Forecasting and Uncertainty Quantification Using a Hybrid of Mechanistic and Non-mechanistic Models for an Age-Structured Population Model

In this paper, we present a new method for the prediction and uncertainty quantification of data-driven multivariate systems. Traditionally, either mechanistic or non-mechanistic modeling methodologies have been used for prediction; however, it is uncommon for the two to be incorporated together. We compare the forecast accuracy of mechanistic modeling, using Bayesian inference, a non-mechanistic modeling approach based on state space reconstruction, and a novel hybrid methodology composed of the two for an age-structured population data set. The data come from cannibalistic flour beetles, in which it is observed that the adults preying on the eggs and pupae result in non-equilibrium population dynamics. Uncertainty quantification methods for the hybrid models are outlined and illustrated for these data. We perform an analysis of the results from Bayesian inference for the mechanistic model and hybrid models to suggest reasons why hybrid modeling methodology may enable more accurate forecasts of multivariate systems than traditional approaches.

[1]  S. Billings.  Nonlinear System Identification: NARMAX Methods in the Time, Frequency, and Spatio-Temporal Domains , 2013 .

[2]  Farmer,et al.  Predicting chaotic time series. , 1987, Physical review letters.

[3]  Balaji Rajagopalan,et al.  Local polynomial method for ensemble forecast of time series , 2005 .

[4]  Brian Dennis,et al.  Chaotic Dynamics in an Insect Population , 1997, Science.

[5]  Nicolette Meshkat,et al.  On Finding and Using Identifiable Parameter Combinations in Nonlinear Dynamic Systems Biology Models and COMBOS: A Novel Web Implementation , 2014, PloS one.

[6]  Ursula Klingmüller,et al.  Structural and practical identifiability analysis of partially observed dynamical models by exploiting the profile likelihood , 2009, Bioinform..

[7]  Jing Gao,et al.  Multistep-Ahead Time Series Prediction , 2006, PAKDD.

[8]  Jens Timmer,et al.  Handbook of time series analysis : recent theoretical developments and applications , 2006 .

[9]  George Sugihara,et al.  Model-free forecasting outperforms the correct mechanistic model for simulated and experimental data , 2013, Proceedings of the National Academy of Sciences.

[10]  Jens Timmer,et al.  Handbook of Time Series Analysis , 2006 .

[11]  Joseph J. DiStefano,et al.  Dynamic Systems Biology Modeling and Simulation , 2015 .

[12]  Kevin B. Flores,et al.  Hybrid modeling and prediction of dynamical systems , 2017, PLoS Comput. Biol..

[13]  Ovide Arino,et al.  Mathematical modelling of the intravenous glucose tolerance test , 2000, Journal of mathematical biology.

[14]  H. T. Banks,et al.  A sensitivity matrix based methodology for inverse problem formulation , 2020, 2004.06831.

[15]  Florian Hartig,et al.  Does model-free forecasting really outperform the true model? , 2013, Proceedings of the National Academy of Sciences.

[16]  Richard L. Smith,et al.  PREDICTIVE INFERENCE , 2004 .

[17]  Mette S Olufsen,et al.  A practical approach to parameter estimation applied to model predicting heart rate regulation , 2013, Journal of mathematical biology.

[18]  Guo Yuan,et al.  Estimating the predictability of an oceanic time series using linear and nonlinear methods , 2004 .

[19]  Harvey Thomas Banks,et al.  Modeling and Inverse Problems in the Presence of Uncertainty , 2014 .

[20]  George Sugihara,et al.  Nonlinear forecasting for the classification of natural time series , 1994, Philosophical Transactions of the Royal Society of London. Series A: Physical and Engineering Sciences.

[21]  Kevin Flores,et al.  Uncertainty quantification in modeling HIV viral mechanics. , 2015, Mathematical biosciences and engineering : MBE.

[22]  H. T. Banks,et al.  Model comparison tests to determine data information content , 2015, Appl. Math. Lett..

[23]  H. T. Banks,et al.  Optimal design of non-equilibrium experiments for genetic network interrogation , 2015, Applied Mathematics Letters.

[24]  Jiménez,et al.  Forecasting on chaotic time series: A local optimal linear-reconstruction method. , 1992, Physical review. A, Atomic, molecular, and optical physics.

[25]  George Sugihara,et al.  Detecting Causality in Complex Ecosystems , 2012, Science.

[26]  Ralph C. Smith,et al.  Uncertainty Quantification: Theory, Implementation, and Applications , 2013 .

[27]  Leonard A. Smith.  Identification and prediction of low dimensional dynamics , 1992 .

[28]  George Sugihara,et al.  Nonlinear forecasting as a way of distinguishing chaos from measurement error in time series , 1990, Nature.

[29]  R. Costantino,et al.  NONLINEAR DEMOGRAPHIC DYNAMICS: MATHEMATICAL MODELS, STATISTICAL METHODS, AND BIOLOGICAL EXPERIMENTS' , 1995 .

[30]  Christopher C. Strelioff,et al.  Medium-term prediction of chaos. , 2006, Physical review letters.

[31]  C. Cobelli,et al.  Parameter and structural identifiability concepts and ambiguities: a critical review and analysis. , 1980, The American journal of physiology.

[32]  Ian P. Woiwod,et al.  Estimating Chaos in an Insect Population , 1997 .

[33]  Amir F. Atiya,et al.  Multi-step-ahead prediction using dynamic recurrent neural networks , 1999, IJCNN'99. International Joint Conference on Neural Networks. Proceedings (Cat. No.99CH36339).

[34]  George Sugihara,et al.  Distinguishing random environmental fluctuations from ecological catastrophes for the North Pacific Ocean , 2005, Nature.

[35]  Martin Casdagli,et al.  Nonlinear prediction of chaotic time series , 1989 .

[36]  James A. Yorke,et al.  Predicting Chaos Most of the Time from Embeddings with Self-Intersections , 1998 .

[37]  Jürgen Kurths,et al.  Nonlinear Dynamical System Identification from Uncertain and Indirect Measurements , 2004, Int. J. Bifurc. Chaos.

[38]  J. Renwick,et al.  Quantifying annual variation in catchability for commercial and research fishing , 2003 .

[39]  Tyrus Berry,et al.  Ensemble Kalman Filtering without a Model , 2016 .

[40]  Heikki Haario,et al.  DRAM: Efficient adaptive MCMC , 2006, Stat. Comput..

[41]  George Sugihara,et al.  Equation-free mechanistic ecosystem forecasting using empirical dynamic modeling , 2015, Proceedings of the National Academy of Sciences.

[42]  O. Lingjærde,et al.  Regularized local linear prediction of chaotic time series , 1998 .