Early Detection of Potato Disease Using an Enhanced Convolutional Neural Network-Long Short-Term Memory Deep Learning Model

Abstract

Potato diseases pose a significant threat to farmers, impacting potato crops’ productivity, quality, and financial stability. Among the most notorious diseases is late blight, caused by Phytophthora infestans, famously responsible for triggering the Irish Potato Famine in the 1840s. Late blight swiftly devastates potato foliage and tubers, particularly in damp, humid conditions. Another common disease is early blight, attributed to Alternaria solani. This disease affects various parts of the potato plant—leaves, stems, and tubers. It mainly shows up in the form of dark stains around the center of a bull’s eye on the leaves, bringing down both the yield and the crop quality. A model consisting of a Convolutional Neural Network - Long Short-Term Memory (CNN-LSTM) enhanced for potato disease detection was proposed in our paper. The dataset used was Z-score standardized before the training and testing process using the proposed CNN-LSTM model was started. The performance of the implemented model, CNN-LSTM, was analyzed alongside five traditional machine learning algorithms, namely Random Forest (RF), Extra Trees (ET), K-Nearest Neighbours (KNN), Adaptive Boosting (AdaBoost), and Support Vector Machine (SVM). Accuracy, sensitivity, specificity, F-score, and AUC were the metrics included in the evaluation, confirming the effectiveness of the models. The results of the experiments showed that our CNN-LSTM reached the highest accuracy at 97.1%.

Plant phenotyping relevance

ジャガイモ病害の植物状態をCNN-LSTMで検出し、複数手法との性能比較・検証を行うことが論文の中心であるため、植物フェノタイピング手法として含める。

Code and data availability

公開状態または取得可能な本文経路を確認できませんでした。

No evidence-backed public reproduction asset is currently recorded.