AI Summary & Key Takeaways
AI InsightThe results demonstrate that strong correlations, particularly between light–temperature and temperature–humidity, are better represented in the quantum model.
📌 3 Key Takeaways
Abstract
This study proposes a novel Quantum Ising Model (QIM)-based approach for the multi-objective optimisation of agricultural greenhouse systems under conditions of climatic variability. A real-time dataset of 4.860 records collected from operational greenhouses in Çanakkale was utilised, incorporating key environmental parameters such as temperature, humidity, light, CO₂, pH, and EC. The originality of this research lies in applying quantum-inspired optimisation to greenhouse automation, grounded in empirical field data. While most previous studies rely on classical multi-objective algorithms (e.g., NSGA, simulated annealing, genetic algorithms), this work evaluates cross-variable interactions within the Ising Hamiltonian framework. In the proposed method, energy functions were constructed for each greenhouse, and optimisation was carried out based on control parameters expressed through spin variables (heater, fan, misting, LED lighting, CO₂ enrichment, irrigation, pH balancing, and EC adjustment). The results demonstrate that strong correlations, particularly between light–temperature and temperature–humidity, are better represented in the quantum model. Moreover, compared to classical methods, the QIM-based approach yielded more balanced and robust solutions under uncertainty. The model optimises greenhouse climate control not only by addressing individual parameter targets but also by capturing the cross-interactions among variables. As a result, it provides a more holistic balance between energy efficiency, crop quality, and sustainability goals. This study represents one of the first field-data-driven applications of quantum optimisation in greenhouse automation and offers an innovative perspective on controlled environment agriculture.