Construction of a Virtual Sensor-Driven Digital Twin System for Plant Growth Monitoring on Rooftop Farms

Urban Farm DB summary

This study proposed and validated a virtual sensor-driven digital twin system for monitoring plant growth on rooftop farms, using a rooftop tomato case in Xiamen, China. The system integrates environmental data acquisition, LSTM–DSSAT model prediction, database storage, and 3D visualization. The coupled Long Short-Term Memory (LSTM) weather prediction model and Decision Support System for Agrotechnology Transfer (DSSAT) crop growth model achieved high predictive accuracy for leaf area index (R2=0.9814) and aboveground biomass (R2=0.9966), supporting 7-day forecasts for phenology and yield.