Spatial, Temporal, and Vertical Variability of Greenhouse Microclimate and Artificial Neural Network-Based Prediction Under Korean Summer and Winter Conditions

Understanding greenhouse microclimatic variability is essential for precise environmental monitoring and control. This study evaluated temperature, relative humidity, CO2 concentration, and light intensity variability in Korean greenhouses during summer and winter, and developed artificial neural network (ANN) models to predict indoor temperature and relative humidity at different layers. A glass greenhouse and an arched-frame double-layer plastic greenhouse were monitored during summer and winter, respectively. A wireless sensor network was deployed at multiple spatial positions and vertical layers, and layer-specific artificial neural network (ANN) models were developed to predict indoor temperature and relative humidity at the top, middle, and bottom layers. The measured results revealed clear temperature and humidity stratification, with the top layer generally showing a higher temperature and lower humidity than the middle and bottom layers. In summer, temperatures reached 36.4 °C, while relative humidity ranged from 55% to 92%, while in winter, temperature varied from 3.4 °C to 35.0 °C and relative humidity ranged from 73% to 91%. Spatial contour mapping showed clear microclimatic gradients, and ANOVA with Tukey’s HSD tests confirmed significant differences among sensor locations (p < 0.05). The ANN models predicted indoor temperature with high accuracy, with R2 values generally above 0.95, while humidity prediction showed larger errors.