Multi-Parameter Prediction of Solar Greenhouse Environment Based on Multi-Source Data Fusion and Deep Learning

• Published in: Agriculture (Basel) Vol. 14; no. 8; p. 1245
• Main Authors: Yuan, Ming, Zhang, Zilin, Li, Gangao, He, Xiuhan, Huang, Zongbao, Li, Zhiwei, Du, Huiling
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 01.08.2024
• Subjects: Accuracy; Agricultural production; Agriculture; Air temperature; Artificial neural networks; Carbon dioxide; Carbon dioxide concentration; Comparative analysis; Computing time; Control algorithms; Couplings; Crop production; Crops; Data integration; Deep learning; Efficiency; Energy consumption; environmental acquisition system; Environmental conditions; environmental factor prediction; Environmental impact; Environmental monitoring; Error analysis; Farm buildings; Greenhouses; Heat transfer; Humidity; intelligent agricultural greenhouse; Internet of Things; Long short-term memory; Microclimate; Neural networks; Optimization; Parameters; Prediction models; Predictions; Radiation; Soil analysis; Soil temperature; solar greenhouse; Temperature; Time series; Trends; Ventilation; China
• ISSN: 2077-0472; 2077-0472
• DOI: 10.3390/agriculture14081245

In the process of agricultural production in solar greenhouses, the key to the healthy growth of greenhouse crops lies in accurately predicting environmental conditions. However, there are complex couplings and nonlinear relationships among greenhouse environmental parameters. This study independently developed a greenhouse environmental acquisition system to achieve a comprehensive method for the monitoring of the greenhouse environment. Additionally, it proposed a multi-parameter and multi-node environmental prediction model for solar greenhouses based on the Golden Jackal Optimization-Convolutional Neural Network-Bidirectional Gated Recurrent Unit-Self-Attention Mechanism (GCBS). The GCBS model successfully captures the complex nonlinear relationships in the greenhouse environment and accurately predicts changes in carbon dioxide concentration, air temperature and humidity, and soil temperature at different location nodes. To validate the performance of this model, we employed multiple evaluation metrics and conducted a comparative analysis with four baseline models. The results indicate that, while the GCBS model exhibits slightly higher computational time compared to the traditional Long Short-Term Memory (LSTM) network for time series prediction, it significantly outperforms the LSTM in terms of prediction accuracy for four key parameters, achieving improvements of 76.89%, 69.37%, 59.83%, and 56.72%, respectively, as measured by the Mean Absolute Error (MAE) metric.