One of the main challenges agricultural greenhouses face is accurately predicting environmental conditions to ensure optimal crop growth. However, the current prediction methods have limitations in handling large volumes of dynamic and nonlinear temporal data, which makes it difficult to make accurate early predictions. This paper aims to forecast a greenhouse’s internal temperature up to one hour in advance using supervised learning tools like Extreme Gradient Boosting (XGBoost) and Recurrent Neural Networks combined with Long-Short Term Memory (LSTM-RNN). The study uses the many-to-one configuration, with a sequence of three input elements and one output element. Significant improvements in the R², RMSE, MAE, and MAPE metrics are observed by considering various combinations. In addition, Bayesian optimization is employed to find the best hyperparameters for each algorithm. The research uses a database of internal data such as temperature, humidity, and dew point and external data such as temperature, humidity, and solar radiation, splitting the data into the year’s four seasons and performing eight experiments according to the two algorithms and each season. The LSTM-RNN model produces the best results for the metrics in summer, achieving an R² = 0.9994, RMSE = 0.2698, MAE = 0.1449, and MAPE = 0.0041, meeting the acceptability criterion of ±2 °C hysteresis.

The microclimate inside a greenhouse forecast has been a case of study in recent years; an adequate forecast of variables such as internal temperature helps farmers prevent losses in the harvest. In this investigation, the forecast of the greenhouse internal temperature is implemented through Recurrent Neural Networks (RNN) topology with Long-Short Term Memory (LSTM) algorithm. The analysis is performed with the many to one configuration for a sequence of three input elements and one output element for each of the year's four seasons. The metrics used for the analysis and validation of the data were the RMSE, MAE, R2, and Ceff. These metrics provide the level of efficiency and goodness of the RNN-LSTM showing how the variables considered provide significance to the forecast of one hour into the future of the internal temperature. It is shown that the LSTM algorithm within the RNN is an effective tool for a good internal temperature forecast in time series for each season, significantly helping the forecast of climatic variables inside a greenhouse.