Seminars of the Focus Area Complex Systems

Prof. Dr. C. Beta, Prof. Dr. K. Dethloff, Prof. Dr. R. Engbert, Prof. Dr. M. Holschneider, Prof. Dr. W. Huisinga, Prof. Dr. Ralf Metzler, Prof. Dr. A. Pikovsky, Prof. Dr. S. Reich, Prof. Dr. M. Rosenblum, Prof. Dr. G. Rüdiger, Prof. Dr. T. Scheffer, Prof. Dr. F. Scherbaum, Prof. Dr. J. Selbig, Prof. Dr. F. Spahn

Seminar

Speaker: Joern Malich, Institute of Physics and Astronomy, University of Potsdam

Title: Modelling and Prediction of Dynamical Systems using Machine Learning * Oberseminar Nichtlineare Dynamik

Time: Mon, Apr 27, 2015, 14:00

Place: bldg 28, room 2.100

Abstract:
We present a methodological approach to model and predict dynamical systems using machine learning algorithms. We apply our method to the problem of power production of regenerative energy sources. There, due to the multiscaling aspect of turbulent systems and noisiness of data, a derivation of approximate equations from basic principles is not possible, and numerical solution is prohibitively expensive. On the other hand machine learning techniques have been successfully employed in many physical situations. It follows the learn-from-past paradigm and trains a model based on dataset from the past. These methods often lack interpretability. That's why it is essential to develop models with high predictive power, but comprehensible at the same time. In this talk, we focus on modern techniques of machine learning, like regression with Gaussian processes and symbolic regression, which can further be used for dynamical system's analysis. Results are demonstrated on the example of power production of solar energy plants.

Back to the seminar schedule



Past NLD Seminars (1994-2007) & (2008 ...)

Students' seminar: Theoretical Physics, PIK, Modeling & TSA Berlin-Potsdam-Colloquia: PhysGesellschaft Berlin, TU Berlin, Pro Physik, AIP, AEI, MPI-KGF, GFZ, HMI, PIK, AWI, Max Planck Institute for the History of Science, Mathematik, DPG Disputationen, & Vorschau UP

Udo Schwarz, Zentrum für Dynamik komplexer Systeme,
Universität Potsdam, Campus Golm Karl-Liebknecht-Str. 24, 14476 Potsdam, building 28, room 2.107
Phone: (+49-331) 977-1658, Fax : (+49-331) 977-1045

Email: Udo.Schwarz AT uni-potsdam.de

DFG SFB 1294

DFG Sonderforschungsbereich 1294 Data assimilation

DFG SPP 1488

DFG Schwerpunktprogramm 1488 Planetmag


News: odeint C++ library

Check out boost::odeint – our fast and flexible C++ library for integrating differential equations!