Airborne hyperspectral imaging of cover crops through radiative transfer process-guided machine learning

Sheng Wang; Kaiyu Guan; Chenhui Zhang; Chongya Jiang; Qu Zhou; Kaiyuan Li; Ziqi Qin; Elizabeth A. Ainsworth; Jingrui He; Jun Wu; Dan Schaefer; Lowell E. Gentry; Andrew J. Margenot; Leo Herzberger

doi:10.1016/j.rse.2022.113386

Airborne hyperspectral imaging of cover crops through radiative transfer process-guided machine learning

Sheng Wang^*, Kaiyu Guan, Chenhui Zhang, Chongya Jiang, Qu Zhou, Kaiyuan Li, Ziqi Qin, Elizabeth A. Ainsworth, Jingrui He, Jun Wu, Dan Schaefer, Lowell E. Gentry, Andrew J. Margenot, Leo Herzberger

^*Corresponding author af dette arbejde

Publikation: Bidrag til tidsskrift/Konferencebidrag i tidsskrift /Bidrag til avis › Tidsskriftartikel › Forskning › peer review

Abstract

Cover cropping between cash crop growing seasons is a multifunctional conservation practice. Timely and accurate monitoring of cover crop traits, notably aboveground biomass and nutrient content, is beneficial to agricultural stakeholders to improve management and understand outcomes. Currently, there is a scarcity of spatially and temporally resolved information for assessing cover crop growth. Remote sensing has a high potential to fill this need, but conventional empirical regression operated with coarse-resolution multispectral data has large uncertainties. Therefore, this study utilized airborne hyperspectral imaging techniques and developed new process-guided machine learning approaches (PGML) for cover crop monitoring. Specifically, we deployed an airborne hyperspectral system covering visible to shortwave-infrared wavelengths (400–2400 nm) to acquire high spatial (0.5 m) and spectral (3–5 nm) resolution reflectance over 23 cover crop fields across Central Illinois in March and April of 2021. Airborne hyperspectral surface reflectance with high spectral and spatial resolution can be well matched with field data to quantify cover crop traits. Furthermore, the PGML models were pre-trained by synthetic data from soil-vegetation radiative transfer modeling (one million records), and then fine-tuned with field data of cover crop biomass and nutrient content. Results show that airborne hyperspectral data with PGML can achieve high accuracy to predict cover crop aboveground biomass (R² = 0.72, relative RMSE = 15.16%) and nitrogen content (R² = 0.69, relative RMSE = 16.59%) through leave-one-field-out cross-validation. Unlike the pure data-driven approach (e.g., partial least-squares regression), PGML incorporated radiative transfer knowledge and obtained higher predictive performance with fewer field data. Meanwhile, with field data for model fine-tuning, PGML predicted biomass more accurately than the inversion of radiative transfer models. We also found that the red edge has a high contribution in quantifying aboveground biomass and nitrogen content, followed by green and shortwave spectra. This study demonstrated the first attempt of utilizing hyperspectral remote sensing to accurately quantify cover crop traits. We highlight the strength of PGML in exploiting sensing data to quantify ecosystem variables to advance agroecosystem monitoring for sustainable agricultural management.

Originalsprog	Engelsk
Artikelnummer	113386
Tidsskrift	Remote Sensing of Environment
Vol/bind	285
ISSN	0034-4257
DOI	https://doi.org/10.1016/j.rse.2022.113386
Status	Udgivet - 1 feb. 2023
Udgivet eksternt	Ja

Adgang til dokumentet

10.1016/j.rse.2022.113386

Andre filer og links

Link to publication in Scopus

Citationsformater

Wang, S., Guan, K., Zhang, C., Jiang, C., Zhou, Q., Li, K., Qin, Z., Ainsworth, E. A., He, J., Wu, J., Schaefer, D., Gentry, L. E., Margenot, A. J., & Herzberger, L. (2023). Airborne hyperspectral imaging of cover crops through radiative transfer process-guided machine learning. Remote Sensing of Environment, 285, Artikel 113386. https://doi.org/10.1016/j.rse.2022.113386

@article{7e3fded265874521b0b8e6e385a69804,

title = "Airborne hyperspectral imaging of cover crops through radiative transfer process-guided machine learning",

abstract = "Cover cropping between cash crop growing seasons is a multifunctional conservation practice. Timely and accurate monitoring of cover crop traits, notably aboveground biomass and nutrient content, is beneficial to agricultural stakeholders to improve management and understand outcomes. Currently, there is a scarcity of spatially and temporally resolved information for assessing cover crop growth. Remote sensing has a high potential to fill this need, but conventional empirical regression operated with coarse-resolution multispectral data has large uncertainties. Therefore, this study utilized airborne hyperspectral imaging techniques and developed new process-guided machine learning approaches (PGML) for cover crop monitoring. Specifically, we deployed an airborne hyperspectral system covering visible to shortwave-infrared wavelengths (400–2400 nm) to acquire high spatial (0.5 m) and spectral (3–5 nm) resolution reflectance over 23 cover crop fields across Central Illinois in March and April of 2021. Airborne hyperspectral surface reflectance with high spectral and spatial resolution can be well matched with field data to quantify cover crop traits. Furthermore, the PGML models were pre-trained by synthetic data from soil-vegetation radiative transfer modeling (one million records), and then fine-tuned with field data of cover crop biomass and nutrient content. Results show that airborne hyperspectral data with PGML can achieve high accuracy to predict cover crop aboveground biomass (R2 = 0.72, relative RMSE = 15.16%) and nitrogen content (R2 = 0.69, relative RMSE = 16.59%) through leave-one-field-out cross-validation. Unlike the pure data-driven approach (e.g., partial least-squares regression), PGML incorporated radiative transfer knowledge and obtained higher predictive performance with fewer field data. Meanwhile, with field data for model fine-tuning, PGML predicted biomass more accurately than the inversion of radiative transfer models. We also found that the red edge has a high contribution in quantifying aboveground biomass and nitrogen content, followed by green and shortwave spectra. This study demonstrated the first attempt of utilizing hyperspectral remote sensing to accurately quantify cover crop traits. We highlight the strength of PGML in exploiting sensing data to quantify ecosystem variables to advance agroecosystem monitoring for sustainable agricultural management.",

keywords = "Aboveground biomass, Cover crop, Imaging spectroscopy, Nitrogen, Process-guided machine learning, Radiative transfer modeling",

author = "Sheng Wang and Kaiyu Guan and Chenhui Zhang and Chongya Jiang and Qu Zhou and Kaiyuan Li and Ziqi Qin and Ainsworth, {Elizabeth A.} and Jingrui He and Jun Wu and Dan Schaefer and Gentry, {Lowell E.} and Margenot, {Andrew J.} and Leo Herzberger",

note = "Publisher Copyright: {\textcopyright} 2022",

year = "2023",

month = feb,

day = "1",

doi = "10.1016/j.rse.2022.113386",

language = "English",

volume = "285",

journal = "Remote Sensing of Environment",

issn = "0034-4257",

publisher = "Elsevier Inc.",

}

TY - JOUR

T1 - Airborne hyperspectral imaging of cover crops through radiative transfer process-guided machine learning

AU - Wang, Sheng

AU - Guan, Kaiyu

AU - Zhang, Chenhui

AU - Jiang, Chongya

AU - Zhou, Qu

AU - Li, Kaiyuan

AU - Qin, Ziqi

AU - Ainsworth, Elizabeth A.

AU - He, Jingrui

AU - Wu, Jun

AU - Schaefer, Dan

AU - Gentry, Lowell E.

AU - Margenot, Andrew J.

AU - Herzberger, Leo

PY - 2023/2/1

Y1 - 2023/2/1

N2 - Cover cropping between cash crop growing seasons is a multifunctional conservation practice. Timely and accurate monitoring of cover crop traits, notably aboveground biomass and nutrient content, is beneficial to agricultural stakeholders to improve management and understand outcomes. Currently, there is a scarcity of spatially and temporally resolved information for assessing cover crop growth. Remote sensing has a high potential to fill this need, but conventional empirical regression operated with coarse-resolution multispectral data has large uncertainties. Therefore, this study utilized airborne hyperspectral imaging techniques and developed new process-guided machine learning approaches (PGML) for cover crop monitoring. Specifically, we deployed an airborne hyperspectral system covering visible to shortwave-infrared wavelengths (400–2400 nm) to acquire high spatial (0.5 m) and spectral (3–5 nm) resolution reflectance over 23 cover crop fields across Central Illinois in March and April of 2021. Airborne hyperspectral surface reflectance with high spectral and spatial resolution can be well matched with field data to quantify cover crop traits. Furthermore, the PGML models were pre-trained by synthetic data from soil-vegetation radiative transfer modeling (one million records), and then fine-tuned with field data of cover crop biomass and nutrient content. Results show that airborne hyperspectral data with PGML can achieve high accuracy to predict cover crop aboveground biomass (R2 = 0.72, relative RMSE = 15.16%) and nitrogen content (R2 = 0.69, relative RMSE = 16.59%) through leave-one-field-out cross-validation. Unlike the pure data-driven approach (e.g., partial least-squares regression), PGML incorporated radiative transfer knowledge and obtained higher predictive performance with fewer field data. Meanwhile, with field data for model fine-tuning, PGML predicted biomass more accurately than the inversion of radiative transfer models. We also found that the red edge has a high contribution in quantifying aboveground biomass and nitrogen content, followed by green and shortwave spectra. This study demonstrated the first attempt of utilizing hyperspectral remote sensing to accurately quantify cover crop traits. We highlight the strength of PGML in exploiting sensing data to quantify ecosystem variables to advance agroecosystem monitoring for sustainable agricultural management.

AB - Cover cropping between cash crop growing seasons is a multifunctional conservation practice. Timely and accurate monitoring of cover crop traits, notably aboveground biomass and nutrient content, is beneficial to agricultural stakeholders to improve management and understand outcomes. Currently, there is a scarcity of spatially and temporally resolved information for assessing cover crop growth. Remote sensing has a high potential to fill this need, but conventional empirical regression operated with coarse-resolution multispectral data has large uncertainties. Therefore, this study utilized airborne hyperspectral imaging techniques and developed new process-guided machine learning approaches (PGML) for cover crop monitoring. Specifically, we deployed an airborne hyperspectral system covering visible to shortwave-infrared wavelengths (400–2400 nm) to acquire high spatial (0.5 m) and spectral (3–5 nm) resolution reflectance over 23 cover crop fields across Central Illinois in March and April of 2021. Airborne hyperspectral surface reflectance with high spectral and spatial resolution can be well matched with field data to quantify cover crop traits. Furthermore, the PGML models were pre-trained by synthetic data from soil-vegetation radiative transfer modeling (one million records), and then fine-tuned with field data of cover crop biomass and nutrient content. Results show that airborne hyperspectral data with PGML can achieve high accuracy to predict cover crop aboveground biomass (R2 = 0.72, relative RMSE = 15.16%) and nitrogen content (R2 = 0.69, relative RMSE = 16.59%) through leave-one-field-out cross-validation. Unlike the pure data-driven approach (e.g., partial least-squares regression), PGML incorporated radiative transfer knowledge and obtained higher predictive performance with fewer field data. Meanwhile, with field data for model fine-tuning, PGML predicted biomass more accurately than the inversion of radiative transfer models. We also found that the red edge has a high contribution in quantifying aboveground biomass and nitrogen content, followed by green and shortwave spectra. This study demonstrated the first attempt of utilizing hyperspectral remote sensing to accurately quantify cover crop traits. We highlight the strength of PGML in exploiting sensing data to quantify ecosystem variables to advance agroecosystem monitoring for sustainable agricultural management.

KW - Aboveground biomass

KW - Cover crop

KW - Imaging spectroscopy

KW - Nitrogen

KW - Process-guided machine learning

KW - Radiative transfer modeling

UR - http://www.scopus.com/inward/record.url?scp=85146420425&partnerID=8YFLogxK

U2 - 10.1016/j.rse.2022.113386

DO - 10.1016/j.rse.2022.113386

M3 - Journal article

AN - SCOPUS:85146420425

SN - 0034-4257

VL - 285

JO - Remote Sensing of Environment

JF - Remote Sensing of Environment

M1 - 113386

ER -

Airborne hyperspectral imaging of cover crops through radiative transfer process-guided machine learning

Abstract

Adgang til dokumentet

Andre filer og links

Fingeraftryk

Citationsformater