Stream: Knowledge, Data and Semantic Processing for Environmental Research


G4. Machine learning for environmental data: concepts, applications, and software
Mikhail Kanevski, Alexei Pozdnoukhov, Vasily Demyanov

There is a growing demand for new analytical and processing environmental observation and monitor, analyse and to model spatio-temporal data streams. These tools can be provided by Machine Learning (ML), which is a general and powerful field for processing and nonlinear robust modelling of complex high dimensional data.

The workshop will present the basic concepts underlying a wide range of conventional ML algorithms and provide the cutting-edge data analysis, modelling and visualisation tools:

  • Artificial neural networks: multilayer perceptrons, radial basis function networks, general regression and probabilistic neural networks
  • Self-organizing Kohonen maps
  • Support vector machines and other kernel-based methods.

Real case studies from environmental a variety of problems, like pollution, climate, natural hazards, renewable resources and other fields of applications will be outlined focusing on the software tools used. The workshop will be useful both for the beginners and advanced researchers and users. Workshop deliverables are: tutorial slides, detailed "how-to-do-it" case studies, software tools, sample datasets.

Working Paper for further information.


G5. The future of semantic technologies in environmental research
Andrea E. Rizzoli, Sasa Nesic, Tomas Pariente-Lobo, Gerald Schimak

This "Semantics and the environment"-workshop and wants to develop a discussion on how environmental research will be impacted by semantic technologies in the near future. What are the challenges, where are the major obstacles, and what are the expected outcomes?

The output of the workshop should be a research agenda for the next four years, identifying the most promising application areas of semantics for environmental sciences. The workshop participants are welcomed to bring their own case studies to be discussed and analysed during the workshop short presentations.

Working Paper for further information.