New and exciting development in the agricultural industry that makes use of AI

• vegetation
• plant
• crop
• cultivation
• stress
• agriculture

• A characterization of biotic stress experienced by coffee leaves using few-shot learning
• Using multivariate sensed data to develop a multi-label tiny ML machine learning model for active and optimal greenhouse microclimate management.
• Analysis of land potential for maize cultivation using geospatial technology in the Didessa river basin, Ethiopia
• A deep convolutional neural network based on an estimation of the virtual NIR channel was developed in order to segment damaged vegetation from RGB photographs.
• Deep learning was used in Maize Crop to detect diseases, predict severity, and calculate crop loss.
• A comprehensive analysis of machine learning approaches to livestock identification, including data sets, methodology, and potential future directions.
• Genus classification of silkworm pupae based on X-ray images with the use of non-destructive ensemble learning
• Prediction of Potassium Exchangeability in Soil Using Mid-Infrared Spectroscopy and Deep Learning: Moving from Prediction to Explainability
• Analysis based on conditional learning of the generalization capabilities of the model for plant culture.
• Optimizing nutrient levels for plant development in aquaponic systems by using machine learning on relatively limited training data sets
• Comparative research on biotic stress categorization of rice crop using deep neural networks that have been pre-trained
• Optimization strategies used within deep convolutional neural networks and applied to the categorization of olive diseases
• Deep Convolutional Neural Network-Based Models for Weed Identification in Greenhouse-Grown Peppers
• An investigation into how well deep learning algorithms can distinguish between weed and crop species when presented with a variety of image backgrounds.
• Agricultural data analysis using explainable artificial intelligence and interpretable machine learning
• Durum wheat yield estimation using machine learning
• In central China, the effect and economic value of using precision seeding and laser field leveling for winter wheat
  
• A discussion on the technology of the Internet of Things in agriculture
• Deep Learning-Powered Computer Vision Approaches for Use in Smart Agriculture Applications
• An investigation into the relationship between artificial intelligence and the agricultural and food processing industries
• Single tree point cloud data can be automatically recorded without the need for markers via rotational projection.
• Transfer learning for image classification of multi-crop leaf diseases using the VGG convolutional neural network
• The use of near-infrared hyperspectral images in order to estimate the true density of commercial biomass pellets.