A deep learning architecture for leaf water potential prediction in Populus euramericana ‘I-214’ from hyperspectral reflectance
These results demonstrate that the proposed CIDL framework provides a generalizable solution for small-sample physiological hyperspectral analysis and offers a reliable, non-destructive pathway for tree water-stress monitoring, with strong potential for applications in smart forestry management.
Authors
- Zhong-Yi Pang
- Heng-Fang Wang
- Hui Li (ORCID: https://orcid.org/0000-0001-9198-3951)
- Zhaokui Li (ORCID: https://orcid.org/0000-0002-5331-7664)
- Xuekai Sun
- Zhuo-Qun Fang
- Jia-xu Guo
- Xue-Wei Gong
- Yan-Hui Peng
- Qing-Song Yu
- Guang-You Hao
Institutions
- Shenyang Aerospace University (CN)
- Ministry of Ecology and Environment (CN)
- State-owned Assets Supervision and Administration Commission of the State Council (CN)
- Institute of Ecology and Geography (MD)
- Institute of Applied Ecology (CN)
- Xinjiang University (CN)
Publication Details
- Journal
- Frontiers in Plant Science
- Published
- 2026-01-26
- DOI
- https://doi.org/10.3389/fpls.2025.1709473
- Primary Topic
- Plant Water Relations and Carbon Dynamics
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- National Natural Science Foundation of China
- Chinese Academy of Sciences
- Natural Science Foundation of Liaoning Province
- Institute of Applied Ecology, Chinese Academy of Sciences