Integration of Deep Learning for Optimization of Coconut Farming in North Sulawesi through Disease Detection Based on Hybrid CNN and LSTM Approaches

Dyah Listianing Tyas (Universitas Prisma)
Andreuw Vandy Lengkong (Universitas Prisma)
Frendy Rocky Rumambi (Universitas Prisma)
Adrian Nicholas Lumowa (Universitas Prisma)

Informatik : Jurnal Ilmu Komputer
Vol 22 No 1 (2026): April 2026

This research aims to develop a palm leaf disease detection system based on a Convolutional Neural Network (CNN) and Bidirectional Long Short-Term Memory (BiLSTM) integrated into a mobile application. The CNN model is used to extract visual features from leaf images, while the BiLSTM serves to capture sequential dependencies, thereby improving classification accuracy. The implementation was carried out by connecting the model, which is served via a Flask API, and accessed by the mobile application using Ngrok as a tunneling service for testing. Test results show that the system is capable of detecting healthy leaf conditions with an accuracy rate of up to 99.7%, and provides descriptive information about the leaf's condition and preventive treatment recommendations. The integration of the model into a mobile application enables real-time plant health monitoring, making it an innovative solution to support farmers in increasing productivity and preventing losses due to disease outbreaks.