Deep learning tool “LKNet” sets new benchmark for accurate rice panicle counting across growth stages
Peer-Reviewed Publication
Updates every hour. Last Updated: 30-Nov-2025 10:11 ET (30-Nov-2025 15:11 GMT/UTC)
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 cost-effective method to measure wheat plant height in unprecedented detail using drone-based cross-circling oblique (CCO) imaging and 3D canopy modeling.
A study on calcium bioavailability by researchers with the Arkansas Agricultural Experiment Station show that two calcium availability tests — a classic approach and a newer, speedier test — offer reliable results that can help poultry producers optimize calcium digestibility.
Jackson Somers, assistant professor of agricultural and resource economics in the College of Agriculture, Health and Natural Resources (CAHNR), investigated participation rates and the economics behind residential composting programs. Somers published his findings in the Journal of Environmental Economics and Management.
Somers found that on average, there is a 2.3-pound reduction in the amount of organic waste going into landfills per household per week when a city implements a composting program, using Austin, Texas as an example. This represents only about 30% of the average weekly food waste generated by a U.S. household.
A research team has developed PlantCaFo, an advanced few-shot plant disease recognition model powered by foundation models, capable of achieving high accuracy with only a handful of training images.