A comprehensive study on potato and tomato disease prediction using deep learning techniques

View at publisher Summarise with VIRAT
Authors: Sandeep Kumar, R. Guavathi, Milan Chakraborty
Cited by: 0

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

This study proposes a convolutional neural network (CNN) model for predicting potato leaf diseases, which is an important step towards effective disease control in agriculture. Based on recent advances in plant disease identification using deep learning, the proposed model uses CNN architectures to identify potato leaf images as healthy or diseased, thereby contributing to efficient and scalable agricultural monitoring. The dataset was divided into three groups: training (80%), validation (10%), and testing (10%), with the mixture used to improve the generalization of the model. The CNN model was built using the Adam optimizer and a sparse categorical cross-entropy loss function with accuracy as the main evaluation metric. The model was trained over many epochs so as to maintain stability and minimize overfitting; accuracy and loss metrics were checked during both training and validation run. Performance markers including accuracy and loss were shown throughout the epochs to reveal the model evolution and dependability after training and testing with previously unknown data. This CNN approach is in line with results from related research showing that specialized CNN architectures have been helpful in spotting many crop diseases. The findings supported the model’s capacity to differentiate between diseased and normal leaves, highlighting its relevance for automated disease identification in precision farming. Including several environmental factors and expanding to other crops to support flexibility and practical applications in disease management will be future developments.

Fields of Study & Subjects

Smart Agriculture and AI Advanced Neural Network Applications Industrial Vision Systems and Defect Detection

Publication details

Journal / source
CRC Press eBooks
Pages
129–137
Publication date
25 March 2026
Language
EN
Document type
Book chapter