Zobrazeno 1 - 10
of 23
pro vyhledávání: '"Michael Steininger"'
Autor:
Yong Wang, Ingo Meirold-Mautner, Alexander Kann, Alenka Šajn Slak, André Simon, Jozef Vivoda, Benedikt Bica, Ernst Böcskör, Lucie Brezková, Johann Dantinger, Mateusz Giszterowicz, György Heizler, Rafal Iwanski, Siegfried Jachs, Thomas Bernard, Rok Kršmanc, Janko Merše, Stefano Micheletti, Franziska Schmid, Michael Steininger, Thomas Haiden, Adam Regec, Matteo Buzzi, Mária Derková, Tomislav Kozarić, Xuexing Qiu, Maarten Reyniers, Jinbiao Yang, Yong Huang, Elyakom Vadislavsky
Publikováno v:
Meteorologische Zeitschrift, Vol 26, Iss 5, Pp 459-473 (2017)
This paper presents the recent WWRP/WMO Forecast Demonstration Project INCA-CE (INtegrating nowCAsting for Central Europe) co-funded by the European Union. Twenty-four partners of national and regional hydro-meteorological services, national and regi
Externí odkaz:
https://doaj.org/article/a8302fc3e6fd4f5fa25cda296a4f555b
Autor:
Simone Zepp, Uta Heiden, Martin Bachmann, Martin Wiesmeier, Michael Steininger, Bas van Wesemael
Publikováno v:
Remote Sensing, Vol 13, Iss 16, p 3141 (2021)
For food security issues or global climate change, there is a growing need for large-scale knowledge of soil organic carbon (SOC) contents in agricultural soils. To capture and quantify SOC contents at a field scale, Earth Observation (EO) can be a v
Externí odkaz:
https://doaj.org/article/17beb220ef664734ac707ce27b0cd0bd
Publikováno v:
Data Mining and Knowledge Discovery. 37:136-166
Climate models are the tool of choice for scientists researching climate change. Like all models they suffer from errors, particularly systematic and location-specific representation errors. One way to reduce these errors is model output statistics (
Autor:
Michael Steininger, Daniel Wurbs
Publikováno v:
Bodenschutz.
Recent studies have shown that many deep metric learning loss functions perform very similarly under the same experimental conditions. One potential reason for this unexpected result is that all losses let the network focus on similar image regions o
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e87934815242b172f8f0f8a670714635
Publikováno v:
Communications in Computer and Information Science ISBN: 9783031177170
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::7945c019a0a4918aa0bb60c76100da24
https://doi.org/10.1007/978-3-031-17718-7_1
https://doi.org/10.1007/978-3-031-17718-7_1
Autor:
Uta Heiden, Michael Steininger, Markus Möller, Bas van Wesemael, Martin Wiesmeier, Martin F. Bachmann, Simone Zepp
High spatial and temporal soil information is crucial to analyze soil developments and for monitoring long term changes to avoid soil degradation. A sufficient soil organic carbon (SOC) content is one of the key soil properties to achieve sustainable
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::41d681dc9fd123031252b918342a1197
https://doi.org/10.5194/egusphere-egu21-7371
https://doi.org/10.5194/egusphere-egu21-7371
In many real world settings, imbalanced data impedes model performance of learning algorithms, like neural networks, mostly for rare cases. This is especially problematic for tasks focusing on these rare occurrences. For example, when estimating prec
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::991e7024b1ddacdabe2d605b78e09664
https://opus.bibliothek.uni-wuerzburg.de/files/26917/Steininger_Machine.pdf
https://opus.bibliothek.uni-wuerzburg.de/files/26917/Steininger_Machine.pdf
Autor:
Konstantin Kobs, Anna Krause, Roland Baumhauer, Christian Schäfer, Heiko Paeth, Michael Steininger, Andreas Hotho
Publikováno v:
Pattern Recognition. ICPR International Workshops and Challenges ISBN: 9783030687793
ICPR Workshops (6)
ICPR Workshops (6)
High-resolution grain size distribution maps for geographical regions are used to model soil-hydrological processes that can be used in climate models. However, measurements are expensive or impossible, which is why interpolation methods are used to
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::7d37ce5b2918f1382b665cafb0027410
https://doi.org/10.1007/978-3-030-68780-9_4
https://doi.org/10.1007/978-3-030-68780-9_4
Publikováno v:
KI 2021: Advances in Artificial Intelligence ISBN: 9783030876258
KI
KI
Creating datasets for supervised learning is a very challenging and expensive task, in which each input example has to be annotated with its expected output (e.g. object class). By combining unsupervised and semi-supervised learning, semi-unsupervise
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::18c7baf3e8192e9fc80e8db8fde6ea40
https://doi.org/10.1007/978-3-030-87626-5_5
https://doi.org/10.1007/978-3-030-87626-5_5