Development of a Cacao Disease Identification and Management App Using Deep Learning

TL;DR

The paper tackles limited data access and technical support for smallholder cacao farmers in the Philippines by developing an offline mobile app that embeds a deep learning classifier for cacao diseases and an infection-level model for black pod. It follows a developmental research approach, collecting ~4,980 images from three sites in Davao, training an EfficientNet-based classifier with data augmentation, and deploying the model on-device via a Flutter app with FlatBuffer export. The disease model achieved 96.93% validation accuracy, and field testing showed 84.2% agreement with expert assessments, demonstrating practical viability for field diagnosis without connectivity. This work enables timely disease management, supports sustainable cacao production, and aligns with national industry roadmaps by delivering an accessible, on-device DL tool and actionable management guidance.

Abstract

Smallholder cacao producers often rely on outdated farming techniques and face significant challenges from pests and diseases, unlike larger plantations with more resources and expertise. In the Philippines, cacao farmers have limited access to data, information, and good agricultural practices. This study addresses these issues by developing a mobile application for cacao disease identification and management that functions offline, enabling use in remote areas where farms are mostly located. The core of the system is a deep learning model trained to identify cacao diseases accurately. The trained model is integrated into the mobile app to support farmers in field diagnosis. The disease identification model achieved a validation accuracy of 96.93% while the model for detecting cacao black pod infection levels achieved 79.49% validation accuracy. Field testing of the application showed an agreement rate of 84.2% compared with expert cacao technician assessments. This approach empowers smallholder farmers by providing accessible, technology-enabled tools to improve cacao crop health and productivity.

Figures (8)

• Figure 1: Cacao disease identification and management system flow.
• Figure 2: System overview.
• Figure 3: Model overview.
• Figure 4: Breakdown of the data cleaning process.
• Figure 5: EfficientNet compound scaling.