Airborne hyperspectral and Sentinel imagery to quantify winter wheat traits through ensemble modeling approaches
-
Published:2023-02-01
Issue:4
Volume:24
Page:1288-1311
-
ISSN:1385-2256
-
Container-title:Precision Agriculture
-
language:en
-
Short-container-title:Precision Agric
Author:
Pancorbo J. L., Alonso-Ayuso M., Camino C., Raya-Sereno M. D., Zarco-Tejada P. J., Molina I., Gabriel J. L., Quemada M.ORCID
Abstract
AbstractEarly prediction of crop production by remote sensing (RS) may help to plan the harvest and ensure food security. This study aims to improve the quantification of yield, grain protein concentration (GPC), and nitrogen (N) output in winter wheat with RS imagery. Ground-truth wheat traits were measured at flowering and harvest in a field experiment combining four N and two water levels in central Spain over 2 years. Hyperspectral and thermal airborne images coincident with Sentinel-1 and Sentinel-2 were acquired at flowering. A parametric linear model using all hyperspectral normalized difference spectral indices (NDSI) and two non-parametric models (artificial neural network and random forest) were used to assess their estimation ability combining NDSIs and other RS indicators. The feasibility of using freely available multispectral satellite was tested by applying the same methodology but using Sentinel-1 and Sentinel-2 bands. Yield estimation obtained the highest R2 value, showing that the visible and short-wave infrared region (VSWIR) had similar accuracy to the hyperspectral and Sentinel-2 imagery (R2 ≈ 0.84). The SWIR bands were important in the GPC estimation with both sensors, whereas N output was better estimated using red-edge-based NDSIs, obtaining satisfactory results with the hyperspectral sensor (R2 = 0.74) and with the Sentinel-2 (R2 = 0.62). When including the Sentinel-2 SWIR index, the NDSI (B11, B3) improved the estimation of N output (R2 = 0.71). Ensemble models based on Sentinel were found to be as reliable as those based on hyperspectral imagery, and including SWIR information improved the quantification of N-related traits.
Funder
Ministerio de Asuntos Económicos y Transformación Digital, Gobierno de España Comunidad de Madrid Ministerio de Ciencia e Innovación Universidad Politécnica de Madrid
Publisher
Springer Science and Business Media LLC
Subject
General Agricultural and Biological Sciences
Reference78 articles.
1. Adak, S., Bandyopadhyay, K. K., Sahoo, R. N., Mridha, N., Shrivastava, M., & Purakayastha, T. J. (2021). Prediction of wheat yield using spectral reflectance indices under different tillage, residue and nitrogen management practices. Current Science, 121(3), 402–413. https://doi.org/10.18520/cs/v121/i3/402-413 2. Aranguren, M., Castellón, A., & Aizpurua, A. (2020). Crop sensor based non-destructive estimation of nitrogen nutritional status, yield, and grain protein content in wheat. Agriculture (switzerland), 10(5), 148. https://doi.org/10.3390/agriculture10050148 3. Bastos, L. M., de Borja, F., Reis, A., Sharda, A., Wright, Y., & Ciampitti, I. A. (2021). Current status and future opportunities for grain protein prediction using on-and off-combine sensors: A synthesis-analysis of the literature. Remote Sensing. https://doi.org/10.3390/rs13245027 4. Breiman, L. (2001). Random forests. Machine Learning, 45, 5–32. https://doi.org/10.1023/A:1010933404324 5. Camino, C., González-Dugo, V., Hernández, P., Sillero, J. C., & Zarco-Tejada, P. J. (2018). Improved nitrogen retrievals with airborne-derived fluorescence and plant traits quantified from VNIR-SWIR hyperspectral imagery in the context of precision agriculture. International Journal of Applied Earth Observation and Geoinformation, 70(April), 105–117. https://doi.org/10.1016/j.jag.2018.04.013
|
|