Agricultural Application of Convolutional Neural Networks: A Case Study on Potato Plant Disease Detection Using Keras Image Generator and Data Augmentation Techniques

Abstract

Crop yields are severely impacted by plant diseases, leading to significant economic consequences. This study presents a plant disease prediction model that utilizes Convolutional Neural Networks (CNNs) and the Keras image augmentation technique. The CNN architecture includes multiple convolutional and pooling layers, as well as fully connected layers. Model training employs the Adam optimiser and categorical cross-entropy loss function, using a dataset of plant leaf images labelled with corresponding diseases for validation. After training the model with 10 epochs and a batch size of 32, an accuracy of 97% was achieved with a loss of 0.11. Validation accuracy and loss were 91% and 0.20, respectively. The Keras image augmentation technique was also evaluated for its effectiveness in generating new images from existing ones, which were used to test the model's ability to generalise when exposed to unseen data. The accuracy and loss on the test images were 95% and 0.25 and for augmented images were 94% and 0.22, respectively, demonstrating the model's potential for use in plant disease management as a diagnostic tool for farmers. This study is unique in combining CNN and Keras Image Generator for the detection of leaf diseases, and the results suggest that the proposed model could be useful for improving crop yields and farmers' income.

Plant phenotyping relevance

CNNと画像拡張を用いたジャガイモ葉の病害状態推定が研究の中心であり、モデル性能も検証しているため、植物フェノタイピング手法として含める。

Code and data availability

植物フェノタイピング解析を再現する公開資産であることを、入力本文と直接リンクから確認できなかったため保留しました。

No evidence-backed public reproduction asset is currently recorded.