Pascal Janetzky, M.Sc.

Chair of Data Science (Informatik X)
University of Würzburg
Campus Hubland Nord
Emil-Fischer-Straße 50
97074 Würzburg
Germany

Phone: (+49 931) 31 - 87028

Email: janetzky[at]informatik.uni-wuerzburg.de

Office: Room 9, 3rd floor at CAIDAS building 50 (Location)

In 2022, I joined the Chair of Computer Science X. Previously, I received my Masters degree in Computer Science from the University of Würzburg.

As part of my research, I have been working with time series and audio data. Did you know that the swarming event of a bee colony can be detected from the audio data? This is one of the findings we had, working with data from the we4bee project.

Recently, I focused on working with environmental and climate data -- the global ERA5 dataset offers a huge collection of long term weather data! Pairing this resource with Machine Learning models makes for an interesting combination, as recent publications regarding weather forecasting demonstrate.

Besides my research, I am also an administrator of our computer cluster. Together with my fellow admin colleagues, we keep the system running (well, most of the time...). If you have done machine learning research at out chair, then it's highly likely that you already interacted with our systems!

If you are looking for a cool thesis topic or research assistant position, don't hesitate to contact me -- actually, that's exactly how I ended up here!

Teaching

Summer term 24:

 Ausgewählte Themen des Machine Learning (BA and MA)

Winter term 23/24

Ausgewählte Themen des Machine Learning (BA and MA)

Winter term 22/23:

Datenbanken (Databases)

Publications

Global Vegetation Modeling with Pre-Trained Weather Transformers. Janetzky, Pascal; Gallusser, Florian; Hentschel, Simon; Hotho, Andreas; Krause, Anna. 2024.
- [ Abstract ]
- [ BibTeX ]
- [ URL ]
- [ Download ]
Accurate vegetation models can produce further insights into the complex inter- action between vegetation activity and ecosystem processes. Previous research has established that long-term trends and short-term variability of temperature and precipitation affect vegetation activity. Motivated by the recent success of Transformer-based Deep Learning models for medium-range weather forecast- ing, we adapt the publicly available pre-trained FourCastNet to model vegetation activity while accounting for the short-term dynamics of climate variability. We investigate how the learned global representation of the atmosphere’s state can be transferred to model the normalized difference vegetation index (NDVI). Our model globally estimates vegetation activity at a resolution of 0.25◦ while relying only on meteorological data. We demonstrate that leveraging pre-trained weather models improves the NDVI estimates compared to learning an NDVI model from scratch. Additionally, we compare our results to other recent data-driven NDVI modeling approaches from machine learning and ecology literature. We further provide experimental evidence on how much data and training time is necessary to turn FourCastNet into an effective vegetation model. Code and models will be made available upon publication.

@misc{janetzky2024global, abstract = {Accurate vegetation models can produce further insights into the complex inter- action between vegetation activity and ecosystem processes. Previous research has established that long-term trends and short-term variability of temperature and precipitation affect vegetation activity. Motivated by the recent success of Transformer-based Deep Learning models for medium-range weather forecast- ing, we adapt the publicly available pre-trained FourCastNet to model vegetation activity while accounting for the short-term dynamics of climate variability. We investigate how the learned global representation of the atmosphere’s state can be transferred to model the normalized difference vegetation index (NDVI). Our model globally estimates vegetation activity at a resolution of 0.25◦ while relying only on meteorological data. We demonstrate that leveraging pre-trained weather models improves the NDVI estimates compared to learning an NDVI model from scratch. Additionally, we compare our results to other recent data-driven NDVI modeling approaches from machine learning and ecology literature. We further provide experimental evidence on how much data and training time is necessary to turn FourCastNet into an effective vegetation model. Code and models will be made available upon publication.}, author = {Janetzky, Pascal and Gallusser, Florian and Hentschel, Simon and Hotho, Andreas and Krause, Anna}, keywords = {ecomodelling}, title = {Global Vegetation Modeling with Pre-Trained Weather Transformers}, year = 2024 }
Swarming Detection in Smart Beehives Using Auto Encoders for Audio Data. Janetzky, Pascal; Schaller, Melanie; Krause, Anna; Hotho, Andreas. In 2023 30th International Conference on Systems, Signals and Image Processing (IWSSIP), pp. 1–5. 2023.
- [ BibTeX ]
- [ Download ]
@inproceedings{10180253, author = {Janetzky, Pascal and Schaller, Melanie and Krause, Anna and Hotho, Andreas}, booktitle = {2023 30th International Conference on Systems, Signals and Image Processing (IWSSIP)}, keywords = {author:KRAUSE}, pages = {1-5}, title = {Swarming Detection in Smart Beehives Using Auto Encoders for Audio Data}, year = 2023 }
Automatic Speech Detection on a Smart Beehive’s Raspberry Pi. Janetzky, Pascal; Lissmann, Philip; Hotho, Andreas; Krause, Anna. In ESC, 8, p. 9. 2023.
- [ BibTeX ]
@article{janetzky2023automatic, author = {Janetzky, Pascal and Lissmann, Philip and Hotho, Andreas and Krause, Anna}, journal = {ESC}, keywords = {author:LISSMANN}, pages = 9, title = {Automatic Speech Detection on a Smart Beehive’s Raspberry Pi}, volume = 8, year = 2023 }
Detecting Presence Of Speech In Acoustic Data Obtained From Beehives. Janetzky, Pascal; Davidson, Padraig; Steininger, Michael; Krause, Anna; Hotho, Andreas. In DCASE, pp. 26–30. 2021.
- [ BibTeX ]
- [ Download ]
@inproceedings{janetzky2021detecting, author = {Janetzky, Pascal and Davidson, Padraig and Steininger, Michael and Krause, Anna and Hotho, Andreas}, booktitle = {DCASE}, keywords = {author:KRAUSE}, pages = {26–30}, title = {Detecting Presence Of Speech In Acoustic Data Obtained From Beehives.}, year = 2021 }

Other scientific activities

Co-Chair of the "Audio, Speech and Music" session at IWSSIP 2023
(Sub-)Reviewer for KI and WebConf'23

Teaching

Publications

Other scientific activities

Hinweis zum Datenschutz

Hinweis zum Datenschutz

Bildnachweise