Explore agricultural weed datasets worldwide
WeedAI is an open-source, searchable image data platform designed to accelerate the development of machine-learning algorithms for weed recognition in cropping systems. It consolidates existing, high-quality annotated datasets of both weeds and crops under a unified schema, and CC BY 4.0 license, making them easy to browse, filter download and incorporate into your pipelines.
Researchers and practitioners can explore data by crop or weed species, growth stage, location, annotation type, and photographic attributes, as well as contribute their own datasets. This collaborative approach ensures that everyone, from academic labs to industry developers, has access to the volume and variety of imagery needed for robust model training and deployment.