Urgent.News

What's breaking now, across thousands of outlets.

AI

Tested on mushrooms, an AI model shows potential for detecting crop stress with far fewer computations

A new artificial intelligence (AI) model can detect stress in agricultural crops using a nondestructive imaging technique, allowing changes in crop health to be monitored over time. Developed by a team of researchers at Penn State, the new model shows promise for accurately detecting crop stress caused by drought, disease, nutrient deficiency and other causes while using less computing power than…

Tested on mushrooms, an AI model shows potential for detecting crop stress with far fewer computations

Researchers at Penn State have developed an artificial intelligence model capable of detecting crop stress using nondestructive imaging. The new model, named PSUMamba, shows promise for accurately identifying stress caused by drought, disease, nutrient deficiency and other factors while using less computing power than some existing AI methods.

Hyperspectral imaging, which captures changes in agricultural products and crops across time, can be computationally expensive. To address this, the researchers created PSUMamba with three separate processing pathways: one analyzing spectral information, another examining changes over time, and the third analyzing spatial features and patterns within crop images.

These pathways work together to improve the model's ability to identify crop stress. The researchers tested the model on white button mushrooms, an economically important crop in Pennsylvania, as postharvest quality degradation is a significant challenge in the industry. By subjecting the mushrooms to controlled stress treatments, the team evaluated the model's ability to detect various types of stress.

The PSUMamba model achieved an impressive average accuracy of 94.47%, sensitivity of 98.98% and AUC-ROC of 99.36%. Compared to a similar Vision Transformer model, PSUMamba uses approximately 10 times fewer computational operations to process data and produce predictions. The study's findings suggest that the AI model could be adapted to monitor other crops and stress factors in real-world agricultural settings, potentially helping producers make more informed decisions and improve sustainability.

Written by urgent.news from Phys.org's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.

Read the original at phys.org →

More in AI

How to Verify AI-Generated Code With Evidence

An AI coding agent says the change is complete. The tests pass. Is that enough to merge? Not always. The code and its tests may share the same mistaken assumption.

  • Define concrete behavior before AI code changes.
  • Run application as recommended by Claude Code team.
  • Use tests for different failure modes and edge cases.

More from Friday 20 November →