What question did this study set out to answer?

To evaluate the effectiveness of hyperspectral data and machine learning methods in estimating the yield of winter wheat.

January 14, 2026Open Access

Hyperspectral Yield Estimation of Winter Wheat Based on Information Fusion of Critical Growth Stages

Key Points

To evaluate the effectiveness of hyperspectral data and machine learning methods in estimating the yield of winter wheat.
Utilized canopy hyperspectral data collected during critical growth stages of winter wheat.
Calculated and analyzed correlations of 18 vegetation indices with crop yield.
Employed Successive Projections Algorithm to identify key spectral bands and Recursive Feature Elimination for feature selection.
Compared performance of four machine learning models: Random Forest, Deep Forest, Support Vector Regression, and Gaussian Process Regression.
Highest correlations observed between vegetation indices and grain yield during flowering and grain-filling stages.
Key bands identified mostly in the near-infrared and short-wave infrared regions.
The Deep Forest model achieved the best performance with R2 = 0.786 and RMSE = 641.470 kg·hm−2.

Abstract

Timely and accurate crop yield estimation is vital for food security and management decision-making. Integrating remote sensing with machine learning provides an effective solution. In this study, based on canopy hyperspectral data collected by an ASD FieldSpec 3 handheld spectrometer during the critical growth stages of winter wheat, 18 vegetation indices (VIs) were systematically calculated, and their correlation with yield was analyzed. At the same time, a continuous projection algorithm, Successive Projections Algorithm (SPA), was used to screen the characteristic bands. Recursive Feature Elimination (RFE) was employed to select optimal features from VIs and characteristic spectral bands, facilitating the construction of a multi-temporal fusion feature set. To identify the superior yield estimation approach, a comparative analysis was conducted among four machine learning models: Deep Forest (DF), Support Vector Regression (SVR), Random Forest (RF), and Gaussian Process Regression (GPR). Performance was evaluated using the coefficient of determination (R2), root mean square error (RMSE), and relative root mean square error (rRMSE). Results indicate that the highest correlations between VIs and grain yield were observed during the flowering and grain-filling stages. Independent analysis showed that VIs reached absolute correlations of 0.713 and 0.730 with winter wheat yield during the flowering and grain-filling stages, respectively, while the SPA further identified key bands primarily in the near-infrared and short-wave infrared regions. On this basis, integrating multi-temporal features through RFE significantly improved the accuracy of yield estimation. Among them, the DF model with the fusion of flowering and filling stage features performed best (R2 = 0.786, RMSE = 641.470 kg·hm−2, rRMSE = 15.67%). This study demonstrates that combining hyperspectral data and VIs from different growth stages provides complementary information. These findings provide an effective method for crop yield estimation in precision agriculture.

Read Full Paperexternally

Bookmark

View Full Paper

Cite This Study

Wang et al. (Mon,) studied this question.

synapsesocial.com/papers/6966e6f513bf7a6f02bfefa8 https://doi.org/https://doi.org/10.3390/agronomy16020186

Bookmark

View Full Paper