Digital Twin for Predictive Monitoring of Crops: State of the Art

Recently, the use of digital twins in crop management has caught the attention of the agricultural sector. This technology is still in its early phases of deployment, and the state-of-the-art methodologies and adoption level of digital twins have not been thoroughly explored. To address this issue, this paper discusses the current trend of crop predictive monitoring using digital twin applications, focusing on the approaches used, adoption levels, and implementation challenges. Digital twins in crop management are still in the lab stage, and large-scale implementations in farming are not reported. Despite the benefits of increased crop productivity, the adoption of digital twins is hampered by challenges such as the complexity of modeling, poor high-speed Internet connectivity in rural areas, data security, significant investment costs, data accuracy, and a lack of knowledge about crop types and farming circumstances. Insights are provided to research academics, companies, and practitioners to help them understand the current state-of-the-art problems and future research prospects in the sector.