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

## TL;DR

This study uses hyperspectral data and machine learning to accurately predict leaf dry matter content across various crops and conditions.

## Contribution

A stacked ensemble framework is introduced to improve prediction accuracy of leaf dry matter content using full-spectrum data.

## Key findings

- Narrow-band spectral indices showed limited predictive performance for leaf dry matter content.
- A stacked ensemble model achieved an R2 of 0.896, outperforming individual models.
- The approach improves accuracy and robustness in estimating leaf biochemical properties.

## 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.