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.

Anew study by researchers at Simon Fraser University is shedding light on how the brain’s wiring in early childhood lays the foundation for attention skills— a key step toward characterizing healthy developmental patterns that could help identify young children at risk for attention-related challenges like ADHD.

Published in the journal eNeuro, the study examined how the brain’s structure and function develop and interact during the critical early childhood years. Importantly, the findings highlight early childhood as a window of opportunity for identifying and supporting children who may be at risk for attention difficulties.

“Think of it like a city,” explains Randy McIntosh, the study’s senior author and founder of SFU’s Institute for Neuroscience and Neurotechnology (INN). “The roads are the brain’s structure, and the traffic is the brain’s activity. In young kids at this age, it turns out the roads matter most. If the roads aren’t built well, traffic can’t flow smoothly, and that can affect how well kids can focus, switch tasks, and ignore distractions.”