Research

My main research interests are the application of artificial intelligence and machine learning methods to scientific problems – with an emphasis on problems in weather prediction and climate physics, atmospheric remote sensing, and probabilistic weather prediction as well as predictability in general.

CV

Work experience

20024-present Postdoc, Wegener Center for Climate and Global Change, University of Graz Austria

2021-2024 Senior Scientist, Know Center GmbH, Graz, Austria
Development of AI models for research and industrial projects, project management

2017-2020 University Assistant, Department of Meteorology (MISU), Stockholm University, Sweden
Weather predictability, use of AI methods for weather and climate science

2016 - 2017 Consultant for weather and climate, Weather Impact BV, Amersfoort, Netherlands
Development of weather forecast products for developing countries

2015 - 2016 Intern and research assistant, Royal Netherlands Meteorological Institute (KNMI), De Bilt, Netherlands
Global and regional numerical climate modeling

2013 - 2014 Junior scientist, Wegener Center for Climate and Global Change, University of Graz, Austria
Data analysis, bias correction of regional climate models

Education

2017-2020 PhD in Atmospheric Sciences and Oceanography,  Student at the Department of Meteorology (MISU), Stockholm, Sweden, University,  PhD-thesis “Artificial intelligence in weather and climate prediction”

2014-2016 MSc. Meteorology, Physical Oceanography and Climate, Utrecht University, Netherlands

2009-2014 BSc. Environmental Systems Science, University of Graz and TU Graz, Austria

2009-2014 BSc. Physics, University of Graz, Austria

Publications

Peer-reviewed publications 

Schlager, E., Scher, S., Mottram, R. H., & Langen, P. L.: Learning to melt: Emulating Greenland surface melt from a polar RCM with machine learning, [in press], preprint at https://doi.org/10.5194/egusphere-2026-7

Scher, S., Schalamon, F. R., Trügler, A., & Abermann, J. (2026) Evaluation of air temperature uncertainty estimates of the NOAA/CIRES/DOE 20th Century Reanalysis over Greenland, Journal of Geophysical Research: Atmospheres, 131, e2025JD045949,  https://doi.org/10.1029/2025JD045949

Shi, J., Li, M., Steiner, A. K., Scher, S., Zhang, M., Hu, J., Gao, W., Fan, Y., & Zhang, K (2026). Evaluation of reanalysis precipitable water vapor under typhoon conditions using multi-source observations, Atmospheric Chemistry and Physics, 26, 4633–4650, https://doi.org/10.5194/acp-26-4633-2026

Scher, S., Ladstädter, F., Schwärz, M., Innerkofler, J., & Kirchengast, G. (2026). Uncertainty propagation from radio occultation profiles to aggregated atmospheric gridded fields. Earth and Space Science, 13(1), e2025EA004389. https://doi.org/10.1029/2025EA004389

Ladstädter, F., Stocker, M., Scher, S., & Steiner, A. K. (2025). Observed changes in the temperature and height of the globally resolved lapserate tropopause. Atmospheric Chemistry and Physics, 25(22), 16053-16062. https://doi.org/10.5194/acp-25-16053-2025

Schalamon, F. R., Scher, S., Trügler, A., Hartl, L., Schöner, W., & Abermann, J. (2025). The role of large-scale atmospheric patterns for recent warming periods in Greenland from 1900–2015. Weather and Climate Dynamics, 6(4), 1075-1088. https://doi.org/10.5194/wcd-6-1075-2025

Kowald, D., Scher, S., Pammer-Schindler, V., Müllner, P., Waxnegger, K., Demelius, L., et al. (2024). Establishing and evaluating trustworthy AI: overview and research challenges. Frontiers in Big Data, 7, 1467222. https://doi.org/10.3389/fdata.2024.1467222

Scher, S., & Messori, G. (2024). Physics-Inspired Adaptions to Low-Parameter Neural Network  Weather Forecast Systems. Artificial Intelligence for the Earth Systems, 3(1), e230046. https://doi.org/10.1175/AIES-D-23-0046.1

Abermann, J., Vandecrux, B., Scher, S., Löffler, K., Schalamon, F., Trügler, A., Fausto, R., &  Schöner, W. (2023). Learning from Alfred Wegener’s pioneering field observations in West  Greenland after a century of climate change. Scientific Reports, 13(1), Article 1.  https://doi.org/10.1038/s41598-023-33225-9

Scher, S., Kopeinik, S., Trügler, A., & Kowald, D. (2023). Modelling the long-term fairness dynamics of data-driven targeted help on job seekers. Scientific Reports, 13(1), 1727. https://doi.org/10.1038/s41598-023-28874-9

Hochman, A., Scher, S., Quinting, J., Pinto, J. G., & Messori, G. (2022). Dynamics and  predictability of cold spells over the Eastern Mediterranean. Climate Dynamics, 58(7–8), 2047– 2064. https://doi.org/10.1007/s00382-020-05465-2

Jewson, S., Scher, S., & Messori, G. (2022). Communicating properties of changes in lagged  weather forecasts. Weather and Forecasting, 37(1), 125–142. https://doi.org/10.1175/WAF-D-21-0086.1

Hochman, A., Scher, S., Quinting, J., Pinto, J. G., & Messori, G. (2021). A new view of heat wave  dynamics and predictability over the Eastern Mediterranean. Earth System Dynamics, 12(1), 133– 149. https://doi.org/10.5194/esd-12-133-2021

Jewson, S., Scher, S., & Messori, G. (2021). Decide now or wait for the next forecast? Testing a  decision framework using real forecasts and observations. Monthly Weather Review, 149(6),  1637–1650. https://doi.org/10.1175/MWR-D-20-0392.1

Scher, S., Jewson, S., & Messori, G. (2021). Robust worst-case scenarios from ensemble  forecasts. Weather and Forecasting, 36(4), 1357–1373. https://doi.org/10.1175/WAF-D-20-0219.1

Scher, S., & Messori, G. (2021). Ensemble methods for neural network-based weather forecasts.  Journal of Advances in Modeling Earth Systems, 13. https://doi.org/10.1029/2020MS002331

Scher, S., & Peßenteiner, S. (2021). Temporal disaggregation of spatial rainfall fields with  generative adversarial networks. Hydrology and Earth System Sciences, 25(6), 3207–3225. https://doi.org/10.5194/hess-25-3207-2021

Molinder, J., Scher, S., Nilsson, E., Körnich, H., Bergström, H., & Sjöblom, A. (2020). Probabilistic forecasting of wind turbine icing related production losses using quantile regression forests.  Energies, 14(1), 158. https://doi.org/10.3390/en14010158

Rasp, S., Dueben, P. D., Scher, S., Weyn, J. A., Mouatadid, S., & Thuerey, N. (2020).  WeatherBench: A benchmark data set for data-driven weather forecasting. Journal of Advances in  Modeling Earth Systems, 12(11), e2020MS002203. https://doi.org/10.1029/2020MS002203

de Vries, H., Scher, S., Haarsma, R., Drijfhout, S., & van Delden, A. (2019). How gulf-stream SST fronts influence atlantic winter storms. Climate Dynamics, 52(9–10), 5899–5909. https://doi.org/10.1007/s00382-018-4486-7

Scher, S., & Messori, G. (2019). Generalization properties of feed-forward neural networks trained  on Lorenz systems. Nonlinear Processes in Geophysics, 26(4), 381–399. https://doi.org/10.5194/npg-26-381-2019

Scher, S., & Messori, G. (2019). How global warming changes the difficulty of synoptic weather forecasting. Geophysical Research Letters, 46(5), 2931–2939. https://doi.org/10.1029/2018GL081856

Scher, S., & Messori, G. (2019). Weather and climate forecasting with neural networks: Using  general circulation models (GCMs) with different complexity as a study ground. Geoscientific  Model Development, 12(7), 2797–2809. https://doi.org/10.5194/gmd-12-2797-2019

Scher, S., & Molinder, J. (2019). Machine learning based prediction of icing-related wind power  production loss. IEEE Access , 7, 129421–129429. https://doi.org/10.1109/ACCESS.2019.2939657

Scher, S. (2018). Toward data-driven weather and climate forecasting: Approximating a simple  general circulation model with deep learning. Geophysical Research Letters, 45(22), 12–616. https://doi.org/10.1029/2018GL080704

Scher, S., & Messori, G. (2018). Predicting weather forecast uncertainty with machine learning. Quarterly Journal of the Royal Meteorological Society, 144(717), 2830–2841. https://doi.org/10.1002/qj.3410

Scher, S., & Messori, G. (2018). Selective ensemble mean technique for severe European  windstorms. Quarterly Journal of the Royal Meteorological Society, 145(718), 376–385. https://doi.org/10.1002/qj.3408

Scher, S., Haarsma, R. J., De Vries, H., Drijfhout, S. S., & Van Delden, A. J. (2017). Resolution dependence of extreme precipitation and deep convection over the Gulf Stream. Journal of  Advances in Modeling Earth Systems, 9(2), 1186–1194. https://doi.org/10.1002/2016MS000903

Preprints

Scher, S., Geiger, B., Kopeinik, S., Trügler, A., & Kowald, D. (2023). A conceptual model for leaving the data-centric approach in machine learning. arXiv Preprint arXiv:2302.03361., https://arxiv.org/abs/2302.03361

Scher, S., & Trügler, A. (2023). Testing robustness of predictions of trained classifiers against naturally occurring perturbations. arXiv Preprint arXiv:2204.10046. https://doi.org/10.48550/arXiv.2204.10046

Schweimer, C., & Scher, S. (2022). Quantifying probabilistic robustness of tree-based classifiers against natural distortions. arXiv Preprint  arXiv:2208.10354., https://doi.org/10.48550/arXiv.2208.10354

Monographs 

Scher, S. “Artificial intelligence in weather and climate prediction: Learning atmospheric dynamics,” PhD Thesis, Department of Meteorology, Stockholm University, 2020. ISBN: 978-91-7911-129-8, https://urn.kb.se/resolve?urn=urn:nbn:se:su:diva-180877

Whitepapers 

“White Paper: Trustworthy AI, Accountability”, Kerstin Waxnegger, Sebastian Scher, Simone  Kopeinik, Tomislav Nad, and Dominik Kowald, www.sgs.com/en/whitepapers/trustworthy-ai accountability-form (2024) 

“White Paper: Trustworthy AI, Fairness in AI and its Relation to Social Well-being”, Simone  Kopeinik, Sebastian Scher, Tomislav Nad, and Dominik Kowald,White Paper:  www.sgs.com/en/whitepapers/trustworthy-ai-fairness-in-ai-and-its-relation-to-social-well being-form (2023) 

“White Paper: Trustworthy AI, Robustness and Performance of AI Applications”, Sebastian Scher,  Andreas Trügler, Simone Kopeinik, Tomislav Nad, and Dominik Kowald, 

www.sgs.com/en/whitepapers/trustworthy-ai-robustness-and-performance-of-ai applications-form, (2023) 

“White Paper: Trustworthy AI, Human Agency and Oversight”, Simone Kopeinik, Sebastian Scher,  Tomislav Nad, and Dominik Kowald, 

www.sgs.com/en/whitepapers/trustworthy-ai-human-agency-and-oversight-form (2023)

“White Paper: Trustworthy AI, Privacy and Security”, Lea Demelius, Andreas Trügler, Simone  Kopeinik, Sebastian Scher, Tomislav Nad, and Dominik Kowald, 

www.sgs.com/en/whitepapers/trustworthy-ai-privacy-and-security-in-ai-form (2023) 

“White Paper: Trustworthy AI, Transparency and Explainability”, Peter Müllner, Emanuel Lacic,  Simone Kopeinik, Sebastian Scher, Tomislav Nad, and Dominik Kowald, 

www.sgs.com/en/whitepapers/trustworthy-ai-transparency-and-explainability-in-ai-form (2023) 

“Trustworthiness of AI”, Tomislav Nad, Sebastian Scher, Florian Königstorfer,  www.sgs.com/en/whitepapers/trustworthiness-of-ai-form (2023) 

“Evaluating the trustworthiness of AI applications – Lessons learned from an audit”, Tomislav Nad,  Philipp Nöhrer, Sebastian Scher, trustyour.ai/2023/05/evaluating-the-trustworthiness-of-ai applications-lessons-learned-from-an-audit/ (2023) 

“Certifying Fairness of AI-Applications An Impossible Task?” Sebastian Scher, Sarah Stryeck,  trustyour.ai/whitepaper/certifying-fairness-of-ai-applications-an-impossible-task/ (2022)