Full-Spectrum Hyperspectral Modeling of Leaf Dry Matter Content Using a Stacked Ensemble Framework.

Abstract

The objective of this study was to assess the predictability of leaf dry matter content across a diverse range of plant species using hyperspectral reflectance data. The dataset encompassed leaves from multiple crops, including potatoes, beans, wheat, maize, peas, tomatoes, basil, and cucumbers, collected under varying growth conditions, cultivation systems, seasonal contexts, and developmental stages. As an initial benchmark, commonly used narrow-band spectral indices and their combinations were evaluated, but they exhibited limited predictive performance for dry matter content. Consequently, several full-spectrum machine learning models were trained and compared to assess their individual predictive ability. Given their complementary strengths, these models were integrated into a stacked ensemble framework to enhance overall accuracy. The resulting ensemble, combining the outputs of multiple base learners through a meta-learner, achieved a coefficient of determination of R2=0.896 on an independent test set, outperforming all individual models. The findings highlight the potential of a multi-model stacking approach to improve the accuracy and robustness of leaf biochemical property estimation from hyperspectral data.

Plant phenotyping relevance

ハイパースペクトル反射データから葉乾物含量を推定する機械学習手法を開発・比較・検証しており、植物形質の取得方法が研究の中心である。

Code and data availability

The supplied blocks describe the authors' hyperspectral leaf dry matter dataset and stacked ensemble modeling, but contain no data availability statement, no public deposit of spectra/phenotype data, and no author code or model release. The only URLs mentioned (indexdatabase.de, R-project.org, tidymodels.org, gaussianp

No evidence-backed public reproduction asset is currently recorded.