Using Sentinel-2 Satellite Images to Estimate Traits of Forage Grasslands

In this project, regression models based on data from field measurements and spectral information extracted from satellite imagery were used to estimate traits of forage grasslands; dry matter yield, canopy average height and total leaf chlorophyll. Four fields at SLUs Röbäcksdalen field station wer...

Descripción completa

Detalles Bibliográficos
Autor principal: Zeiner, Niklas
Formato: H2
Lenguaje:Inglés
sueco
Publicado: SLU/Dept. of Agricultural Research for Northern Sweden 2021
Materias:
_version_ 1855572752680878080
author Zeiner, Niklas
author_browse Zeiner, Niklas
author_facet Zeiner, Niklas
author_sort Zeiner, Niklas
collection Epsilon Archive for Student Projects
description In this project, regression models based on data from field measurements and spectral information extracted from satellite imagery were used to estimate traits of forage grasslands; dry matter yield, canopy average height and total leaf chlorophyll. Four fields at SLUs Röbäcksdalen field station were sampled on 22 occasions and a total of 198 samples, including measurement of the highest plant, canopy height, leaf chlorophyll content, canopy spectral reflectance and biomass were collected. Two regression methods, partial least squares (PLS) and support vector machines (SVM), were used to build regression models using different subsets of the available spectral information. Model calibration was performed with 2/3 of the dataset and model validation was performed with the remaining 1/3 of the dataset. It was shown that the models built with SVM outperformed the models built with PLS, during both calibration and validation as well as for all different traits and subsets of spectral information. Field measurement and regression model results were discussed and limitations, their significance and possible improvements were considered. It was concluded that using spectral information from satellite images is a promising approach for estimation of traits in the field and could be used to build tools as a tool to support farmers’ decision making.
format H2
id RepoSLU16481
institution Swedish University of Agricultural Sciences
language Inglés
swe
publishDate 2021
publishDateSort 2021
publisher SLU/Dept. of Agricultural Research for Northern Sweden
publisherStr SLU/Dept. of Agricultural Research for Northern Sweden
record_format eprints
spelling RepoSLU164812024-04-22T08:13:37Z Using Sentinel-2 Satellite Images to Estimate Traits of Forage Grasslands Zeiner, Niklas Remote sensing Forage grasslands Sentinel-2 Dry matter yield Canopy average height Total leaf chlorophyll content Partial least squares Support vector machines In this project, regression models based on data from field measurements and spectral information extracted from satellite imagery were used to estimate traits of forage grasslands; dry matter yield, canopy average height and total leaf chlorophyll. Four fields at SLUs Röbäcksdalen field station were sampled on 22 occasions and a total of 198 samples, including measurement of the highest plant, canopy height, leaf chlorophyll content, canopy spectral reflectance and biomass were collected. Two regression methods, partial least squares (PLS) and support vector machines (SVM), were used to build regression models using different subsets of the available spectral information. Model calibration was performed with 2/3 of the dataset and model validation was performed with the remaining 1/3 of the dataset. It was shown that the models built with SVM outperformed the models built with PLS, during both calibration and validation as well as for all different traits and subsets of spectral information. Field measurement and regression model results were discussed and limitations, their significance and possible improvements were considered. It was concluded that using spectral information from satellite images is a promising approach for estimation of traits in the field and could be used to build tools as a tool to support farmers’ decision making. SLU/Dept. of Agricultural Research for Northern Sweden 2021 H2 eng swe https://stud.epsilon.slu.se/16481/
spellingShingle Remote sensing
Forage grasslands
Sentinel-2
Dry matter yield
Canopy average height
Total leaf chlorophyll content
Partial least squares
Support vector machines
Zeiner, Niklas
Using Sentinel-2 Satellite Images to Estimate Traits of Forage Grasslands
title Using Sentinel-2 Satellite Images to Estimate Traits of Forage Grasslands
title_full Using Sentinel-2 Satellite Images to Estimate Traits of Forage Grasslands
title_fullStr Using Sentinel-2 Satellite Images to Estimate Traits of Forage Grasslands
title_full_unstemmed Using Sentinel-2 Satellite Images to Estimate Traits of Forage Grasslands
title_short Using Sentinel-2 Satellite Images to Estimate Traits of Forage Grasslands
title_sort using sentinel-2 satellite images to estimate traits of forage grasslands
topic Remote sensing
Forage grasslands
Sentinel-2
Dry matter yield
Canopy average height
Total leaf chlorophyll content
Partial least squares
Support vector machines