Classification of Pests in Spinach Plants using the Convolutional Neural Network Method

Agriculture is a key sector that supports food security. Spinach plays an important role in meeting the nutritional needs of communities. However, the productivity of spinach plants in Malumbi Village has decreased due to pest attacks that have not been handled optimally by farmers. Lack of access to information leads to errors in pest identification and handling. Therefore, this study aims to develop a web-based classification system using the Convolutional Neural Network (CNN) method to assist farmers in recognizing pest types in spinach plants quickly and accurately through leaf imagery. CNNs were chosen for their ability to recognize complex visual patterns and generate accurate classifications based on imagery. The research stages include dataset collection, image preprocessing, CNN model training, and accuracy measurement. This research is expected to provide benefits in simplifying the process of digital pest identification, improving the accuracy of diagnosis, and assisting farmers in making more effective pest management decisions. The test results showed that the CNN model built was able to classify pest types with an accuracy rate of up to 84% in the validation data, and was successfully implemented in the form of a web application that could be used directly by farmers.