PubMed · 2026-04-22
Researchers built an AI model combining two types of neural networks to predict temperature and humidity at different heights inside Chinese solar greenhouses, achieving high accuracy. This could help growers automate climate control and boost crop yields by tailoring conditions to each layer of the plant canopy.
The hybrid AI model predicted temperature with a mean squared error of 1.2°C across canopy heights from 0.2 m to 2.0 m inside solar greenhouses.
The model integrates both environmental sensor data and equipment operational status, capturing complex spatial and time-based variation that simpler models miss.
The framework targets multi-layer microclimate prediction specifically in Chinese solar greenhouses, a widely used low-energy greenhouse design critical for winter food production.