Control

The use of antibiotics is not permitted in Switzerland; moreover, no other medication exists to combat European foul brood. Hives with symptoms must therefore be destroyed in order to limit the outbreak, and the contaminated material must be sanitised. Since prevention is the best cure, early detection is desirable. Numerous studies have been undertaken and documents have been created at the Swiss Bee Research Centre and elsewhere to draw the attention of beekeepers to these problems and inform them about the causes and the control measures to be implemented.

Merkblatt zur erkennung von Bienenbrutkrankheiten (German (PDF, 357 kB, 18.10.2017) and French (PDF, 226 kB, 02.02.2017))
M. Tschumi (2011)

Machine learning-powered segmentation of forage crops in RGB imagery through artificial sward images.

Institutional Repository Agroscope

Moreno H., Rueda-Ayala C., Rueda Ayala V. P., Ribeiro A., Ranz C., Andújar D.

Machine learning-powered segmentation of forage crops in RGB imagery through artificial sward images.

Agronomy, 15, (2), 2025, Article 356.

Téléchargement anglais (16087 kB)

Résumé:

Accurate assessment of forage quality is essential for ensuring optimal animal nutrition. Key parameters, such as Leaf Area Index (LAI) and grass coverage, are indicators that provide valuable insights into forage health and productivity. Accurate measurement is essential to ensure that livestock obtain the proper nutrition during various phases of plant growth. This study evaluated machine learning (ML) methods for non-invasive assessment of grassland development using RGB imagery, focusing on ryegrass and Timothy (Lolium perenne L. and Phleum pratense L.). ML models were implemented to segment and quantify coverage of live plants, dead material, and bare soil at three pasture growth stages (leaf development, tillering, and beginning of flowering). Unsupervised and supervised ML models, including a hybrid approach combining Gaussian Mixture Model (GMM) and Nearest Centroid Classifier (NCC), were applied for pixel-wise segmentation and classification. The best results were achieved in the tillering stage, with R2 values from 0.72 to 0.97 for Timothy (α = 0.05). For ryegrass, the RGB-based pixel-wise model performed best, particularly during leaf development, with R2 reaching 0.97. However, all models struggled during the beginning of flowering, particularly with dead grass and bare soil coverage

ISSN en ligne: 2073-4395
Digital Object Identifier (DOI): https://doi.org/10.3390/agronomy15020356
ID publication (Code web): 58854 Envoyer par e-mail

Début de la page

Tierseuchenverordnung - Abschnitt: Sauerbrut der Bienen (German, French and Italian)

Technische Weisungen des BLV - Sauerbrut (German, French and Italian)

Main Navigation

Agroscope

Search

Breadcrumb

Control

Machine learning-powered segmentation of forage crops in RGB imagery through artificial sward images.