Robust Hyperspectral Estimation of Winter Wheat Aboveground Dry Biomass Using CARS-UVE Band Selection and Transfer-Oriented Validation.
Saved in:
| Title: | Robust Hyperspectral Estimation of Winter Wheat Aboveground Dry Biomass Using CARS-UVE Band Selection and Transfer-Oriented Validation. |
|---|---|
| Authors: | Zhu, Shiyou1 (AUTHOR), Chen, Yulong1,2 (AUTHOR), Wang, Yian1 (AUTHOR), Yang, Sha2 (AUTHOR), Feng, Meichen1 (AUTHOR), Yang, Wude1 (AUTHOR), Bai, Juan1 (AUTHOR), Li, Guangxin1 (AUTHOR) liguangxin@sxau.edu.cn |
| Source: | Remote Sensing. Jun2026, Vol. 18 Issue 12, p1997. 23p. |
| Subjects: | Biomass estimation, Model validation, Support vector machines, Winter wheat, Partial least squares regression, Dry matter content of plants, Spectral reflectance |
| Abstract: | Highlights: A pooled 70/30 split favored SG + CARS-UVE + SVR for winter wheat AGDB estimation. Repeated splits showed overlapping confidence intervals among the primary SG workflows. Full-season and same-window transfer tests changed model ranking and exposed limited transferability. Recurrent blue-green and red-edge regions were more defensible than a single selected-band set. Field hyperspectral sensing can estimate crop biomass, but model ranking may depend strongly on validation design. We evaluated winter wheat aboveground dry biomass (AGDB) estimation using 84 canopy spectra collected across two growing seasons and seven nitrogen-management treatments in Shanxi, China. Six spectral inputs were compared with CARS-UVE band selection, partial least squares regression (PLSR), and support vector regression (SVR). Under a conventional 70/30 pooled split, SG + CARS-UVE + SVR gave the highest apparent accuracy (R2 = 0.8864, RMSE = 0.1174 kg m−2, RPD = 2.9665). This advantage was not stable. Across 20 SG-based repeated splits, CARS-UVE-SVR reached a mean R2 of 0.7413 with a 95% confidence interval of 0.6941–0.7885, similar to full-band PLSR (0.7448, 0.7058–0.7837), and pairwise tests showed no significant R2 advantage. Cross-year transfer further favored simpler latent-variable models: SG + CARS-UVE + PLSR reached R2 = 0.7577 in the 2021 → 2022 direction, whereas the pooled best SVR model dropped to R2 = 0.3402. A stricter same-window cross-year analysis produced weak or negative R2 values, showing that broad phenological biomass gradients supported much of the pooled accuracy. Recurrent selected regions occurred near 436–441 nm, 506–516 nm, and 711–713 nm. These findings suggest that repeated and transfer-oriented validation should be used routinely before hyperspectral biomass models are interpreted for cross-season crop monitoring. [ABSTRACT FROM AUTHOR] |
| Copyright of Remote Sensing is the property of MDPI and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
|
Full text is not displayed to guests.
Login for full access.
|
|
Be the first to leave a comment!
