Text: DOI arXiv

References:

[1] Grabowski, W. W., Coupling cloud processes with the large-scale dynamics using the Cloud-Resolving Convection Parameterization (CRCP), J. Atmos. Sci., 58, 978-996 (2001)
[2] Weinan, E.; Engquist, B.; Li, X.; Ren, W.; Vanden-Eijnden, E., Heterogeneous multiscale methods: a review, Commun. Comput. Phys., 2, 3, 367-450 (2007) · Zbl 1164.65496
[3] Frenkel, Y.; Majda, A. J.; Khouider, B., Using the stochastic multicloud model to improve tropical convective parameterization: a paradigm example, J. Atmos. Sci., 69, 1080-1105 (2012)
[4] Majda, A. J.; Grooms, I., New perspectives on superparameterization for geophysical turbulence, J. Comput. Phys., 271, 60-77 (2014) · Zbl 1349.86035
[5] Katsoulakis, M. A.; Majda, A. J.; Sopasakis, A., Multiscale couplings in prototype hybrid deterministic/stochastic systems: part I, deterministic closures, Commun. Math. Sci., 2, 2, 255-294 (2004) · Zbl 1103.93013
[6] Katsoulakis, M. A.; Majda, A. J.; Sopasakis, A., Multiscale couplings in prototype hybrid deterministic/stochastic systems: part II, stochastic closures, Commun. Math. Sci., 3, 3, 453-478 (2004) · Zbl 1101.34042
[7] Majda, A. J.; Harlim, J., Physics constrained nonlinear regression models for time series, Nonlinearity, 26, 201-217 (2013) · Zbl 1262.93024
[8] Harlim, J.; Mahdi, A.; Majda, A. J., An ensemble Kalman filter for statistical estimation of physics constrained nonlinear regression models, J. Comput. Phys., 257, Part A, 782-812 (2014) · Zbl 1349.62593
[9] Berry, T.; Harlim, J., Linear theory for filtering nonlinear multi scale systems with model error, Proc. R. Soc. A, 470, 2167 (2014)
[10] Berry, T.; Sauer, T., Adaptive ensemble Kalman filtering of nonlinear systems, Tellus A, 65, 20331 (2013)
[11] Zhen, Y.; Harlim, J., Adaptive error covariance estimation methods for ensemble Kalman filtering, J. Comput. Phys., 273, 619-638 (2015) · Zbl 1349.62333
[12] Arnold, H. M.; Moroz, I. M.; Palmer, T. N., Stochastic parametrizations and model uncertainty in the Lorenz 96 system, Philos. Trans. R. Soc. A, Math. Phys. Eng. Sci., 371, 1991 (2013)
[13] Härdle, W., Nonparametric and Semiparametric Models (2004), Springer · Zbl 1059.62032
[14] Terrell, D. G.; Scott, D. W., Variable kernel density estimation, Ann. Stat., 20, 1236-1265 (1992) · Zbl 0763.62024
[15] Berry, T.; Harlim, J., Nonparametric uncertainty quantification for stochastic gradient flows, SIAM/ASA J. Uncertain. Quantificat., 3, 1, 484-508 (2015) · Zbl 1339.60067
[16] Berry, T.; Giannakis, D.; Harlim, J., Nonparametric forecasting of low-dimensional dynamical systems, Phys. Rev. E, 91, Article 032915 pp. (2015)
[17] Berry, T.; Harlim, J., Forecasting turbulent modes with nonparametric diffusion models: learning from noisy data, Physica D (2015), submitted for publication
[18] Majda, A. J.; Timofeyev, I.; Vanden-Eijnden, E., Models for stochastic climate prediction, Proc. Natl. Acad. Sci., 96, 15687-15691 (1999)
[19] Khasminskii, R. Z., Principle of averaging for parabolic and elliptic differential equations and for Markov processes with small diffusion, Theory Probab. Appl., 8, 1, 1-21 (1963) · Zbl 0211.20701
[20] Majda, A. J.; Gershgorin, B.; Yuan, Y., Low frequency response and fluctuation-dissipation theorems: theory and practice, J. Atmos. Sci., 67, 1181-1201 (2010)
[21] Sauer, T.; Yorke, J. A.; Casdagli, M., Embedology, J. Stat. Phys., 65, 3-4, 579-616 (1991) · Zbl 0943.37506
[22] Stark, J., Delay embeddings for forced systems. I. Deterministic forcing, J. Nonlinear Sci., 9, 255-332 (1999) · Zbl 0985.37098
[23] Stark, J.; Broomhead, D. S.; Davies, M. E.; Huke, J., Delay embeddings for forced systems. II. Stochastic forcing, J. Nonlinear Sci., 13, 519-577 (2003)
[24] Berry, T.; Cressman, J. R.; Gregurić Ferenček, Z.; Sauer, T., Time-scale separation from diffusion-mapped delay coordinates, SIAM J. Appl. Dyn. Syst., 12, 618-649 (2013) · Zbl 1291.37101
[25] Giannakis, D.; Majda, A. J., Time series reconstruction via machine learning: revealing decadal variability and intermittency in the north pacific sector of a coupled climate model, (Conference on Intelligent Data Understanding. Conference on Intelligent Data Understanding, CIDU, Mountain View, California (2011)), 107-117
[26] Giannakis, D.; Majda, A. J., Nonlinear Laplacian spectral analysis for time series with intermittency and low-frequency variability, Proc. Natl. Acad. Sci., 109, 7, 2222-2227 (2012) · Zbl 1256.62053
[27] Coifman, R.; Lafon, S., Diffusion maps, Appl. Comput. Harmon. Anal., 21, 5-30 (2006) · Zbl 1095.68094
[28] Berry, T.; Harlim, J., Variable bandwidth diffusion kernels, Appl. Comput. Harmon. Anal., 40, 1, 68-96 (2016) · Zbl 1343.94020
[29] Lorenz, E. N., Predictability - a problem partly solved, (Proceedings on Predictability. Proceedings on Predictability, held at ECMWF on 4-8 September 1995 (1996)), 1-18
[30] Lorenz, E. N., Deterministic nonperiodic flow, J. Atmos. Sci., 20, 2, 130-141 (1963) · Zbl 1417.37129
[31] Julier, S. J.; Uhlmann, J. K., Unscented filtering and nonlinear estimation, Proc. IEEE, 92, 3, 401-422 (2004)
[32] Friedland, B., Treatment of bias in recursive filtering, IEEE Trans. Autom. Control, AC-14, 359-367 (1969)
[33] Friedland, B., Estimating sudden changes of biases in linear dynamical systems, IEEE Trans. Autom. Control, AC-27, 237-240 (1982) · Zbl 0483.93076
[34] Mehra, R. K., Approaches to adaptive filtering, IEEE Trans. Autom. Control, 17, 5, 693-698 (1972) · Zbl 0261.93036
[35] Kang, E. L.; Harlim, J., Filtering partially observed multiscale systems with heterogeneous multiscale methods-based reduced climate models, Mon. Weather Rev., 140, 3, 860-873 (2012)
[36] Golightly, A.; Wilkinson, D. J., Bayesian inference for nonlinear multivariate diffusion models observed with error, Comput. Stat. Data Anal., 52, 3, 1674-1693 (2008) · Zbl 1452.62603
[37] Takens, F., Detecting strange attractors in turbulence, (Rand, D.; Young, L.-S., Dynamical Systems and Turbulence, Warwick. Dynamical Systems and Turbulence, Warwick, Lect. Notes Math., vol. 898 (1981), Springer: Springer Berlin, Heidelberg), 366-381 · Zbl 0513.58032
[38] Sauer, T.; Yorke, J. A.; Casdagli, M., Embedology, J. Stat. Phys., 65, 3, 579-616 (1991) · Zbl 0943.37506
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.