Category: News

The Central Library of the Research Centre Jülich has elected “IntelliO3-ts v1.0: a neural network approach to predict near-surface ozone concentrations in Germany” by Felix Kleinert, Lukas H. Leufen, and Martin G. Schultz as the open access publication of the month.

The article “IntelliO3-ts v1.0: a neural network approach to predict near-surface ozone concentrations in Germany” by Felix Kleinert, Lukas H. Leufen, and Martin G. Schultz has been published in Geoscientific Model Development (GMD). The article is available from https://doi.org/10.5194/gmd-14-1-2021 under the Creative Commons Attribution 4.0 License.

The preprint of a paper on the machine learning workflow tool MLAir by Lukas Leufen et.al. is now in the public discussion phase. MLAir enables to easily build your custom workflow to train a machine learning algorithm on time series data. Check out the manuscript “MLAir (v1.0) – a tool to enable fast and flexible machine learning on air data time series” available at https://gmd.copernicus.org/preprints/gmd-2020-332/ or go straight to the code repository at https://gitlab.version.fz-juelich.de/toar/mlair and start your contribution.

The ozone situation in Germany -state of knowledge, research gaps and recommendations- was discussed at a workshop organized by the German Environment Agency (Umweltbundesamt) and the Institute for Advanced Sustainability Studies (IASS Potsdam) in November 2019. The documentation is now available at https://www.umweltbundesamt.de/publikationen/the-ozone-situation-in-germany

A preprint of the manuscript “IntelliO3-ts v1.0: A neural network approach to predict
near-surface ozone concentrations in Germany” by Felix Kleinert at. al. has been made available by the Geoscientific Model Development (GMD) journal. It can be accessed at https://gmd.copernicus.org/preprints/gmd-2020-169/ and is open for interactive public discussion until 12 Oct 2020.
Referees, authors, and other members of the scientific community can post interactive comments alongside the preprint. These comments are fully citable and archived.

AutoQA4Env has been presented by Najmeh Kaffashzadeh in the virtual EGU conference session on atmospheric composition variability and trends. Many scientific and statistical efforts are devoted to developing advanced analytic tools or methods, but a better quantification of trend and uncertainty cannot be achieved without proper data quality control (QC). Automated QC tools are needed to allow better use of existing data, for example in the machine learning applications of the IntelliAQ project. The presentation discusses the challenges involved and presents a methodology for automated QC and its integration into the workflow used for the TOAR-database. 

Bing Gong attended the Eumetnet workshop on “AI for weather and climate studies” held at Royal Meteorological Institute of Belgium. In the two-day workshop, 20 presentations were given on the existing or exploring potential weather and climate application of AI. Bing Gong gave a presentation on “Parallel deep learning workflow for short-term temperature forecasts with video frame prediction methods”.

Martin Schultz and Lukas Leufen attended a workshop on “Machine Learning in weather and climate modelling” at Corpus Christi college in Oxford. This workshop assembled more than 100 top-notch climate scientists and experts in HPC computer science and machine learning to present ongoing work and discuss the way forward. It became clear from the start that machine learning can likely play an important role in almost all stages of a weather and climate modelling workflow. Much discussed topics were the perceived need to impose physical constraints on the machine learning algorithms and quantify uncertainties. Martin Schultz’s presentation on the IntelliAQ and DeepRain projects was well received and the positive response confirmed the research strategy followed by these projects.

A first alpha version of the auto-qc tool has been released to the Helmholtz Digital Earth community for testing and further developments.

Severin Hußmann ran the first movie frame prediction tests using the Lotter et al. (2016) neural network architecture on the JSC supercomputer JURECA.