2026/02/26 by Wee Fong Lee, Peter P. Ling, Aaron B. Wilson · 1 voice
Computer Science · Agricultural and Biological Sciences · Earth and Planetary Sciences · #Solar Radiation and Photovoltaics #Greenhouse Technology and Climate Control #Meteorological Phenomena and Simulations
paper · doi:10.21273/horttech05825-25
openalex publication_date 2026/02/26 · openalex created_date 2026/02/27 · openalex updated_date 2026/06/11
High tunnels are widely used by growers in the United States to extend the growing season, but their low-cost design often lacks temperature monitoring and automated ventilation. Consequently, crops can experience rapid increases in air temperature that may lead to heat stress or damage. Accurate 1-hour temperature forecasts can support timely manual ventilation and reduce crop risk. We evaluated the reuse of a machine learning (ML) artificial neural network (ANN) architecture, developed originally for solar radiation forecasting, for predicting internal high-tunnel temperatures. Three weather data sources were tested as model inputs: local weather station data, the National Oceanic and Atmospheric Administration’s High-Resolution Rapid Refresh (HRRR) forecasts, and HRRR data enhanced with solar radiation predictions from a previously developed ML-based solar radiation forecasting model. Models were trained using high-tunnel and weather data from Apr and Oct 2024 at two solar radiation thresholds (> 400 W·m –2 and > 100 W·m –2 ) tested on both the same 2024 (training-year) data and future data from Mar 2025 to assess model generalization. Results showed that for the training-year data, the enhanced HRRR feature group provided the most useful forecasts, particularly for locations without local weather data. Expanding training data to include data from > 100 W·m –2 broadened the model’s operating range, but sometimes reduced accuracy within 500 to 700 W·m –2 . When applied to future (2025) data, model performance degraded substantially; however, removing the date and time variables from the input features improved results, though they were still less than training-year accuracy. Models retrained using combined 2024 and 2025 datasets performed notably better, especially when trained with a solar radiation threshold > 100 W·m –2 , outperforming those trained solely on 2024 data. These findings demonstrate that the ANN structure can be repurposed effectively for high-tunnel temperature forecasting. They also underscore the importance of training data quality, feature (input variable) selection, and generalization strategy for reliable, real-world agricultural applications, where early temperature warnings can help growers minimize crop losses and improve management decisions. Looking forward, continuous learning approaches, such as retraining with new data or updating key input features such as solar radiation forecasts, may help sustain model performance as environmental conditions and tunnel characteristics evolve.