MPŠ MP&Scaron MP&Scaron MP&Scaron Avtorji

Jožef Stefan
Postgraduate School

Jamova 39
SI-1000 Ljubljana

Phone: +386 1 477 31 00
Fax: +386 1 477 31 10


Course Description

Automated Modeling of Dynamic Systems with Ecological Applications


Ecotechnologies, third-level study programme


prof. dr. Sašo Džeroski


The course objective is to familiarize the student with the field of automated modeling of dynamic systems, including basic concepts and state of the art methods.

The competencies of the students successfully completing this course will include the understanding of basic concepts from the field, familiarity with the state-of-the art methods, and capability of independent use of the methods in new practical projects of modeling ecological and environmental systems.


Introduction: Modeling dynamic systems
State-space and input-output models
Discrete and continuous-time models
Parametric and non-parametric models
Qualitative and quantitative models
Reasoning with parametric models
Parameter fitting/ identification
Structure identification
Learning nonparametric discrete time models
Learning process-based models
Representation: Entities, Processes, Libraries
Learning methods: LAGRAMGE, ProBMoT
Case studies in automated modeling of
aquatic ecosystems and epidemiology

Course literature:

Selected chapters from the following books:
• Mobus, G.E., and Kalton, M.C. Principles of Systems Science. Springer, 2015.
• Joergensen, S.E., and Fath, B. Fundamentals of Ecological Modelling: Applications in Environmental Management and Research. Elsevier, 2011.
• Džeroski S., and Todorovski L., editors. Computational Discovery of Scientific Knowledge: Introduction, Techniques, and Applications in Environmental and Life Sciences. Springer, 2007.
• Murray, J.D. Mathematical Biology. Part I: Introduction. Springer, 2002.

Significant publications and references:

Aleksovski, D., Kocijan, J., and Džeroski, S. (2015). Model-tree ensembles for noise-tolerant system identification. Advanced Engineering Informatics, 29(1): 1-15. DOI: 10.1016/j.aei.2014.07.008

Simidjievski, N., Todorovski, L., and Džeroski, S. (2015). Learning ensembles of population dynamics models and their application to modelling aquatic ecosystems. Ecological Modelling, 306: 305-317. DOI: 10.1016/j.ecolmodel.2014.08.019

Simidjievski, N., Todorovski, L., and Džeroski, S. (2015). Predicting long-term population dynamics with bagging and boosting of process-based models. Expert Systems with Applications, 42(22): 8484-8496. DOI: 10.1016/j.eswa.2015.07.004

Škerjanec, M., Atanasova, N., Čerepnalkoski, D., Džeroski, S., and Kompare, B. (2014). Development of a knowledge library for automated watershed modeling. Environmental Modelling and Software, 54: 60-72.
DOI: 10.1016/j.envsoft.2013.12.017

Taškova, K., Šilc, J., Atanasova, N., and Džeroski, S. (2012). Parameter estimation in a nonlinear dynamic model of an aquatic ecosystem with meta-heuristic optimization. Ecological Modelling, 226(1): 36-61. DOI: 10.1016/j.ecolmodel.2011.11.029

Čerepnalkoski, D., Taškova, K., Todorovski, L., Atanasova, N., and Džeroski, S. (2012). The influence of parameter fitting methods on model structure selection in automated modeling of aquatic ecosystems. Ecological Modelling, 245: 136-166. DOI: 10.1016/j.ecolmodel.2012.06.001


• oral exam (50%)
• seminar work with oral defense (50%)

Students obligations:

• oral exam
• seminar work with oral defense