Author: Isabel Barrio

Posted on

Machine learning and herbarium specimens to assess changes in flowering phenology

A recent paper from the Machine Vision for Natural History research group at NTNU University Museum, including several NordBorN members, reports on global trends in flowering phenology, an indicator of the impact of anthropogenic climate change. A machine learning model was used to examine more than 8 million images of herbarium specimens from around the world and spanning two centuries. High diversity in temporal trends in flowering seasonality was found across different ecoregions, with greater variability at low latitudes than at high latitudes. This likely reflects the effects of a combination of shifts in temperature and precipitation seasonality, together with lower photoperiodic constraints to flowering. The study demonstrates the utility of machine learning approaches in large-scale analysis of museum collections and underscores both the importance of natural history collections in assessing long-term trends and the need for digitization efforts to make such specimens available to researchers across the world.

Future work is planned to link global flowering phenology patterns with local climate data, and to examine borealization by combining analysis of historical museum collections with data from field studies. You can read the paper here.

Reference: Williamson, D.R., Prestø, T., Westergaard, K.B., Trascau, B.M., Vange, V., Hassel, K., Koch, W. and Speed, J.D., Long‐term trends in global flowering phenology. New Phytologist. https://doi.org/10.1111/nph.70139

Image: Herbarium specimen of Leucanthemum maximum from the NTNU collection which was IDed by one of the co-authors

Posted on

NordBorN meeting in Aarhus 2025

The second NordBorN meeting was held in Denmark on March 25-27, 2025, hosted by our colleagues from Aarhus University. Twenty NordBorN members participated in the meeting in person, and others joined online for parts of the meeting. All the nine NordBorN partners were represented at the meeting.

One of the highlights of the meeting was the visit to the to the Mols Laboratory rewilding center, where we had the chance to learn more about rewilding efforts in Denmark and discuss borealization under the sun.

This year, we had the honour to host some guest researchers from Anglia Ruskin University who are studying the social implications of borealization. As well, during the meeting we had the opportunity to hear more about the research being done by our early career scientists, and to discuss future opportunities for collaboration.

Thanks again Niels, Efrén and Gala for a superb organization on the ground, and of course Mariana V for the endless support.

You can find relevant meeting documents here:

Posted on

Large herbivore and carnivore populations in boreal and tundra ecosystems are highly variable in time and space

NordBorN researchers have estimated and mapped historic biomass densities of large herbivores and carnivores across Norway. The current high densities of wild ungulates, especially moose and roe deer, contrast with historically high densities of livestock. Carnivores show a low level of recovery from near absence in the mid 20th century. However, densities are far below where they were in the 19th century.

These findings have implications for borealization: Previous studies have shown that herbivory can prevent the spread of boreal species into the tundra, yet it is clear that the trophic interactions involving large herbivores and carnivores are highly dynamic in both time and space.

Reference: Speed, J.D.M, Sobocinski, A., Kolstad, A. L., Linnell, J. D., Solberg, E. J., Mattisson, J., & Austrheim, G. (2025). The trophic distribution of biomass in ecosystems with co-occurring wildlife and livestock. Scientific Reports, 15(1), 1474. https://www.nature.com/articles/s41598-025-85469-2

Photo: Lynx (Erik F. Brandsborg, CC BY-SA)