Digital twin-based applications in crop monitoring

Abstract

Technological advances in agriculture, particularly the use of digital twins, are having a significant impact on crop management. This article explores the use of digital twins in crop management, focusing on modeling methodologies, roles, implementation architecture, challenges, and prospects. The review identifies various modeling methods for digital twin development in crop monitoring, including physics-based, agent-based, data-driven, hybrid, and spatial models. These models provide up-to-date information on environmental conditions, soil moisture, and other variables affecting crop development and yield. Despite being in its early stages of implementation, digital twin technology is showing signs of progress, suggesting it could be the next step in crop farming's digitalization, increasing visibility and transparency, and improving decision-making processes. The review offers valuable insights and fills research gaps, enabling informed decisions for farmers, policymakers, and service providers to enhance productivity, sustainability, and resilience in modern agriculture.