From Prediction to Creation: Generative Plant Design
Plants · 26.06.2026 · 15 (13) · 1967
DOI: 10.3390/plants15131967 ↗Kurz gefasst
Übersichtsarbeit in der Zeitschrift Plants, online erschienen am 26.06.2026. Verfasst von Juan Ma und 3 weiteren Autor:innen. Beteiligte Einrichtung: Institute of Cereal Crops, Henan Academy of Agricultural Sciences, Zhengzhou 450002, China. Die Arbeit nennt 98 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Henan Academy of Agricultural Sciences, Henan Science and Technology Department, Science and Technology Project of Henan Province.
Abstract (Originalsprache)
Recent advances in generative modeling have shifted plant breeding from predictive selection to de novo generative design. This review outlines generative methods for navigating the design space and introduces the latent space as a continuous, designable representation that enables a transition from static plant design to dynamic adaptive response programs. We then categorize navigation of the latent space into three strategies: exploration through unconditional generation, guidance through conditional generation, and optimization through feedback loops. We propose a dual-loop generative artificial intelligence-enhanced Design–Build–Test–Learn framework for accelerated plant design. The inner computational loop performs Design–Predict–Optimize guided by causal constraints and virtual evaluators, while the outer experimental loop (Build–Test–Learn) validates elite designs through digital twins and field trials to bridge the reality gap. A proof-of-concept simulation for drought-tolerance design demonstrates the framework’s dual-loop logic and quantitative performance. We further identify five hierarchical challenges that hinder real-world application: the pitfall of continuity assumption, multi-modal data fusion, causal identifiability, and trustworthy evaluation, as well as pleiotropy and genetic load. Finally, we discuss limitations and risks across data, model, regulatory, and interpretability dimensions and highlight critical open questions for realizing dynamic, adaptive, and climate-resilient breeding. This review provides a biology-grounded, systematic framework for next-generation intelligent plant improvement.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Institute of Cereal Crops, Henan Academy of Agricultural Sciences, Zhengzhou 450002, China.
ORCID-Profile: Juan Ma
Förderung
- Henan Academy of Agricultural Sciences
- Henan Science and Technology Department
- Science and Technology Project of Henan Province
Zitieren
APA
Ma, J., Wang, Y., Qi, J., & Cheng, Z. (2026). From Prediction to Creation: Generative Plant Design. Plants, 15(13), 1967. https://doi.org/10.3390/plants15131967
Vancouver
Ma J, Wang Y, Qi J, Cheng Z. From Prediction to Creation: Generative Plant Design. Plants. 2026;15(13):1967. doi:10.3390/plants15131967
BibTeX
@article{Ma2026,
author = {Ma, Juan and Wang, Yanzhao and Qi, Jianshuang and Cheng, Zeqiang},
title = {From Prediction to Creation: Generative Plant Design},
journal = {Plants},
year = {2026},
volume = {15},
number = {13},
pages = {1967},
doi = {10.3390/plants15131967}
}
EUVIMED