A condition-aware retrieval-augmented decision support framework for tomato cultivation management
Frontiers in Plant Science · 18.06.2026 · 17
DOI: 10.3389/fpls.2026.1802748 ↗Kurz gefasst
Fachartikel in der Zeitschrift Frontiers in Plant Science, online erschienen am 18.06.2026. Verfasst von Yiqun Wang und 4 weiteren Autor:innen. Beteiligte Einrichtung: School of Automation, Beijing Information Science & Technology University, Beijing, China. Die Arbeit nennt 46 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Tomato cultivation management requires decisions that depend on growth stage, environment, and production scenarios. Retrieval-augmented generation (RAG) can ground large language model (LLM) outputs in external knowledge, but conventional retrieval often ignores such conditional constraints, leading to evidence that is topically relevant yet condition-inapplicable. This study develops TSCA-RAG, a condition-aware RAG framework for tomato cultivation question answering. TSCA-RAG extracts temporal, environmental, and contextual conditions from user queries using a structured label set and employs TSCAF-Retrieval, which combines semantic retrieval, BM25 keyword retrieval, and metadata-based condition retrieval through adaptive fusion and a cross-strategy consistency reward. A tomato cultivation knowledge base was constructed as fine-grained knowledge units with condition annotations and used to evaluate both retrieval and end-to-end generation. Retrieval performance was assessed using Recall@K, MRR, and NDCG@5, and answer quality was evaluated using similarity-based and rubric-based metrics under matched generation settings. On retrieval benchmarks, TSCA-RAG improves over Fine-tuned BGE-M3 with relative gains of 5.70% in Recall@1, 4.31% in Recall@5, and 4.76% in NDCG@5. In end-to-end evaluation, TSCA-RAG achieves higher Faithfulness, Correctness, and Utility, with an 11.29% increase in Utility compared with the strongest baseline RAG system. The condition extraction module attains an overall F1 of 81.8%, and a built-in confidence attenuation mechanism recovers approximately 53% of performance loss from single-dimension extraction errors. These results indicate that explicitly modeling cultivation conditions, combined with robust extraction and adaptive error mitigation, can improve evidence applicability and response usefulness for AI-assisted tomato cultivation decision support.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Automation, Beijing Information Science & Technology University, Beijing, China.
- Beijing Academy of Agriculture and Forestry Sciences Information Technology Research Center, Beijing, China.
- China Agricultural University College of Information and Electrical Engineering, Beijing, China.
Zitieren
APA
Wang, Y., Zhao, K., Li, H., Wang, R., & Chen, W. (2026). A condition-aware retrieval-augmented decision support framework for tomato cultivation management. Frontiers in Plant Science, 17. https://doi.org/10.3389/fpls.2026.1802748
Vancouver
Wang Y, Zhao K, Li H, Wang R, Chen W. A condition-aware retrieval-augmented decision support framework for tomato cultivation management. Frontiers in Plant Science. 2026;17. doi:10.3389/fpls.2026.1802748
BibTeX
@article{Wang2026,
author = {Wang, Yiqun and Zhao, Keqing and Li, Hongda and Wang, Ruihuan and Chen, Wenbai},
title = {A condition-aware retrieval-augmented decision support framework for tomato cultivation management},
journal = {Frontiers in Plant Science},
year = {2026},
volume = {17},
doi = {10.3389/fpls.2026.1802748}
}
EUVIMED