Imaging based AI modeling for Point of Care diagnostics of Potato Plant

Abstract

Abstract This work presents a lightweight imaging-based AI model for rapid, point-of-care diagnosis of potato leaf diseases. Using the PlantVillage dataset comprising approximately 3,000 labeled images across three classes— Healthy , Early Blight , and Late Blight —a transfer learning approach was implemented with the MobileNetV2architecture. The dataset was split into 80% training and 20% validation sets, with preprocessing and augmentation to enhance generalization. Trained for 10 epochs using the Adam optimizer (learning rate = 0.001), the model achieved a training accuracy of 96.8% and a validation accuracy of 93.7% , with respective losses of 0.13and 0.21 . Class-wise evaluation confirmed balanced precision and recall across all categories, while external testing yielded correct disease identification with 57.2% confidence . The model demonstrates that high diagnostic accuracy can be achieved on basic hardware, making it suitable for low-resource agricultural settings. Compared to complex multimodal architectures, this MobileNetV2-based design offers fast inference, minimal computational demand, and strong generalization—establishing an efficient foundation for real-time, AI-driven plant disease diagnostics.

Plant phenotyping relevance

ジャガイモ葉の病害状態を画像から推定するAI診断モデルの開発・検証が研究の中心であり、植物表現型の取得方法に該当する。

Code and data availability

The paper uses the public PlantVillage dataset (Kaggle, by Emmarex) and mentions an authors' code link (GitHub - mggm1982/Potato-Disease-Classification) plus a YouTube video explanation. However, the GitHub code URL is not among the allowed URLs, and the only matching allowed link (youtu.be/H-bHmpIJ4K0) is a video expl

No evidence-backed public reproduction asset is currently recorded.