This Collection supports and amplifies research related to:
SDG 2 – Zero Hunger.
Computer vision is rapidly transforming plant sciences and agriculture by enabling high-throughput, precise, and scalable phenotyping and monitoring. This Collection invites Data Descriptors documenting the generation, curation, and validation of datasets that underpin computer vision applications across plant biology, crop science, and agricultural systems.
We welcome datasets derived from image-based phenotyping platforms, such as UAV and satellite imagery, field cameras, root imaging systems, hyperspectral or multispectral, and event-based (neuromorphic) imaging technologies. Relevant datasets may include annotated image sets for tasks such as plant disease detection, yield estimation, weed identification, crop classification, growth monitoring and tracking, real-time pest detection, pollinator tracking, leaf motion analysis, or trait quantification. Datasets supporting the training and evaluation of machine learning or deep learning models are particularly encouraged, provided they are well documented and openly accessible.
This Collection aims to support the development of reproducible, high-quality datasets that serve as benchmarks or foundational resources for the plant science and agricultural research communities. Contributions involving both model and non-model plant species, as well as data relevant to precision agriculture, sustainable farming, and food security, are highly welcome.
