The Plant Phenome Journal, Volume 9, Issue 1, December 2026.Abstract An agronomic trait such as stand count is important for cultivar development and crop management practices. Manually counting the number of plants is time consuming, labor‐intensive, and prone to error. The use of unoccupied aerial systems (UAS)‐collected red, green, blue (RGB) imagery in conjunction with advanced deep learning and image ...
Aliasghar Bazrafkan +1 more
wiley +1 more source
Diffusion-augmented YOLO26-Swin cascaded framework with hybrid SHAP-CAM for autonomous power grid inspection. [PDF]
Auton Intell SystStefenon SF +4 more
europepmc +1 more source
Transformer‐Based Contextual Modeling for Predicting Calories From Recipes
Applied AI Letters, Volume 7, Issue 3, October 2026.A transformer‐based regression model with token‐level attention pooling is proposed for predicting calorie content directly from unstructured recipe text. By fine‐tuning RoBERTa in an end‐to‐end manner, attention is learned to be focused on calorie‐relevant tokens such as ingredients, fats, and cooking methods.
Md. Siam Ansary, Amina Brinto
wiley +1 more source
SCT-YOLO: A Dual-Stream Defect Detection Network Utilizing Computational Shape, Texture, and Color Features. [PDF]
Sensors (Basel)Mou Z +6 more
europepmc +1 more source
Agrosystems, Geosciences &Environment, Volume 9, Issue 3, September 2026.Abstract Agricultural practices are constantly evolving due to changes in regulation, climate, and technology. Regulations in California resulted in phasing out rice (Oryza sativa L.) straw burning in the 1990s, leading to a range of alternative practices to manage the straw, which impact agronomic practices, air quality, ecosystem services, and ...
Luke J. Matthews +3 more
wiley +1 more source
A multi-class defect detection method for substations based on the improved YOLOv10n. [PDF]
Front Artif IntellHuang L +5 more
europepmc +1 more source
Deep Learning Pipeline for the Identification of Ground Beetles (Carabidae) in New Zealand
New Zealand Journal of Zoology, Volume 53, Issue 3, September 2026.The identification of invertebrates is often difficult and time‐consuming because of their high abundance and diversity. This limits the use of invertebrates in environmental monitoring and conservation. However, computer vision approaches combined with deep learning models offer a range of benefits to insect conservation, particularly for image‐based ...
Yuzhi Gong +2 more
wiley +1 more source
Made in the shade: Leaf responses of native wildflowers to single‐axis photovoltaic solar energy
PLANTS, PEOPLE, PLANET, Volume 8, Issue 5, Page 1599-1615, September 2026.As solar energy expands globally, balancing renewable power generation with biodiversity and ecosystem health has become an urgent challenge. This study investigated how native wildflowers respond at leaf level to the unique microclimates created by rotating solar panels in California's Central Valley.
Yudi Li +3 more
wiley +1 more source
Adaptive elastic convolution-based YOLO for peripheral blood smear cell detection. [PDF]
PLoS OneIssac NM, K R.
europepmc +1 more source
Wind Turbine Blade Crack Detection and Assessment in Images Using Machine Learning
Wind Energy, Volume 29, Issue 9, September 2026.ABSTRACT As the wind energy industry matures, inspection of wind turbine blades (WTBs) is shifting from a manual process involving rope access and grading of damage, towards unmanned aerial vehicle (UAV) photography and artificial intelligence‐aided processing of data.
Callum Rothon +2 more
wiley +1 more source