Smart Agriculture and AI

The paper develops a UAV-based imaging pipeline to predict plant density in wheat and pea crops, showing high heritability across diverse intercropping scenarios.

MACISF is a deep learning framework for automated fruit quality evaluation, achieving high accuracy in classification, health detection, and defect localization.

This paper introduces LYM-1, a multi-crop yield prediction model for Canadian prairies using extensive yield, weather, and soil data, showing improved predictive performance and revealing agronomically relevant interactions.

This paper evaluates PSNet, a multimodal framework combining hyperspectral and RGB imaging, for early detection of Albugo candida in Arabidopsis thaliana, showing high accuracy but no consistent advantage of hyperspectral fusion over RGB alone.

This paper develops and evaluates an AI toolkit for detecting and mapping ragweed under climate change, showing improved performance with multi-domain training and satellite-based models.

This paper develops Drought-Spec-Net, a model for early tomato drought detection using Vis NIR data, achieving high accuracy and providing yield impact assessments.

YieldLearn estimates yield-related traits in durum wheat using physiological indicators and machine learning, showing moderate accuracy and feature importance.

DIRTNet, a hybrid deep learning model, accurately predicts root depth and diameter from FBG sensor data in both simulated and real maize root growth scenarios.

This paper introduces a regression-based framework to predict flowering time from sparse UAV observations, reducing the need for repeated data collection.

The paper uses standardized leaf imaging and vision encoders to capture disease response variation missed by human scoring, identifying genomic hotspots linked to disease symptoms.

OneGrow generates temporal plant images and organ masks, addressing the lack of paired data by jointly modeling wheat images and masks over time.

This paper compares segmentation methods for plant phenotyping, finding that pretrained vision transformers outperform color thresholding and supervised U-Nets in generalization across species and conditions.

The paper introduces a physics-informed hybrid deep learning model for spatiotemporal rice disease prediction, improving accuracy and interpretability using multi-source data.

This study applies YOLOv8 for automated detection of livestock gastrointestinal parasite eggs and cysts in microscopic images, achieving moderate performance metrics but highlighting data limitations.

The paper presents a pipeline for longitudinal plant disease phenotyping using time-series imaging, enabling objective quantification of disease progression in wheat rusts.

This paper develops a digital-twin framework that integrates video-derived feeding behavior with physiological data to improve precision nutrition in dairy cows, showing reduced prediction errors in dry matter intake.

RADIX is a deep learning framework that segments root anatomical structures across species and platforms, revealing genetic and environmental influences on root barriers.

MIRA automates fungal spore counting and sizing using YOLO deep learning, achieving high accuracy and efficiency compared to manual methods.

The paper develops an automated image analysis pipeline for plant phenotyping in controlled environments, using multispectral imaging and AI to extract and analyze phenotypic features across multiple crops.

The paper develops a Bayesian method to estimate soil water content from capacitive sensor data, enabling low-cost plant watering systems without destructive calibration.

PolliCrop is a computer vision pipeline that detects and identifies flower-visiting insects on sunflower plants, showing accurate performance in predicting visitation frequencies across genotypes.

RootQuant uses deep learning to automatically quantify root traits from minirhizotron images, achieving high accuracy across species without pixel-level annotations.

The paper introduces LeafMD, a multiregional image-text dataset and benchmark for vision-language modeling of plant diseases, highlighting performance gaps and benefits of agriculture-adapted models.

SeedMeasure quantifies seed size and morphology from images, offering a fast, open-source, and cross-platform tool validated across nine species.

This paper develops a deep learning framework for classifying, localizing, and segmenting guava diseases using image analysis, achieving high accuracy and transparency.

This paper evaluates dairy cow vocalization models across farms, showing that reliability varies by vocalization type and that cross-farm generalizability is limited for certain categories.

This paper develops a method to detect early plant stress using leaf movement analysis in lettuce and other crops, detecting stress within 1 hour using low-cost imaging and open-source algorithms.

This paper develops an efficient image processing pipeline for soil fauna monitoring by combining traditional computer vision with fine-tuned foundation models, reducing annotation effort and enabling large-scale ecological analysis.