Abstract
Natural and artificial dynamical systems in the real world often have dynamics at multiple time scales. Such dynamics can contribute substantially to the complexity of a dynamical system and increase the difficulty with which it can be analyzed. Although evolutionary algorithms have been proposed that are amenable to the automated modeling of dynamical systems, none have explicitly taken into account multiple time scales or leveraged the information about these dynamics that is inherent in experimental observations. We propose a hybrid approach to the design of models for multiple-time-scale dynamical systems that combines an evolutionary algorithm with other metaheuristics and conventional nonlinear regression. With only minimal human-supplied domain knowledge, the algorithm automates the process of analyzing raw experimental observations and creating an interpretable symbolic model of the system under study. We describe the algorithm in detail and demonstrate its applicability to a variety of both physical and simulated systems. In addition, we study the performance and scalability of the algorithm under different types of dynamics, varying levels of experimental noise, and other factors relevant to the practical application of the algorithm.
Similar content being viewed by others
References
Akansu AN, Haddad PR (2000) Multiresolution signal decomposition: transforms, subbands, and wavelets. Academic Press, Waltham
Argemà A, Saurina J (2007) Study of the degradation of 5-azacytidine as a model of unstable drugs using a stopped-flow method and further data analysis with multivariate curve resolution. Talanta 74:176–182
Beisler JA (1978) Isolation, characterization, and properties of a labile hydrolysis product of the antitumor nucleoside, 5-azacytidine. J Med Chem 21:204–208
Bishop CM (2006) Pattern recognition and machine learning. Springer, London
Bongard JC, Lipson H (2007) Automated reverse engineering of nonlinear dynamical systems. Proc Natl Acad Sci USA 104:9943–9948
Borcard D, Legendre P, Avois-Jacquet C, Tuomisto H (2004) Dissecting the spatial structure of ecological data at multiple scales. Ecology 85:1826–1832
Brameier MF, Banzhaf W (2007) Linear genetic programming. Springer, New York
Chen W, Fish J (2001) A dispersive model for wave propagation in periodic heterogeneous media based on homogenization with multiple spatial and temporal scales. J Appl Mech 68:153–161
Chen WW, Niepel M, Sorger PK (2010) Classic and contemporary approaches to modeling biochemical reactions. Genes Dev 24:1861–1875
Chung J, Jung D, Yoo HH (2004) Stability analysis for the flapwise motion of a cantilever beam with rotary oscillation. J Sound Vib 273:1047–1062
Clery D, Voss D (2005) All for one and one for all. Science 308:809
Cornforth TW, Lipson H (2012) In: proceedings of the genetic and evolutionary computation conference. Symbolic regression of multiple-time-scale dynamical systems, Philadelphia, USA, 2012, pp 735–742
DeJong KA (2006) Evolutionary computation: a unified approach. MIT Press, Cambridge
Deng L, Trepat X, Butler JP, Millet E, Morgan KG, Weitz DA, Fredberg JJ (2006) Fast and slow dynamics of the cytoskeleton. Nat Mater 5:636–640
Draper NR, Smith H (1998) Applied regression analysis. Wiley, New York
Evans J, Rzhetsky A (2010) Machine science. Science 329:399–400
Guven A (2009) Linear genetic programming for time-series modeling of daily flow rate. J Earth Syst Sci 118:137–146
Harris-Warrick RM, Flamm RE (1987) Multiple mechanisms of bursting in a conditional bursting neuron. J Neurosci 7:2113–2128
Henzler-Wildman KA, Lei M, Thai V, Kerns SJ, Karplus M, Kern D (2007) A hierarchy of timescales in protein dynamics is linked to enzyme catalysis. Nature 450:913–916
Hornby GS (2006) In: proceedings of the genetic and evolutionary computation conference. ALPS: the age-layered population structure for reducing the problem of premature convergence, New York, 206, pp 815–822
Iba H, de Garis H, Sato T (1994), In Davidor Y, Schwefel H-P, Männer R (eds) proceedings of the PPSN III. Genetic programming with local hill-climbing, Springer, London, 1994, pp 302–311
Jara EC (2011) Long memory time series forecasting by using genetic programming. Genet Program Evol Mach 12:429–456
Jones CKRT (2001) Multiple-time-scale dynamical systems. Springer, New York
Julier S, Uhlmann J, Durrant-Whyte HF (2000) A new method for the nonlinear transformation of means and covariances in filters and estimators. IEEE Trans Automat Control 45:477–482
King RD, Whelan KE, Jones FM, Reiser PGK, Bryant CH, Muggleton SH, Kell DB, Oliver SG (2004) Functional genomic hypothesis generation and experimentation by a robot scientist. Nature 427:247–252
King RD, Rowland J, Oliver SG, Young M, Aubrey W, Byrne E, Liakata M, Markham M, Pir P, Soldatova LN, Sparkes A, Whelan KE, Clare A (2009) The automation of science. Science 324:85–89
Klein R (2001) Asymptotic adaptive methods for multi-scale problems in fluid mechanics. J Eng Math 39:261–343
Koza JR (1992) Genetic programming: on the programming of computers by means of natural selection. MIT Press, Cambridge
Koza JR, Bennett FH, Andre D, Keane MA (1999) Genetic programming III: Darwinian invention and problem solving. Morgan Kaufmann, San Francisco
Langley P, Simon HA, Bradshaw G, Zytkow JM (1987) Scientific discovery: computational exploration of the creative processes. MIT Press, Cambridge
Lawlor FD (1973) MFIT: a multiple nonlinear curve fitting technique. IBM Poughkeepsie laboratory technical report TR 00.2482
Le Pourhiet A, Corrège M, Caruana D (2003) Control of self-oscillating systems. IEEE Proc Control Theory Appl 150:599–610
Lee CH, Othmer HG (2009) A multi-time-scale analysis of chemical reaction networks: I Deterministic systems. J Math Biol 60:387–450
Mahfoud SW (1992), In: Männer R, Manderick R (eds) parallel problem solving from nature—PPSN-II. Crowding and preselection revisited, Elsevier
Mulloy BS, Riolo RL, Savit RS (1996) In: Genetic programming 1996: proceedings of the first annual conference. Dynamics of genetic programming and chaotic time series prediction, pp 166–174
Nocedal J, Wright SJ (2006) Numerical optimization. Springer, New York
Palsson BO (1987) On the dynamics of the irreversible Michaelis-Menten reaction mechanism. Chem Eng Sci 42:447–458
Pandolfi JM (2002) Coral community dynamics at multiple scales. Coral Reefs 21:13–23
Russell S, Norvig P (2009) Artificial intelligence: a modern approach, 3rd edn. Prentice Hall, Upper Saddle River
Sakamoto E, Iba H (2001) In: proceedings of the 2001 congress on evolutionary computation. Inferring a system of differential equations for a gene regulatory network by using genetic programming. pp 720–726
Schmidt MD, Lipson H (2007) In: proceedings of the genetic and evolutionary computation conference 2007. Comparison of tree and graph encodings as a function of problem complexity. pp 1674–1679
Schmidt MD, Lipson H (2008) Coevolution of fitness predictors. IEEE Trans Evol Comp. 12:736–749
Schmidt MD, Lipson H (2009) Distilling free-form natural laws from experimental data. Science 324:81–85
Schmidt MD, Lipson H (2010) In: proceedings of the genetic and evolutionary computation conference 2010. Predicting solution rank to improve performance. pp 949–956
Schmidt MD, Lipson H (2010) Age-fitness Pareto optimization. Genet Program Theory Pract 8:129–146
Schmidt MD, Vallabhajosyula RR, Jenkins JW, Hood JE, Soni AS, Wikswo JP, Lipson H (2011) Automated refinement and inference of analytical models for metabolic networks. Phys Biol 8:055011
Strogatz SH (2001) Exploring complex networks. Nature 410:268–276
Szalay A, Gray J (2006) 2020 Computing: science in an exponential world. Nature 440:413–414
Verhulst F (2005) Methods and applications of singular perturbations: boundary layers and multiple timescale dynamics. Springer, New York
Wagner N, Michalewicz Z, Khouja M, McGregor RR (2007) Time series forecasting for dynamic environments: the DyFor genetic program model. IEEE Trans Evolut Comput 11:433–452
Waltz D, Buchanan BG (2009) Automating science. Science 324:43–44
Acknowledgments
Support was provided by the Tri-Institutional Training Program in Computational Biology and Medicine, US National Science Foundation grant ECCS 0941561 on Cyber-enabled Discovery and Innovation (CDI), US National Institutes of Health NIDA grant RC2 DA028981, and the US Defense Threat Reduction Agency (DTRA) grant HDTRA 1-09-1-0013.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Cornforth, T.W., Lipson, H. A hybrid evolutionary algorithm for the symbolic modeling of multiple-time-scale dynamical systems. Evol. Intel. 8, 149–164 (2015). https://doi.org/10.1007/s12065-015-0126-x
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12065-015-0126-x