Supermodeling: The Next Level of Abstraction in the Use of Data Assimilation

Data assimilation (DA) is a key procedure that synchronizes a computer model with real observations. However, in the case of overparametrized complex systems modeling, the task of parameter-estimation through data assimilation can expand exponentially. It leads to unacceptable computational overhead, substantial inaccuracies in parameter matching, and wrong predictions. Here we define a Supermodel as a kind of ensembling scheme, which consists of a few sub-models representing various instances of the baseline model. The sub-models differ in parameter sets and are synchronized through couplings between the most sensitive dynamical variables. We demonstrate that after a short pretraining of the fully parametrized small sub-model ensemble, and then training a few latent parameters of the low-parameterized Supermodel, we can outperform in efficiency and accuracy the baseline model matched to data by a classical DA procedure.

[1]  Marc Bocquet,et al.  Data Assimilation: Methods, Algorithms, and Applications , 2016 .

[2]  Michael P. H. Stumpf,et al.  Simulation-based model selection for dynamical systems in systems and population biology , 2009, Bioinform..

[3]  Sebastian Reich,et al.  Data assimilation: The Schrödinger perspective , 2018, Acta Numerica.

[4]  Paul Marjoram,et al.  Markov chain Monte Carlo without likelihoods , 2003, Proceedings of the National Academy of Sciences of the United States of America.

[5]  Paola Annoni,et al.  Variance based sensitivity analysis of model output. Design and estimator for the total sensitivity index , 2010, Comput. Phys. Commun..

[6]  E. Kalnay,et al.  Methodological and Ideological Options Human and nature dynamics ( HANDY ) : Modeling inequality and use of resources in the collapse or sustainability of societies , 2014 .

[7]  Wim Wiegerinck,et al.  On the Limit of Large Couplings and Weighted Averaged Dynamics , 2013 .

[8]  N. Keenlyside,et al.  Role of atmosphere-ocean interactions in supermodeling the tropical Pacific climate. , 2017, Chaos.

[9]  W. Wiegerinck,et al.  Attractor learning in synchronized chaotic systems in the presence of unresolved scales. , 2017, Chaos.

[10]  J. Møller.  Discussion on the paper by Feranhead and Prangle , 2012 .

[11]  Wim Wiegerinck,et al.  A multi-model ensemble method that combines imperfect models through learning , 2010 .

[12]  D. Crisan,et al.  Fundamentals of Stochastic Filtering , 2008 .

[13]  Nando de Freitas,et al.  An Introduction to MCMC for Machine Learning , 2004, Machine Learning.

[14]  Eugenia Kalnay,et al.  Atmospheric Modeling, Data Assimilation and Predictability , 2002 .

[15]  Gregory S. Duane,et al.  Synchronicity from Synchronized Chaos , 2011, Entropy.

[16]  Keshav Pingali,et al.  Supermodeling of tumor dynamics with parallel isogeometric analysis solver , 2019, ArXiv.

[17]  Christian P. Robert,et al.  Componentwise approximate Bayesian computation via Gibbs-like steps , 2019, Biometrika.

[18]  Simo Srkk,et al.  Bayesian Filtering and Smoothing , 2013 .

[19]  Witold Dzwinel,et al.  Supermodeling in Simulation of Melanoma Progression , 2016, ICCS.

[20]  D. Shahsavani,et al.  Variance-based sensitivity analysis of model outputs using surrogate models , 2011, Environ. Model. Softw..

[21]  Witold Dzwinel,et al.  A concept of a prognostic system for personalized anti-tumor therapy based on supermodeling , 2017, ICCS.

[22]  Witold Dzwinel,et al.  Efficient model of tumor dynamics simulated in multi-GPU environment , 2018, Int. J. High Perform. Comput. Appl..

[23]  Ljupco Kocarev,et al.  Supermodeling by Combining Imperfect Models , 2011, FET.

[24]  Gregory S. Duane.  Data Assimilation as Artificial Perception and Supermodeling as Artificial Consciousness , 2013 .

[25]  Arnaud Doucet,et al.  An adaptive sequential Monte Carlo method for approximate Bayesian computation , 2011, Statistics and Computing.

[26]  Aki Vehtari,et al.  Efficient Acquisition Rules for Model-Based Approximate Bayesian Computation , 2017, Bayesian Analysis.

[27]  Mantas Lukosevicius,et al.  A Practical Guide to Applying Echo State Networks , 2012, Neural Networks: Tricks of the Trade.

[28]  Herbert Jaeger,et al.  Reservoir computing approaches to recurrent neural network training , 2009, Comput. Sci. Rev..

[29]  Marcin Sendera,et al.  Data adaptation in HANDY economy-ideology model , 2019, ArXiv.

[30]  M. Gutmann,et al.  Approximate Bayesian Computation , 2019, Annual Review of Statistics and Its Application.

[31]  I. Sobola,et al.  Global sensitivity indices for nonlinear mathematical models and their Monte Carlo estimates , 2001 .

[32]  Theodore Kypraios,et al.  A tutorial introduction to Bayesian inference for stochastic epidemic models using Approximate Bayesian Computation. , 2017, Mathematical biosciences.

[33]  Michael Ghil,et al.  Introduction to focus issue: Synchronization in large networks and continuous media-data, models, and supermodels. , 2017, Chaos.

[34]  Andrew Golightly,et al.  Ensemble MCMC: Accelerating Pseudo-Marginal MCMC for State Space Models using the Ensemble Kalman Filter , 2019, Bayesian Analysis.

[35]  Sebastian Reich,et al.  A mollified ensemble Kalman filter , 2010, 1002.3091.

[36]  Bozhkov Lachezar,et al.  Echo State Network , 2017, Encyclopedia of Machine Learning and Data Mining.

[37]  Gregory S Duane,et al.  Simulating climate with a synchronization-based supermodel. , 2017, Chaos.

[38]  Paul Fearnhead,et al.  Constructing summary statistics for approximate Bayesian computation: semi‐automatic approximate Bayesian computation , 2012 .

[39]  E. Ionides,et al.  Inference for dynamic and latent variable models via iterated, perturbed Bayes maps , 2015, Proceedings of the National Academy of Sciences.

[40]  Jan Hasenauer,et al.  pyABC: distributed, likelihood-free inference , 2017, bioRxiv.