With the global population exceeding 8 billion, the urgency for innovative food production solutions has intensified.

Recent research aims to improve sustainable agricultural practices and mitigate the adverse effects of climate change on crop yield and quality.

Convolutional Neural Networks (CNNs) are increasingly being utilized for automated disease detection in crops, leveraging their ability to learn from extensive image datasets.

Modern sensing technologies, including remote sensing and hyperspectral imaging, are proving effective for early disease detection in agriculture.

A study led by Purdue University researchers, including PhD candidate Claudia Aviles Toledo, adapted a recurrent neural network to predict maize yield using remote sensing technologies and environmental data.

This research emphasizes the importance of multi-source data for accurate yield predictions, enabling forecasts up to three months before harvest.

Traditional plant phenotyping methods are labor-intensive and costly, but advancements in UAV and satellite remote sensing are streamlining data collection.

An enhanced YOLOv5 model has been introduced to improve the accuracy of counting shrimp larvae, addressing challenges posed by high-density populations.

The new CUIB-YOLO model effectively balances computational efficiency with detection accuracy, making it suitable for devices with limited resources.

Ablation studies confirmed that combining specific model improvements yielded superior detection performance while maintaining a reduced model size.

The integration of computer vision and automated detection systems enhances accuracy and reduces costs, making these technologies viable for small and mid-sized farms.

Given that the agricultural sector consumes a significant portion of the world's freshwater resources, effective monitoring of crop water stress is essential for sustainability.