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.