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

Abstract

Rooftop farms are urban green infrastructure integrating food production, ecological regulation, and public services, and their management increasingly relies on data-driven approaches. However, open built environments, microclimatic heterogeneity, and limited sensor deployment challenge continuous monitoring and short-term prediction of rooftop plant growth. This study proposes and validates a virtual sensor-driven digital twin system using a rooftop tomato case in Xiamen, China. The system adopts a five-layer architecture comprising data acquisition, transmission, modeling, processing, and application service layers. By coupling a Long Short-Term Memory (LSTM) weather prediction model with the Decision Support System for Agrotechnology Transfer (DSSAT) crop growth model, a predictive virtual sensor module was developed to forecast leaf area index (LAI), aboveground biomass, phenology, and yield for seven days. Results show that the system links environmental data acquisition, LSTM–DSSAT prediction, database storage, and three-dimensional visualization, transforming rooftop plant growth into an updatable, predictable, and visualized digital twin object. The coupled model showed high predictive accuracy, with R2 values of 0.9814 for LAI and 0.9966 for aboveground biomass, while supporting phenology and yield prediction. The system supports irrigation optimization, landscape management, and activity planning in sensor-constrained rooftop farms.

Plant phenotyping relevance

植物成長のLAI、地上部バイオマス、フェノロジー、収量を予測する仮想センサー・デジタルツインを開発し、精度検証しており、表現型推定手法が研究の中心である。

Code and data availability

The supplied blocks describe a rooftop tomato digital twin case study (LSTM–DSSAT virtual sensor, 3D models, sensor data), but contain no public dataset, image, code, or model deposit with availability language or author URLs. Data collection methods are described, but no repository or public asset is mentioned.

No evidence-backed public reproduction asset is currently recorded.