Data Assimilation with Gaussian Mixture Models Using the Dynamically Orthogonal Field Equations. Part I: Theory and Scheme

AbstractThis work introduces and derives an efficient, data-driven assimilation scheme, focused on a time-dependent stochastic subspace that respects nonlinear dynamics and captures non-Gaussian statistics as it occurs. The motivation is to obtain a filter that is applicable to realistic geophysical applications, but that also rigorously utilizes the governing dynamical equations with information theory and learning theory for efficient Bayesian data assimilation. Building on the foundations of classical filters, the underlying theory and algorithmic implementation of the new filter are developed and derived. The stochastic Dynamically Orthogonal (DO) field equations and their adaptive stochastic subspace are employed to predict prior probabilities for the full dynamical state, effectively approximating the Fokker–Planck equation. At assimilation times, the DO realizations are fit to semiparametric Gaussian Mixture Models (GMMs) using the Expectation-Maximization algorithm and the Bayesian Information Cri...

[1]  A. Bennett.  Inverse Methods in Physical Oceanography , 1992 .

[2]  D. Menemenlis.  Inverse Modeling of the Ocean and Atmosphere , 2002 .

[3]  A Gordon,et al.  Classification, 2nd Edition , 1999 .

[4]  Pierre F. J. Lermusiaux,et al.  Dynamically orthogonal field equations for continuous stochastic dynamical systems , 2009 .

[5]  P. Sura.  On non-Gaussian SST variability in the Gulf Stream and other strong currents , 2010 .

[6]  E. Lorenz.  Deterministic nonperiodic flow , 1963 .

[7]  Christopher K. Wikle,et al.  Atmospheric Modeling, Data Assimilation, and Predictability , 2005, Technometrics.

[8]  J. Whitaker,et al.  Ensemble Square Root Filters , 2003, Statistical Methods for Climate Scientists.

[9]  Hans R. Künsch,et al.  Mixture ensemble Kalman filters , 2013, Comput. Stat. Data Anal..

[10]  B. Silverman,et al.  Density Estimation for Statistics and Data Analysis , 1987 .

[11]  B. R. Noack.  Turbulence, Coherent Structures, Dynamical Systems and Symmetry , 2013 .

[12]  Petar M. Djuric,et al.  Gaussian particle filtering , 2003, IEEE Trans. Signal Process..

[13]  G. Evensen.  Sequential data assimilation with a nonlinear quasi‐geostrophic model using Monte Carlo methods to forecast error statistics , 1994 .

[14]  C. Wunsch.  The Ocean Circulation Inverse Problem , 1996 .

[15]  Neil J. Gordon,et al.  Editors: Sequential Monte Carlo Methods in Practice , 2001 .

[16]  M. Ghil,et al.  Data assimilation in meteorology and oceanography , 1991 .

[17]  G. Eyink,et al.  Ensemble Filtering for Nonlinear Dynamics , 2003 .

[18]  Radford M. Neal.  Pattern Recognition and Machine Learning , 2007, Technometrics.

[19]  Svenska geofysiska föreningen.  Tellus. Series A, Dynamic meteorology and oceanography , 1983 .

[20]  Pierre F. J. Lermusiaux,et al.  Numerical schemes for dynamically orthogonal equations of stochastic fluid and ocean flows , 2013, J. Comput. Phys..

[21]  Pierre F. J. Lermusiaux,et al.  Data Assimilation with Gaussian Mixture Models Using the Dynamically Orthogonal Field Equations. Part II: Applications , 2013 .

[22]  Pierre F. J. Lermusiaux,et al.  Advanced interdisciplinary data assimilation: filtering and smoothing via error subspace statistical estimation , 2002, OCEANS '02 MTS/IEEE.

[23]  Pierre F. J. Lermusiaux,et al.  Modeling Uncertainties in the Prediction of the Acoustic Wavefield in a Shelfbeak Environment , 2001 .

[24]  Isidore Eisenberger,et al.  Genesis of Bimodal Distributions , 1964 .

[25]  J. Restrepo,et al.  The Diffusion Kernel Filter Applied to Lagrangian Data Assimilation , 2009 .

[26]  Thomas M. Cover,et al.  Elements of Information Theory , 2005 .

[27]  G. Eyink,et al.  A Maximum Entropy Method for Particle Filtering , 2006 .

[28]  Chris Snyder,et al.  Toward a nonlinear ensemble filter for high‐dimensional systems , 2003 .

[29]  F. L. Dimet,et al.  Variational algorithms for analysis and assimilation of meteorological observations: theoretical aspects , 1986 .

[30]  Michael Ghil,et al.  Advanced data assimilation in strongly nonlinear dynamical systems , 1994 .

[31]  Kazimierz Sobczyk,et al.  Information dynamics : Premises, challenges and results , 2001 .

[32]  R. Daley.  Atmospheric Data Analysis , 1991 .

[33]  P. J. Green,et al.  Density Estimation for Statistics and Data Analysis , 1987 .

[34]  Philippe Courtier,et al.  Unified Notation for Data Assimilation : Operational, Sequential and Variational , 1997 .

[35]  Albert Tarantola,et al.  Inverse problem theory - and methods for model parameter estimation , 2004 .

[36]  A. Robinson,et al.  Data Assimilation via Error Subspace Statistical Estimation.Part I: Theory and Schemes , 1999, Monthly Weather Review.

[37]  P. Houtekamer,et al.  Data Assimilation Using an Ensemble Kalman Filter Technique , 1998 .

[38]  Dinh-Tuan Pham,et al.  A New Approximate Solution of the Optimal Nonlinear Filter for Data Assimilation in Meteorology and Oceanography , 2008 .

[39]  Pierre F. J. Lermusiaux,et al.  Estimation and study of mesoscale variability in the strait of Sicily , 1999 .

[40]  T. Sapsis,et al.  Dynamical criteria for the evolution of the stochastic dimensionality in flows with uncertainty , 2012 .

[41]  T. Başar,et al.  A New Approach to Linear Filtering and Prediction Problems , 2001 .

[42]  P. Malanotte‐Rizzoli.  Modern approaches to data assimilation in ocean modeling , 1996 .

[43]  P. Deb.  Finite Mixture Models , 2008 .

[44]  Pierre FJ Lermusiaux.  Evolving the subspace of the three-dimensional multiscale ocean variability: Massachusetts Bay , 2001 .

[45]  Robert B. Ash,et al.  Information Theory , 2020, The SAGE International Encyclopedia of Mass Media and Society.

[46]  Peter Jan,et al.  Particle Filtering in Geophysical Systems , 2009 .

[47]  Pierre F. J. Lermusiaux,et al.  Quantifying Uncertainties in Ocean Predictions , 2006 .

[48]  Timothy J. Robinson,et al.  Sequential Monte Carlo Methods in Practice , 2003 .

[49]  Kirsten Morris,et al.  Control of Systems Governed by Partial Differential Equations , 2018, The Control Systems Handbook.

[50]  J. Whitaker,et al.  Ensemble Data Assimilation without Perturbed Observations , 2002 .

[51]  Jeffrey L. Anderson,et al.  A Monte Carlo Implementation of the Nonlinear Filtering Problem to Produce Ensemble Assimilations and Forecasts , 1999 .

[52]  Jorma Rissanen.  Optimal Estimation , 2011, ALT.

[53]  H. Sorenson,et al.  Nonlinear Bayesian estimation using Gaussian sum approximations , 1972 .

[54]  G. Evensen.  Data Assimilation: The Ensemble Kalman Filter , 2006 .

[55]  G. Casella,et al.  Statistical Inference , 2003, Encyclopedia of Social Network Analysis and Mining.

[56]  David J. C. MacKay,et al.  Information Theory, Inference, and Learning Algorithms , 2004, IEEE Transactions on Information Theory.

[57]  J. Lions.  Optimal Control of Systems Governed by Partial Differential Equations , 1971 .

[58]  Dick Dee,et al.  On the choice of variable for atmospheric moisture analysis , 2022 .

[59]  Hernan G. Arango,et al.  A comprehensive ocean prediction and analysis system based on the tangent linear and adjoint of a regional ocean model , 2004 .

[60]  G. Schwarz.  Estimating the Dimension of a Model , 1978 .

[61]  A.H. Haddad,et al.  Applied optimal estimation , 1976, Proceedings of the IEEE.

[62]  John G. Proakis,et al.  Probability, random variables and stochastic processes , 1985, IEEE Trans. Acoust. Speech Signal Process..

[63]  Andrew F. Bennett,et al.  Inverse Methods in Physical Oceanography: Frontmatter , 1992 .

[64]  D. Pham.  Stochastic Methods for Sequential Data Assimilation in Strongly Nonlinear Systems , 2001 .

[65]  M. Bocquet,et al.  Beyond Gaussian Statistical Modeling in Geophysical Data Assimilation , 2010 .

[66]  Keston W. Smith.  Cluster ensemble Kalman filter , 2007 .

[67]  R. Ghanem,et al.  Stochastic Finite Elements: A Spectral Approach , 1990 .

[68]  Pierre F. J. Lermusiaux,et al.  Uncertainty estimation and prediction for interdisciplinary ocean dynamics , 2006, J. Comput. Phys..

[69]  Charles M. Grinstead,et al.  Introduction to probability , 1999, Statistics for the Behavioural Sciences.

[70]  Geoffrey J. McLachlan,et al.  Finite Mixture Models , 2019, Annual Review of Statistics and Its Application.

[71]  Laura Dovera,et al.  Multimodal ensemble Kalman filtering using Gaussian mixture models , 2011 .

[72]  Pierre F. J. Lermusiaux,et al.  Adaptive modeling, adaptive data assimilation and adaptive sampling , 2007 .

[73]  P. Marsaleix,et al.  Space-time structure and dynamics of the forecast error in a coastal circulation model of the Gulf of Lions , 2003 .

[74]  Jun S. Liu,et al.  Mixture Kalman filters , 2000 .

[75]  D. Rubin,et al.  Maximum likelihood from incomplete data via the EM - algorithm plus discussions on the paper , 1977 .