A deep learning architecture for leaf water potential prediction in Populus euramericana 'I-214' from hyperspectral reflectance.

Abstract

Introduction Leaf water potential (Ψ leaf ) is a fundamental physiological metric quantifying tree water status and forest drought stress, yet its measurement remains labor-intensive and destructive. Hyperspectral techniques show great promise for retrieving plant physiological traits; however, robust Ψ leaf estimation remains limited by three critical factors: unbalanced data distributions, the need for global-local feature synergy, and inherent uncertainty in point-based regression. Methods Here, we propose a deep learning framework (CIDL) that integrates: (1) a conditional generative adversarial network (CGAN) to generate balanced synthetic samples across the full Ψ leaf domain; (2) a feature extractor that combines Inception-ResNet with ACmix (IRAC) to capture local absorption features and long-range spectral dependencies jointly; and (3) a distribution-aware regression network (DARN) to explicitly model the target-variable distribution, thereby enhancing predictive reliability. The model was trained and evaluated using a dataset derived from dehydration experiments on leaves of young Populus euramericana 'I-214' trees, comprising 229 paired Ψ leaf and hyperspectral reflectance measurements, which were further augmented with 500 CGAN-generated synthetic samples to improve model robustness. Results CIDL achieved a prediction accuracy of R 2 = 0.78 and RMSE = 0.27 MPa on the test set, clearly outperforming traditional machine learning methods (mean R 2 = 0.66, mean RMSE = 0.34 MPa) and yielding a modest yet consistent improvement over mainstream deep learning approaches (mean R 2 = 0.76, mean RMSE = 0.28 MPa). Discussion 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.

Plant phenotyping relevance

葉のハイパースペクトル反射から葉水ポテンシャルという植物生理形質を推定する深層学習フレームワークを開発し、既存手法と比較検証しているため、植物フェノタイピング手法が中心である。

Code and data availability

The supplied blocks describe a paper-specific dataset (229 paired leaf water potential and hyperspectral measurements from Populus euramericana 'I-214') and the CIDL deep learning framework, but contain no public deposit, repository, or availability URL for the data, images, or code. The Data availability statement is仅

No evidence-backed public reproduction asset is currently recorded.