A multi-sensor deep learning framework for spatiotemporal prediction and three-dimensional reconstruction of temperature and humidity fields in solar greenhouses
Smart Agricultural Technology · 2026-12 · 15 · 102517
DOI: 10.1016/j.atech.2026.102517 ↗Kurz gefasst
Fachartikel in der Zeitschrift Smart Agricultural Technology, 2026-12. Verfasst von Dongyu Wang und 14 weiteren Autor:innen. Die Arbeit nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: Innovative Research Group Project of the National Natural Science Foundation of China, National Natural Science Foundation of China.
Abstract (Originalsprache)
Accurate prediction of temperature and humidity fields in solar greenhouses is essential for precise environmental control and disease risk early warning. However, the microclimate exhibits significant spatiotemporal heterogeneity due to the asymmetrical envelope structure and the development of the crop canopy in solar greenhouses. Consequently, conventional single-point monitoring or purely time-series models struggle to accurately characterize its three-dimensional spatial distribution. To address this challenge, this study proposed a multi-sensor deep learning framework that integrated three-dimensional spatial coordinate embedding and sensor-level gated attention mechanisms. A CNN-BiLSTM-SA model was developed, which extracted local dynamic features via multi-scale convolution, captured long-term dependencies of environmental parameters using BiLSTM, and dynamically assigned weights to different sensors through a sensor-level gated attention mechanism according to environmental states. This enabled multi-step prediction and continuous three-dimensional reconstruction of temperature and humidity fields. The model was validated using multi-source sensor monitoring data collected throughout the entire growth cycle of cucumbers in a typical solar greenhouse. The results indicated that the proposed model achieves MAE, RMSE, and R² of 0.88°C, 1.236°C, and 0.92 for temperature, and 2.619%, 3.735%, and 0.93 for relative humidity. Relative to CNN-BiLSTM, sensor-level gated attention reduced temperature and humidity RMSE by 26.6% and 37.9%. Two-dimensional slices, three-dimensional field reconstructions, and time-series analysis at key nodes further demonstrated the model’s ability to effectively recover the dominant spatial structures and dynamic evolution patterns of the temperature and humidity fields. This study has achieved a precise characterization of the temperature and humidity fields in solar greenhouses, providing a high-accuracy data foundation and methodological support for zoned precise regulation and disease risk warning in solar greenhouses.
Förderung
- Innovative Research Group Project of the National Natural Science Foundation of China
- National Natural Science Foundation of China
Zitieren
APA
Wang, D., Yang, T., Lu, M., Xu, D., Wang, Z., Gu, X., Shen, J., Lu, T., Guo, J., He, J., Tang, C., Liu, Y., Ma, Y., Zhu, J., & Lv, C. (2026). A multi-sensor deep learning framework for spatiotemporal prediction and three-dimensional reconstruction of temperature and humidity fields in solar greenhouses. Smart Agricultural Technology, 15, 102517. https://doi.org/10.1016/j.atech.2026.102517
Vancouver
Wang D, Yang T, Lu M, Xu D, Wang Z, Gu X, et al. A multi-sensor deep learning framework for spatiotemporal prediction and three-dimensional reconstruction of temperature and humidity fields in solar greenhouses. Smart Agricultural Technology. 2026;15:102517. doi:10.1016/j.atech.2026.102517
BibTeX
@article{Wang2026,
author = {Wang, Dongyu and Yang, Taiguo and Lu, Muxin and Xu, Demin and Wang, Zhi and Gu, Xinyu and Shen, Jiahang and Lu, Tiangang and Guo, Jia and He, Jiyuan and Tang, Chao and Liu, Yinchi and Ma, Yuntao and Zhu, Jinyu and Lv, Chunli},
title = {A multi-sensor deep learning framework for spatiotemporal prediction and three-dimensional reconstruction of temperature and humidity fields in solar greenhouses},
journal = {Smart Agricultural Technology},
year = {2026},
volume = {15},
pages = {102517},
doi = {10.1016/j.atech.2026.102517}
}
EUVIMED