A research team has developed CitrusGAN, a generative adversarial network (GAN)-based deep learning framework that reconstructs precise 3D citrus CT models from just a few low-cost X-ray images.

A research team developed a 3D deep learning–based panoptic segmentation model that combines semantic and instance segmentation to map plant tissue microstructures from X-ray micro-computed tomography (CT) images.

A research team has developed a multimodal machine vision model that can accurately predict the flowering, or anthesis, time of individual wheat plants—up to two weeks in advance.

A research team has developed a deep learning-based framework that allows agricultural robots to identify new weed species using only a few training images.

A research team has developed PhenoRob-F, an autonomous, cross-row, field phenotyping robot designed to collect high-resolution data on crop growth, yield, and stress response.

A research team has developed a neural network-based approach to automatically generate realistic 3D models of plant leaves—each labeled with precise morphological traits such as length and width.

A research team has developed a novel way to detect disease resistance in loblolly pine (Pinus taeda L.) using near-infrared (NIR) spectroscopy, offering a faster and more objective alternative to traditional visual inspection.