Our latest research explores how YOLO object detectors, trained on citizen science images, perform on unseen time-lapse images of pollinators captured with a fixed smartphone setup. While successful for larger pollinators, detecting smaller or blurrier flower visitors remains a challenge.

The DOGE firings have nothing to do with “efficiency” or “cutting waste.” They’re a direct push to weaken federal agencies perceived as liberal. This was evident from the start, and now the data confirms it: targeted agencies overwhelmingly those seen as more left-leaning. 🧵⬇️

[new paper] EuPPollNet: A European Database of Plant-Pollinator Networks onlinelibrary.wiley.com/doi/10.1111/... Another wonderful paper of @joseblanuza.bsky.social making open more than >1500 networks and looking at their properties. Come for the data, stay for the cool figures!

2025 starts with a methodology publication by Ștefan et al. on Utilising affordable smartphones and open-source time-lapse photography for pollinator image collection and annotation - Happy new year! doi.org/10.26786/192...

Our research center (iDiv) will host a very interesting summer school (25 – 29 August 2025) - Deep learning for biodiversity and ecological research. More details here: www.idiv.de/events/summe... #biodiversity #education #aiforgood #technology #idiv

📢 Excited to share our new paper: "Utilising affordable smartphones and open-source time-lapse photography for pollinator image collection and annotation" 🌼📸 What taxonomists can achieve using only field-captured images from a fixed setup? 🔗 Read it here: www.pollinationecology.org/index.php/jp...