We successfully applied a tool for automated equation discovery to the real-world practically relevant problem of modeling the dynamics of phytoplankton in a lake. We built a model of the dynamics of phytoplankton in Lake Glumsoe, Denmark. To this end, we used data on characteristic lake parameters, collected over a period of two years, as well as a library of domain knowledge for modeling lake ecosystems. The model of lake Glumsoe was successfully validated on data that were not used for the construction of the model.
F.17 Transfer of existing technologies, know-how, methods and procedures into practice
COBISS.SI-ID: 21313063We present the results of the analysis of outputs from an individual-based model in agriculture with machine learning. Individual-based models are becoming increasingly popular in agriculture, where they are used for modeling different types of plant populations. We present a new individual-based model for simulating the dynamics of a transgene within oilseed rape populations. We use the output from this model to develop equation-based models of the oilseed rape (OSR) population dynamics in a single arable field with the equation discovery system Lagramge.
F.17 Transfer of existing technologies, know-how, methods and procedures into practice
COBISS.SI-ID: 23020327We organized the Third and Fourth Workshop on Machine Learning in Systems Biology (MLSB-09, MLSB-10) in Ljubljana and Edinburgh. We also co-chaired the program committees for both events. The workshop is a highly reputed event with high quality invited speakers and reviewed contributions that attracts more than 60 participants. Papers presented at the workshop were published in proceedings. At the workshops members of the project team also presented the results of their work on EU projects EETP and PHAGOSYS.
B.02 Presiding over the programming board of a conference
COBISS.SI-ID: 24513831Two entries in the first comprehensive encyclopedia in the scientific field of machine learning provide introductions to equation discovery and inductive process modeling. Both tasks are directly related to the work performed within the project and the articles are based on some of the results achieved within the project. Entries have a high impact potential, since the encyclopedia provides a first comprehensive, expository, and tutorial overview of the machine learning field targeted at a wide audience of computing experts, as well as professionals from other domains.
F.17 Transfer of existing technologies, know-how, methods and procedures into practice
COBISS.SI-ID: 3552686We have started applying equation discovery methods and in particular methods for inductive process modeling, which allow for the use of domain knowledge, to practical problems in the area of systems biology and ecology. This includes the formulation of libraries of domain knowledge about biological reactions and their use together with measured data to discover the structure and dynamics of biological and ecological networks. Examples of successful use include the modeling of aquatic ecosystems (lakes and oceans) and cellular processes (glycolisis, endocytosis).
F.17 Transfer of existing technologies, know-how, methods and procedures into practice
COBISS.SI-ID: 22059815