A research team has developed an advanced deep learning model, LKNet, to improve the accuracy of rice panicle counting in dense crop canopies.

A research team has developed a novel deep learning framework that integrates 3D radiative transfer modeling (RTM) with a knowledge-guided convolutional neural network (KGCNN) to accurately and dynamically retrieve maize leaf area index (LAI) across different years and growth stages.

A research team has introduced DepthCropSeg, a powerful, depth-informed crop segmentation approach that achieves near-supervised performance without the need for pixel-level manual annotations.