Gated recurrent unit models outperform other Machine learning models in prediction of minimum temperature in greenhouse Based on local weather data

•The minimum temperature in greenhouse (Timin) is essential for greenhouse management.•Local weather data could be used to predict Timin.•Different machine learning including deep learning models were used to predict Timin.•The RF, SVM and MLR models generally underestimated Timin values.•The GRU model was more suitable for Timin prediction in lacking input variable.