Sign up for our daily Newsletter and stay up to date with all the latest news!

Subscribe I am already a subscriber

You are using software which is blocking our advertisements (adblocker).

As we provide the news for free, we are relying on revenues from our banners. So please disable your adblocker and reload the page to continue using this site.
Thanks!

Click here for a guide on disabling your adblocker.

Sign up for our daily Newsletter and stay up to date with all the latest news!

Subscribe I am already a subscriber

China: Predicting humidity in greenhouses based on machine learning

Prediction of greenhouse temperature and relative humidity is crucial, as it enables the forecasting of environmental parameters for manual intervention in advance.

However, temperature and relative humidity prediction systems face two critical limitations: inconsistent temporal resolution in data acquisition and the absence of standardized protocols for environmental data collection. These issues collectively lead to non-uniform control strategies that compromise system interoperability in agricultural applications. This research predicted temperature and relative humidity at different time intervals in South China greenhouses using the BPPSO, LSSVM, and RBF models, which have demonstrated their superiority in temperature and relative humidity prediction. The results showed that the R² of temperature and relative humidity predictions increased gradually with decreasing time intervals, with a 15-minute interval achieving the maximum value. The R² of the temperature predictions by the three models were 0.923, 0.923, and 0.912, while the R² for relative humidity predictions were 0.948, 0.952, and 0.948, respectively. The prediction accuracy for relative humidity was higher than that for temperature. All three models could be used to predict temperature and relative humidity in greenhouses in South China, with LSSVM showing a higher R² than the other two models. When the time interval was 15 minutes, the MAE, MAPE, and RMSE for temperature were 0.574, 1.941, and 0.867, respectively, whereas for relative humidity, they were 2.747, 3.383, and 3.907, respectively. The study concluded that the LSSVM model with a 15-minute time interval was suitable for predicting temperature and relative humidity in South China greenhouses.

This study provides a reference for early intervention in greenhouse temperature and relative humidity management.

Source: Nature Magazine