1. Dataset for "Image-based recognition using advanced neural networks can aid surveillance of Agrilus jewel beetles"Valerio Caruso, Davide Rassati, Pierfilippo Cerretti, Gianfranco Curletti, Maarten De Groot, Eva Groznik, Jerzy M. Gutowski, Christian Pylatiuk, Alain Roques, Aurélien Sallé, 2025, complete scientific database of research data Keywords: Agrilus anxius, Agrilus planipennis, bronze birch borer, deep learning, early-detection, emerald ash b4orer, Entomoscope
Published in DiRROS: 27.02.2026; Views: 110; Downloads: 66
 Full text (8,06 GB)
This document has many files! More... |
2. Image-based recognition using advanced neural networks can aid surveillance of Agrilus jewel beetlesValerio Caruso, Hossein Shirali, Christophe Bouget, Pierfilippo Cerretti, Gianfranco Curletti, Maarten De Groot, Eva Groznik, Jerzy M. Gutowski, Christian Pylatiuk, Radosław Plewa, 2026, original scientific article Abstract: The genus Agrilus includes two species, Agrilus planipennis and A. anxius, that are of particular phytosanitary concern and that are regulated by the European Union legislation. This implies that phytosanitary agencies of all EU countries are obliged to establish specific surveillance programmes to verify the absence of these species from their territory. These activities commonly consist of the use of green-coloured traps, which are, however, attractive not only for A. planipennis and A. anxius, but also for a wide range of other Agrilus species. For this reason, much time and expertise is required to sort and identify specimens to species, impeding an efficient rapid response. In this study, we tested the efficacy of the Entomoscope, a low-cost, open-source photomicroscope that uses high-resolution digital imaging and allows a pre-trained Convolutional Neural Networks (CNN) model to accurately detect, image and classify insect specimens, for automatic identification of 13 Agrilus species, including A. planipennis and A. anxius. We benchmarked models from three different CNN architectures and selected YOLOv8l as the most robust performer; this model achieved a Top-1 accuracy of 90.2% on a “real-world” test set (i.e. a dataset simulating real surveillance conditions). For most species, including A. planipennis and A. anxius, either no errors or only a few errors were made, whereas for a few native species, misidentifications were more common. These results provided proof of concept for an AI-driven surveillance system that can strongly aid in surveillance activities of Agrilus species.
Keywords: Agrilus anxius, Agrilus planipennis, bronze birch borer, deep learning, early-detection, emerald ash b4orer, Entomoscope
Published in DiRROS: 27.02.2026; Views: 90; Downloads: 26
 Link to file |
3. Larval diet breadth and wingspan mediate landscape–richness relationship in butterfly communitiesDušanka Vujanović, Maja Knežević, Aleksandra Đorđević, Andrijana Andrić, Milica Ranković Perišić, Marina Janković Milosavljević, Sanja Veselić, Gianalberto Losapio, Maarten De Groot, Ante Vujić, Snežana Radenković, 2026, original scientific article Abstract: Landscape structure and species traits both shape butterfly assemblages, but their joint effects, and how landscapes restructure trait space independently of richness, remain less understood. We surveyed butterflies at 50 semi-natural grasslands (Serbia) and modelled species richness (SR) with GAMs using two sets of landscape predictors within 2-km buffers: composition (% cover of grassland, forest, complex agriculture) and configuration (distance to the nearest natural patch, nearest natural-patch size, edge density). We included community-weighted mean (CWM) of two traits: wingspan (WS) and host-plant specificity (HPS) and fit landscape-only models, trait-additive models and pre-specified trait–landscape interactions per set (HPS and complex agriculture; WS and distance to the nearest natural patch). To test whether these gradients restructure trait space, we modelled functional divergence (FDiv) as a complementary response. The only landscape predictor of SR was complex agriculture, which increased richness but reduced FDiv. Beyond landscape composition, HPS consistently improved SR models in both sets, with richness peaking at intermediate-to-narrow diet breadth and declining towards extremes. Isolation increased SR only in large-winged communities (WS × distance to the nearest natural patch), and FDiv increased with isolation, evidencing greater representation of trait extremes. Crucially, landscape effects on FDiv persisted after conditioning on SR, showing that landscapes filter which traits persist, not just how many species occur. Butterfly assemblages are driven by resource-based and movement-based filtering rather than landscape structure alone. Our key novelty shows that the same landscape gradients decouple taxonomic from functional diversity; agricultural complexity adds species while compressing trait breadth, whereas isolation benefits large-winged communities and expands trait dispersion. Conservation should therefore track functional structure as well as counts, maintaining diverse larval host-plants and stepping-stone connectivity to sustain both species richness and the functional breadth that underpins resilience.
Keywords: butterfly community, larval diet breadth, species richness, trait–environment interactions, wingspan
Published in DiRROS: 17.02.2026; Views: 165; Downloads: 66
 Full text (2,88 MB)
This document has many files! More... |
4. European Bee and Hovefly Database (EBHD)Ahlam Sentil, Marija Miličić, Jordan Benrezkallah, Jelena Ačanski, Andrijana Andrić, Matthieu Aubert, Ignasi Bartomeus, Paolo Biella, Mira Boustani, Leif Bloss Carstensen, Maarten De Groot, 2025, complete scientific database of research data Abstract: This publication includes: (i) Two occurrence databases of bees and hoverflies in “Pollinator Core” template, saved as RDS and CSV files. The databases are a result of compiled datasets from diverse sources, including taxonomists, national experts, published data, museum collections, literature, and aggregated datasets from previous European projects. They comprise more than 4,34 million and 1,04 million records for wild bees and hoverflies, respectively. The databases cover 97% of the European bee fauna and 97% of the European hoverfly fauna.
Keywords: database, wild bee, hoverfly, Europe
Published in DiRROS: 12.02.2026; Views: 339; Downloads: 59
 Full text (0,48 KB)
This document has many files! More... |
5. Synthesised database of wild bee and hoverfly records in EuropeAhlam Sentil, Marija Miličić, Jordan Benrezkallah, Jelena Ačanski, Andrijana Andrić, Matthieu Aubert, Ignasi Bartomeus, Paolo Biella, Mira Boustani, Leif Bloss Carstensen, Maarten De Groot, 2026, other scientific articles Abstract: Wild bees (Hymenoptera: Anthophila) and hoverflies (Diptera: Syrphidae), the two major groups of insect pollinators, are undergoing alarming declines worldwide, including Europe. The lack of accessible and verified spatial and temporal occurrence records currently challenges efforts to understand and mitigate this decline. Here, we compiled datasets from diverse sources, including taxonomists, national experts, public repositories, museum collections, published literature, verified open-access platforms, and aggregated datasets from previous European projects. The collected data were standardised, cleaned and validated by taxonomists and national experts. This collective effort resulted in two databases comprising more than 4.34 million and 1.04 million records for wild bees and hoverflies, respectively. The databases cover 97% of the European bee fauna (2,083 species out of 2,138 recorded in Europe) and 97% of the European hoverfly fauna (886 species out of 913 recorded in Europe). These standardised databases constitute essential resources for future assessments of status and trends, habitat associations, and other research and conservation initiatives to protect and understand wild pollinators on the European continent.
Keywords: database, wild bee, hoverfly, Europe
Published in DiRROS: 12.02.2026; Views: 387; Downloads: 94
Full text (4,61 MB)
This document has many files! More... |
6. Ko lubadar postane zvezdar – ustaljenost terminologije kot temelj učinkovite komunikacije v gozdarstvuMaarten De Groot, Ana Brglez, Luka Capuder, Zina Devetak, Eva Groznik, Tine Hauptman, Nikica Ogris, Barbara Piškur, 2025, professional article Abstract: V času podnebnih sprememb, globalne trgovine in širjenja invazivnih organizmov je jasna, konsistentna in funkcionalna komunikacija med strokovnjaki, lastniki gozdov in javnostjo ključna za učinkovito gospodarjenje z gozdovi. Nedavna prizadevanja za posodobitev slovenskih imen podlubnikov, kot jih predlagajo Jurc in sod. (2024) v reviji Scopolia, odpirajo pomembno razpravo o strokovni ustreznosti, funkcionalnosti in ustaljenosti terminologije. S pričujočim komentarjem želimo opozoriti na pomen ohranjanja ustaljenih slovenskih poimenovanj, ki so v stroki uveljavljena že desetletja, ter predlagamo mehanizme za vzpostavitev strukturiranega procesa za usklajevanje slovenske terminologije.
Keywords: podlubniki, strokovna terminologija, ozaveščanje, komunikacija, terminologija, ustaljena imena, zdravje gozdov, slovenksi jezik
Published in DiRROS: 27.01.2026; Views: 337; Downloads: 128
Full text (144,52 KB) |
7. Kako ravnamo s sečnimi ostanki za preprečevanje prenamnožitve podlubnikov?Maarten De Groot, Simon Zidar, Luka Capuder, Martin Križaj, Tine Hauptman, Marija Kolšek, 2025, professional article Keywords: sečni ostanki, podlubniki, varstvo gozdov
Published in DiRROS: 27.01.2026; Views: 235; Downloads: 78
Full text (390,24 KB) |
8. Distribution and habitat selection of Western (Osmoderma eremita) and Eastern hermit beetle (O. barnabita) in the contact area in SloveniaAl Vrezec, Špela Ambrožič Ergaver, Andrej Kapla, Maarten De Groot, Andrej Kobler, Klemen Čandek, Alenka Žunič Kosi, 2025, published scientific conference contribution abstract Keywords: pheromone traps, Hermit Beetle, genetic structure
Published in DiRROS: 21.01.2026; Views: 195; Downloads: 107
Full text (3,81 MB)
This document has many files! More... |
9. European beech decline in Slovenia is caused by a complex diseaseNikica Ogris, Ana Brglez, Andreja Kavčič, Janja Zajc Žunič, Maarten De Groot, Barbara Piškur, 2026, original scientific article Abstract: In recent decades, the average crown defoliation of European beech (Fagus sylvatica) in Central Europe has been steadily increasing, resulting in a decline in tree vitality. This study aimed to identify the key factors contributing to this deterioration. Forty healthy and 40 damaged European beech trees were felled on a systematic 16 × 16 km grid, and all tree parts were sampled for fungi and insects. Additionally, soil samples were collected for Phytophthora testing. Of 6400 cultured samples, 5828 fungal cultures were classified into 251 morphotypes. The twenty most frequent morphotypes from each tree part were selected for further molecular identification, revealing 44 different fungal taxa. The most frequently isolated fungal species were Neonectria coccinea, Neohendersonia kickxii, Apiognomonia errabunda and Aureobasidium pullulans—all well-known and common endophytes. Surprisingly, Phytophthora species were detected in only three of the 80 soil samples. The most frequent insect species were Orchestes fagi, Phyllaphis fagi, Psilocorsis reflexella and Phyllonorycter maestingella. The results indicate that the decline of European beech in Central Europe is driven by a multifaceted interplay of biotic and abiotic factors, with fungi playing the most significant role. Analysis revealed distinct differences in fungal and insect communities across sampled tree parts, but not between healthy and damaged trees. This finding is crucial, as it shows that healthy trees host endophytes that can exhibit pathogenic traits under external stress factors. Therefore, resilience and sustainability of beech will depend on mitigation of stressors and implementation of adaptive management strategies that address the evolving environmental challenges.
Keywords: Fagus sylvatica, decline, complex disease, drought, climate change, sustainability
Published in DiRROS: 23.12.2025; Views: 274; Downloads: 135
Full text (2,62 MB)
This document has many files! More... |
10. |
