A Spatiotemporal Multimodal Transformer for Pre-Harvest Apple and Pear Quality Prediction
Agronomy · 23.07.2026 · 16 (15) · 1399
DOI: 10.3390/agronomy16151399 ↗Kurz gefasst
Fachartikel in der Zeitschrift Agronomy, online erschienen am 23.07.2026. Verfasst von Zhengjie Fu und 6 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 56 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
This study addresses the problem of pre-harvest fruit commodity grade prediction in intelligent orchards. To overcome the limitations of conventional post-harvest grading systems, including delayed quality evaluation, the limited representation capability of single-modality approaches, and the difficulty of modeling heterogeneous agricultural information collected throughout the growing season, this study proposes STF-Former, a spatiotemporal multimodal Transformer framework for pre-harvest fruit quality prediction. Rather than relying solely on static visual observations, the proposed framework formulates fruit quality prediction as a multimodal spatiotemporal learning problem by jointly exploiting phenotypic evolution, environmental dynamics, and field management information across different growth stages. Through stage-aware temporal modeling and cross-modal representation learning, STF-Former captures the dynamic interactions between fruit developmental processes and environmental water–fertilizer conditions, providing a unified prediction framework for both commodity grades and key quality indicators. This design improves the interpretability of quality formation and establishes a methodological framework for integrating heterogeneous agricultural data in precision orchard management. Experimental results demonstrate that the proposed method achieves significant advantages in both classification and regression tasks. In the commodity grade classification task, STF-Former achieves an Accuracy of 0.887, a Precision of 0.875, a Recall of 0.861, a Macro-F1 score of 0.868, and an AUC of 0.924, substantially outperforming traditional machine-learning methods (Random Forest and XGBoost) as well as mainstream unimodal deep-learning models. In the regression task for key quality indicators, superior performance is consistently achieved across multiple agronomic metrics, where the mean absolute error (MAE) is 3.41 mm for fruit diameter, 11.85 g for single fruit weight, 0.057 for coloration index, 0.81 °Brix for soluble solid content, and 2.68 N for firmness, with an overall R2 reaching 0.846. These results validate the effectiveness and robustness of multimodal spatiotemporal learning for accurate pre-harvest fruit quality prediction. The proposed framework provides a practical technical solution for intelligent orchard management, harvest planning, and data-driven precision agriculture, while offering a scalable paradigm for integrating multimodal sensing and temporal learning in smart agricultural systems.
Zitieren
APA
Fu, Z., Shen, H., Shi, Y., Zhang, Y., Xiao, L., Li, Y., & Dong, M. (2026). A Spatiotemporal Multimodal Transformer for Pre-Harvest Apple and Pear Quality Prediction. Agronomy, 16(15), 1399. https://doi.org/10.3390/agronomy16151399
Vancouver
Fu Z, Shen H, Shi Y, Zhang Y, Xiao L, Li Y, et al. A Spatiotemporal Multimodal Transformer for Pre-Harvest Apple and Pear Quality Prediction. Agronomy. 2026;16(15):1399. doi:10.3390/agronomy16151399
BibTeX
@article{Fu2026,
author = {Fu, Zhengjie and Shen, Huaren and Shi, Yan and Zhang, Yiheng and Xiao, Luyao and Li, Ying and Dong, Min},
title = {A Spatiotemporal Multimodal Transformer for Pre-Harvest Apple and Pear Quality Prediction},
journal = {Agronomy},
year = {2026},
volume = {16},
number = {15},
pages = {1399},
doi = {10.3390/agronomy16151399}
}
EUVIMED