A digital twin and IoT-enabled framework for smart landscape systems in sustainable city engineering

The integration of green infrastructure is pivotal for sustainable city engineering, yet conventional landscape management paradigms often suffer from inefficiencies due to reactive, schedule-based maintenance and a lack of predictive capabilities. The emergence of Digital Twin (DT) technology, which creates dynamic virtual counterparts of physical entities, offers a transformative solution. This paper proposes a novel, integrated Internet of Things (IoT) and DT framework specifically designed for the intelligent management of urban landscape systems. The framework is architected into four synergistic layers: (1) a pervasive IoT sensing layer comprising a network of soil moisture, microclimate, and LiDAR sensors for real-time data acquisition; (2) a high-fidelity DT modeling layer that constructs and continuously updates a multi-physics virtual replica through the seamless integration of Building Information Modeling (BIM) and Geographic Information Systems (GIS), calibrated with machine learning algorithms; (3) a predictive simulation and analysis layer that leverages the DT to run scenario-based analyses for irrigation optimization, urban heat island mitigation, and vegetation health prognosis; and (4) an application and control layer that provides decision support and enables automated, adaptive control actions. The framework was rigorously validated through a six-month field deployment in a 20-hectare urban park in Beijing, China. Results demonstrated a 28% reduction in irrigation water consumption, a 15% increase in vegetation survival rate, and a 32% decrease in manual maintenance hours compared to a control zone managed by conventional methods. This research contributes a scalable, data-driven paradigm for enhancing the sustainability and resilience of urban green spaces, directly supporting global urban sustainability goals.