Digital twin framework for precision downy mildew intervention in greenhouses using intelligent air quality sensing

Greenhouse cucumber production in the Shanxi region is persistently threatened by downy mildew (Pseudoperonospora cubensis), a fungal pathogen promoted by complex environmental factors including adverse AQI values, high humidity, and pronounced temperature fluctuations, causing annual yield losses of 15–25%. To address this challenge, this study introduces a digital twin (DT)-driven framework for precision disease intervention. The system integrates intelligent air quality sensing, a hybrid OOA-PSO optimization algorithm, and a PDE-based 3D disease model. A pivotal innovation is the incorporation of AQI as a dynamic driver, enabling high-fidelity 3D disease heatmaps that accurately capture the real-time spatiotemporal distribution of infection hotspots. Based on an edge-cloud DT paradigm, the architecture provides a continuous adaptive feedback loop, improving the efficiency and responsiveness of intervention strategies. Experiments calibrated with five years of Shanxi greenhouse data show a mean hotspot coverage rate of 96.7% (SD = 0.5%), a 31% reduction in spraying path length, and a 53% decrease in fungicide consumption compared with uniform spraying. Although these results are from simulation and need further real-world validation, they improve resource efficiency and reduce chemical emissions, supporting sustainable agriculture. This work offers a scalable, intelligent, and eco-friendly solution for advanced disease management in modern greenhouses.