Wir spielen mit offenen Karten - Der FOSSGIS e.V.
Neu auf der #FOSSGIS2026 und ihr kennt den FOSSGIS-Verein noch nicht?
Um 16:30 stellt Jochen Topf von der Koordinierungsstelle den Verein vor und gibt einen Einblick hinter die Kulissen - nicht verpassen! https://pretalx.com/fossgis2026/talk/ULQLYP/
Wir freuen uns außerdem über neue Mitglieder & auf einen Besuch am Stand des FOSSGIS e.V. im Foyer!
Informationen zum Verein https://www.fossgis.de/verein/
#FOSSGIS-Konferenz im Livestream
Die #FOSSGIS2026 Konferenz wird auch im Livestream übertragen. Ein tolles Programm erwartet uns in den nächsten 3 Tagen rund um #OpenSource #Geospatial #OpenData #OSM & mehr.
Schauen Sie gerne vorbei.
https://www.fossgis-konferenz.de/2026/programm/
Es geht los - das Programm der #FOSSGIS2026 ist gestartet und der FOSSGIS Verein und unser diesjähriger Gastgeber @unigoettingen begrüßen herzlich alle Teilnehmenden vor Ort und digital!
🎉 New R package {quaxnat} published on CRAN by Axer, Schlicht & Nuske. Estimation of the natural regeneration potential of tree species.
Already benefitting from the brand new CRAN DOI Service: https://doi.org/10.32614/CRAN.package.quaxnat
Functions for estimating the potential dispersal of tree species using regeneration densities and dispersal distances to nearest seed trees. A quantile regression is implemented to determine the dispersal potential. Spatial prediction can be used to identify natural regeneration potential for forest restoration as described in Axer et al. (2021) <<a href="https://doi.org/10.1016%2Fj.foreco.2020.118802" target="_top">doi:10.1016/j.foreco.2020.118802</a>>.
A new anothology about the extreme dangers of staying on our current trajectory — global warming of 3 degrees or more. The book includes an important chapter from Mastodon's Stefan Rahmstorf (@rahmstorf).
Best of all it's free to read!
➡️ https://link.springer.com/book/10.1007/978-3-031-58144-1
#Science #Environment #Climate #ClimateChange #ClimateCrisis
Hi #QGIS Community, wir gründen gerade ein #DevOps Team für QGIS-Erweiterungen. Falls jemand einen sicheren #job mit viel Gestaltungsfreiraum im #FOSSGIS Bereich sucht:
https://karriere.niedersachsen.de/Stellenangebote.html?typ=&berufsgruppen=&besoldungsentgeltgruppeIds=&schulabschluss=&plz=&entfernung=&suchwort=lgln
#ProductOwner #Developer #Scrum #Niedersachsen
@qgis @qgisDE
New paper: "Data science competition for cross-site individual tree species identification from airborne remote sensing data"
TLDR; Predicting common species w/local training data works; rarer species are difficult; same species w/o local training data are harder.
Data on individual tree crowns from remote sensing have the potential to advance forest ecology by providing information about forest composition and structure with a continuous spatial coverage over large spatial extents. Classifying individual trees to their taxonomic species over large regions from remote sensing data is challenging. Methods to classify individual species are often accurate for common species, but perform poorly for less common species and when applied to new sites. We ran a data science competition to help identify effective methods for the task of classification of individual crowns to species identity. The competition included data from three sites to assess each methods’ ability to generalize patterns across two sites simultaneously and apply methods to an untrained site. Three different metrics were used to assess and compare model performance. Six teams participated, representing four countries and nine individuals. The highest performing method from a previous competition in 2017 was applied and used as a baseline to understand advancements and changes in successful methods. The best species classification method was based on a two-stage fully connected neural network that significantly outperformed the baseline random forest and gradient boosting ensemble methods. All methods generalized well by showing relatively strong performance on the trained sites (accuracy = 0.46–0.55, macro F1 = 0.09–0.32, cross entropy loss = 2.4–9.2), but generally failed to transfer effectively to the untrained site (accuracy = 0.07–0.32, macro F1 = 0.02–0.18, cross entropy loss = 2.8–16.3). Classification performance was influenced by the number of samples with species labels available for training, with most methods predicting common species at the training sites well (maximum F1 score of 0.86) relative to the uncommon species where none were predicted. Classification errors were most common between species in the same genus and different species that occur in the same habitat. Most methods performed better than the baseline in detecting if a species was not in the training data by predicting an untrained mixed-species class, especially in the untrained site. This work has highlighted that data science competitions can encourage advancement of methods, particularly by bringing in new people from outside the focal discipline, and by providing an open dataset and evaluation criteria from which participants can learn.
This endorsement from Pensoft
leaves the big, monopolist academic publishing houses alone in their opposition to the conclusions on scholarly publishing by the Council of the EU:
after widespread support from scholarly organizations, e.g.:
or funders, e.g.:
https://www.dfg.de/en/service/press/press_releases/2023/press_release_no_16/index.html
What once was a radical approach is now mainstream and accepted. Let's make it happen:
FOSSGIS Verein
Bread and Circuses
Achim Zeileis
package authors.
Jonas Bostelmann
weecology
Björn Brembs
gislars