Abstract
In this chapter, we focus on the equation discovery task, i.e., the task of inducing models based on algebraic and ordinary differential equations from measured and observed data. We propose a methodology for integrating domain knowledge in the process of equation discovery. The proposed methodology transforms the available domain knowledge to a grammar specifying the space of candidate equation-based models. We show here how various aspects of knowledge about modeling dynamic systems in a particular domain of interest can be transformed to grammars. Thereafter, the equation discovery method Lagramge can search through the space of models specified by the grammar and find ones that fit measured data well. We illustrate the utility of the proposed methodology on three modeling tasks from the domain of Environmental sciences. All three tasks involve establishing models of real-world systems from noisy measurement data.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Bendoricchio, G., Coffaro, G., DeMarchi, C.: A trophic model for Ulva Rigida in the Lagoon of Venice. Ecological Modelling 75/76, 485–496 (1994)
Bunch, D.S., Gay, D.M., Welsch, R.E.: Algorithm 717; subroutines for maximum likelihood and quasi-likelihood estimation of parameters in nonlinear regression models. ACM Transactions on Mathematical Software 19, 109–130 (1993)
Chomsky, N.: Three models for the description of language. IRE Transactions on Information Theory 2, 113–124 (1956)
Coffaro, G., Carrer, G., Bendoricchio, G.: Model for Ulva Rigida growth in the Lagoon of Venice (Technical Report). University of Padova, Padova, Italy. UNESCO MURST Project: Venice Lagoon Ecosystem (1993)
Džeroski, S., Todorovski, L.: Discovering dynamics: from inductive logic programming to machine discovery. Journal of Intelligent Information Systems 4, 89–108 (1995)
Falkenheiner, B., Forbus, K.D.: Compositional modeling: Finding the right model for the job. Artificial Intelligence 51, 95–143 (1991)
Forbus, K.D.: Qulitative process theory. Artificial Intelligence 24, 85–168 (1984)
Giordano, F.R., Weir, M.D., Fox, W.P.: A first course in mathematical modeling. 2nd edn. Brooks/Cole Publishing Company, Pacific Grove (1997)
Hopcroft, J.E., Ullman, J.D.: Introduction to automata theory, languages and computation. Addison-Wesley, Reading (1979)
Kokar, M.M.: Determining arguments of invariant functional descriptions. Machine Learning 4, 403–422 (1986)
Kompare, B., Džeroski, S.: Getting more out of data: automated modelling of algal growth with machine learning. In: Proceedings of the International symposium on coastal ocean space utilisation, Yokohama, Japan, pp. 209–220 (1995)
Križman, V.: Avtomatsko odkrivanje strukture modelov dinamičnih sistemov. Doctoral dissertation, Faculty of computer and information science, University of Ljubljana, Ljubljana, Slovenia. In Slovene (1998)
Langley, P., Sanchez, J., Todorovski, L., Džeroski, S.: Inducing process models from continuous data. In: Proceedings of the Fourteenth International Conference on Machine Learning, pp. 347–354. Morgan Kaufmann, Sidney, Australia (2002)
Langley, P., Simon, H., Bradshaw, G.: Heuristics for empirical discovery. In: Computational models of learning, pp. 21–54. Springer, Heidelberg (1987)
Langley, P., Żytkow, J.: Data-driven approaches to empirical discovery. Artificial Intelligence 40, 283–312 (1989)
Lavrač, N., Džeroski, S.: Inductive logic programming: Techniques and applications. Ellis Horwood, Chichester (1994), available for download at http://www-ai.ijs.si/SasoDzeroski/ILPBook/
Mitchell, T.M.: The need for biases in learning generalizations. In: Readings in machine learning, pp. 184–191. Morgan Kaufmann, San Mateo, CA (1991)
Murray, J.D.: Mathematical biology, 2nd corrected edn. Springer, Heidelberg (1993)
Nédellec, C., Rouveirol, C., Adé, H., Bergadano, F., Tausend, B.: Declarative bias in ILP. In: Raedt, L.D. (ed.) Advances in inductive logic programming, pp. 82–103. IOS Press, Amsterdam, The Netherlands (1996)
Ourston, D., Mooney, R.J.: Theory refinement combining analytical and empirical methods. Artificial Intelligence 66, 273–309 (1994)
Pazzani, M., Kibler, D.: The utility of background knowledge in inductive learning. Machine Learning 9, 57–94 (1992)
Pazzani, M.J., Mani, S., Shankle, W.R.: Acceptance of rules generated by machine learning among medical experts. Methods of Information in Medicine 40, 380–385 (2001)
Potter, C.S., Klooster, S.A.: Global model estimates of carbon and nitrogen storage in litter and soil pools: Response to change in vegetation quality and biomass allocation. Tellus 49B, 1–17 (1997)
Quinlan, J.R.: C4.5: Programs for machine learning. Morgan Kaufmann, San Mateo (1993)
Robertson, D., Bundy, A., Muetzelfield, R., Haggith, M., Uschold, M.: Eco-logic: logic-based approaches to ecological modelling. MIT Press, Cambridge (1991)
Salles, P., Bredeweg, B.: Qualitative reasoning about population and community ecology. AI Magazine 24, 77–90 (2003)
Todorovski, L.: Using domain knowledge for automated modeling of dynamic systems with equation discovery. Doctoral dissertation, Faculty of computer and information science, University of Ljubljana, Slovenia (2003)
Todorovski, L., Džeroski, S.: Declarative bias in equation discovery. In: Proceedings of the Fourteenth International Conference on Machine Learning, pp. 376–384. Morgan Kaufmann, San Mateo (1997)
Todorovski, L., Džeroski, S.: Theory revision in equation discovery. In: Proceedings of the Fourth International Conference on Discovery Science, pp. 389–400. Springer, Heidelberg (2001a)
Todorovski, L., Džeroski, S.: Using domain knowledge on population dynamics modeling for equation discovery. In: Proceedings of the Twelfth European Conference on Machine Learning, pp. 478–490. Springer, Heidelberg (2001b)
Todorovski, L., Džeroski, S., Kompare, B.: Modelling and prediction of phytoplankton growth with equation discovery. Ecological Modelling 113, 71–81 (1998)
Towell, G.G., Shavlik, J.W.: Knowledge-based artificial neural networks. Artificial Intelligence 70, 119–165 (1994)
Utgoff, P.E.: Shift of bias for inductive concept learning. In: Machine learning: An artificial intelligence approach — vol. 2, pp. 107–148. Morgan Kaufmann, San Mateo, CA (1986)
Voit, E.O.: Computational analysis of biochemical systems. Cambridge University Press, Cambridge, UK (2000)
Washio, T., Motoda, H.: Discovering admissible models of complex systems based on scale-types and identity constraints. In: Proceedings of the Fifteenth International Joint Conference on Artificial Intelligence, pp. 810–817. Morgan Kaufmann, San Mateo, CA (1997)
Whigham, P.A., Recknagel, F.: Predicting chlorophyll-a in freshwater lakes by hybridising process-based models and genetic algorithms. Ecological Modelling 146, 243–251 (2001)
Williams, R.J., Zipser, D.: A learning algorithm for continually running fully recurrent neural networks. Neural Computation 1, 270–280 (1989)
Wrobel, S.: First order theory refinement. In: Raedt, L.D. (ed.) Advances in inductive logic programming, pp. 14–33. IOS Press, Amsterdam, The Netherlands (1996)
Zembowicz, R., Żytkow, J.M.: Discovery of equations: Experimental evaluation of convergence. In: Proceedings of the Tenth National Conference on Artificial Intelligence, pp. 70–75. Morgan Kaufmann, San Mateo (1992)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2007 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Todorovski, L., Džeroski, S. (2007). Integrating Domain Knowledge in Equation Discovery. In: Džeroski, S., Todorovski, L. (eds) Computational Discovery of Scientific Knowledge. Lecture Notes in Computer Science(), vol 4660. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-73920-3_4
Download citation
DOI: https://doi.org/10.1007/978-3-540-73920-3_4
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-73919-7
Online ISBN: 978-3-540-73920-3
eBook Packages: Computer ScienceComputer Science (R0)