ESoWC 2020 Final Results
The third edition of ECMWF Summer of Weather Code just ended and all the outcomes from the nine participant projects were presented at the final ESoWC Day 2020, on 16 October 2020 during a virtual event.
During the summer, all developers worked under the thorough guide of the ECMWF mentors, with a view to create a shared learning experience that could benefit both sides and learn from each other. A great benefit to the project also comes from the fact that the majority of the participants come from backgrounds that are not directly related to the meteorology field, thus bringing new ideas and point of views to ESoWC.
In addition, many of the project teams are continuing their collaboration even after submitting their final results, and this is not only an evidence for the quality of the developments that we can find with ESoWC, but also a proof of the great philosophy at the core of the project.
This year’s innovative outcomes were focusing three main fields: Machine learning, Copernicus open data and ECMWF’s model performance, data storage and archiving.
Four teams explored the use of machine learning and artificial intelligence in a range of applications:
- ‘Virtual assistant for users of ECMWF online products and services’ – the team developed a chatbot that assists ECMWF users to find answers to common support queries.
- ‘Applying AI capabilities to address operational challenges in ECMWF products team’ – the team applied AI capabilities to better understand sudden disruptions or failures of ECMWF production chain systems and predict future spikes and surges.
- ‘Exploring machine/deep learning techniques to detect and track tropical cyclones' - the team developed a deep-learning algorithm which recognises and classifies tropical cyclones based on their intensities.
- ‘DeepGEFF’ – the team explored whether fire danger forecasting using deep learning achieves comparable skill to the Global ECMWF Fire Forecasting (GEFF) system
Three teams put a focus on Copernicus open data:
- ‘Classification of air quality’ – the team developed a classification scheme to easily validate and remove outliers from surface air quality observations. This allowed the comparison of station data with air quality forecasts from the Copernicus Atmosphere Monitoring Service.
- ‘Detecting anomalies in Air Quality Stations (DAAQS)’ – the team applied clustering algorithms to provide reliability and representativeness scores for air quality stations.
- ‘UNSEEN-Open’ – the team developed an open, reproducible and transferable workflow based on climate reanalysis and seasonal forecast data to assess and anticipate climate extremes beyond the observed record.
And another two teams worked on challenges related to ECMWF’s model performance, data storage and archiving:
- ‘HPC performance profiling tool’ – the team developed an interface to interactively visualise HPC performance data in order to better track and analyse the performance of ECMWF’s integrated forecasting system (IFS).
- ‘Compressing atmospheric data into its real information’ – based on the global real-time forecast dataset from the Copernicus Atmosphere Monitoring Service, the team tested different configurations in order to estimate data encoding errors and the potential to compress the volume of data
At the end of the Final ESoWC Day, the project coordinators announced that next year’s edition has been confirmed. For any updates, follow ECMWF Summer of Weather Code on Twitter, Facebook and Linkedin.