explainable-ai
Explainable AI (XAI) refers to machine learning methods designed to make the predictions and decision-making processes of complex models transparent and interpretable to humans, rather than functioning as opaque 'black boxes.' In plant science, this matters because researchers increasingly rely on AI to analyze images and data for tasks like disease detection or crop trait classification, and explainability allows scientists to verify that models are identifying biologically meaningful features—such as characteristic lesion patterns or leaf abnormalities—rather than spurious correlations. This transparency builds trust in AI-driven diagnostic tools and can even reveal new biological insights by highlighting which plant characteristics are most predictive of a given condition.
open_in_new WikipediaPubMed · 2026-07-02
Researchers built a lightweight AI model called PD-ViCo that can identify five brinjal (eggplant) diseases from photos with 99% accuracy, using a new dataset of field-harvested images from Bangladesh. The model also explains its decisions visually, making it practical for farmers to use in real conditions.
PD-ViCo achieved 99.12% classification accuracy and 97.76% F1-score across five disease classes, outperforming both standard Vision Transformer and Swin Transformer baselines.
A new dataset of 1,823 field-harvested brinjal images was created from real agricultural conditions in Bangladesh, covering Phomopsis Blight, Fruit and Shoot Borer, Fruit Cracking, Wet Rot, and Healthy samples.
Grad-CAM visualizations confirmed the model focuses on disease-affected regions of the fruit, providing interpretable evidence that supports trust in real-world deployment.
