A research team has developed an innovative automated method, SSP-MambaNet, designed to address the challenge of identifying and counting missing virus-free strawberry seedlings in nutrient pots post-transplantation.

A research team has developed an approach to accelerate herbicide screening by integrating spectral image analysis with machine learning.

A research team has developed a novel high-throughput phenotyping platform, the Multispectral Automated Dynamic Imager (MADI), to monitor plant growth and stress in real time.

A research team demonstrates how advanced plant phenotyping and machine learning can quantify the hidden physiological signals of cold stress, transforming them into an accurate early-warning system.