Adopting TOGAF Framework for Sustainable and Scalable Robusta Coffee Leaf Rust Management

Abstract

Robusta coffee (Coffea canephora) is a globally significant crop. However, managing Coffee Leaf Rust remains challenging due to the reliance on manual detection methods and the lack of structured technological integration. This study proposes a TOGAF-based framework as a scalable and adaptable solution for structuring Coffee Leaf Rust management strategies. The framework leverages enterprise architecture principles to integrate learning algorithms, image detection, and systematic plantation mapping within a structured approach that enhances data organization, rust severity visualization, and predictive analysis. The proposed framework provides a strategic roadmap for integrating technology into Coffee Leaf Rust detection and management by focusing on modularity, scalability, and stakeholder engagement. Unlike existing ad-hoc approaches, this framework is a foundation for future technology-driven solutions, balancing manual practices with structured digital adoption. As no prior research has combined TOGAF with agricultural disease management, this study presents a novel conceptual contribution that could guide future developments in smart agriculture. By adopting this framework, the Robusta coffee industry can move toward proactive, data-driven Coffee Leaf Rust management, fostering long-term resilience and productivity.