LSTM-GRU hybrid model for multi-layer microclimate prediction in solar greenhouse.
Li B, Wang Z, Guo Y, Zhou X, Qiao B
Greenhouse Technology
Tomatoes and cucumbers growing in your local greenhouse could soon benefit from AI that keeps the air at each shelf height perfectly tuned — meaning fresher, cheaper produce year-round.
Inside a greenhouse, the air near the floor is different from the air near the ceiling — and plants at different heights have different needs. Scientists trained a computer model to predict exactly how warm and humid each layer of a greenhouse will be, using sensor data and equipment settings. The model was surprisingly accurate, which means farmers could soon use it to automatically adjust heating and ventilation for every part of the greenhouse, not just the room as a whole.
Key Findings
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.
chevron_right Technical Summary
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.
Abstract Preview
Precise microclimate control across vertical canopy layers is critical for optimizing crop production in horticulture solar greenhouses, yet existing prediction models fail to capture the complex s...
open_in_new Read full abstractAbstract copyright held by the original publisher.
Was this useful?
Want to tell us more? (optional)
Thanks for the note!
Something went wrong — please try again.
Too many submissions. Try again in an hour.
Gene editing removes 97% of celiac-triggering proteins from bread wheat
It could mean that people with celiac disease — roughly 1 in 100 worldwide — may one day safely eat bread made from real wheat, without sacrificing the taste...
Precision agriculture is a data-driven management approach that gathers and analyzes temporal, spatial, and individual plant information to guide agricultural decisions. For plant science, this technique enables detailed investigation of how plants respond to environmental conditions and management
arrow_forward Explore topic