Öffnen
Datum
2020-09-30Schlagwort
500 Naturwissenschaften 580 Pflanzen (Botanik) BiomasseGrünlandLidarFernerkundungDatenfusionVielblättrige LupineMetadata
Zur Langanzeige
Aufsatz
Remote sensing data fusion as a tool for biomass prediction in extensive grasslands invaded by L. polyphyllus
Zusammenfassung
Remote sensing data fusion is a powerful tool to gain information of quantitative and qualitative vegetation properties on field level. The aim of this study was to develop prediction models from sensor data fusion for fresh and dry matter yield (FMY/DMY) in extensively managed grasslands with variable degree of invasion by Lupinus polyphyllus. Therefore, a terrestrial 3d laser scanner (TLS) and a drone-based hyperspectral camera was used to collect high resolution 3d point clouds and hyperspectral aerial orthomosaics of four extremely heterogenous grasslands. From 3d point clouds multiple features (vegetation height, sum of voxel, point density and surface structure) were extracted and combined with hyperspectral data to develop an optimized biomass model from random forest regression algorithm to predict FMY and DMY (ntrain = 130, ntest = 33). Models from hyperspectral data solitarily had the lowest prediction performance (FMY: R2 = 0.61, nRMSEr = 17.14; DMY: R2 = 0.59, nRMSEr = 19.37). Higher performance was gained by models derived from 3d laser data (FMY: R2 = 0. 76, nRMSEr = 13.3; DMY: R2 = 0. 74, nRMSEr = 15.1). A fusion of both sensor systems increased the FMY prediction performance up to R2 = 0.8; nRMSEr = 12.02 and the DMY prediction performance to R2 = 0.81 and nRMSEr = 12.06. The fusion of complementary sensor systems can increase the power to predict biomass yields of heterogenous and extensively managed grasslands. It is a novel alternative to labour-intensive, traditional biomass prediction methods and to remote sensing methods using only single sensor data.
Zitierform
In: Remote Sensing in Ecology and Conservation Volume 7 / Issue 2 (2020-09-30) , S. 198-213 ; eissn:2056-3485Förderhinweis
Gefördert durch den Publikationsfonds der Universität KasselZitieren
@article{doi:10.17170/kobra-202108054491,
author={Schulze-Brüninghoff, Damian and Wachendorf, Michael and Astor, Thomas},
title={Remote sensing data fusion as a tool for biomass prediction in extensive grasslands invaded by L. polyphyllus},
journal={Remote Sensing in Ecology and Conservation},
year={2020}
}
0500 Oax 0501 Text $btxt$2rdacontent 0502 Computermedien $bc$2rdacarrier 1100 2020$n2020 1500 1/eng 2050 ##0##http://hdl.handle.net/123456789/13082 3000 Schulze-Brüninghoff, Damian 3010 Wachendorf, Michael 3010 Astor, Thomas 4000 Remote sensing data fusion as a tool for biomass prediction in extensive grasslands invaded by L. polyphyllus / Schulze-Brüninghoff, Damian 4030 4060 Online-Ressource 4085 ##0##=u http://nbn-resolving.de/http://hdl.handle.net/123456789/13082=x R 4204 \$dAufsatz 4170 5550 {{Biomasse}} 5550 {{Grünland}} 5550 {{Lidar}} 5550 {{Fernerkundung}} 5550 {{Datenfusion}} 5550 {{Vielblättrige Lupine}} 7136 ##0##http://hdl.handle.net/123456789/13082
2021-08-06T13:15:26Z 2021-08-06T13:15:26Z 2020-09-30 doi:10.17170/kobra-202108054491 http://hdl.handle.net/123456789/13082 Gefördert durch den Publikationsfonds der Universität Kassel eng Namensnennung-Nicht-kommerziell 4.0 International http://creativecommons.org/licenses/by-nc/4.0/ above-ground biomass heterogenous grassland hyperspectral LiDAR senor fusion 500 580 Remote sensing data fusion as a tool for biomass prediction in extensive grasslands invaded by L. polyphyllus Aufsatz Remote sensing data fusion is a powerful tool to gain information of quantitative and qualitative vegetation properties on field level. The aim of this study was to develop prediction models from sensor data fusion for fresh and dry matter yield (FMY/DMY) in extensively managed grasslands with variable degree of invasion by Lupinus polyphyllus. Therefore, a terrestrial 3d laser scanner (TLS) and a drone-based hyperspectral camera was used to collect high resolution 3d point clouds and hyperspectral aerial orthomosaics of four extremely heterogenous grasslands. From 3d point clouds multiple features (vegetation height, sum of voxel, point density and surface structure) were extracted and combined with hyperspectral data to develop an optimized biomass model from random forest regression algorithm to predict FMY and DMY (ntrain = 130, ntest = 33). Models from hyperspectral data solitarily had the lowest prediction performance (FMY: R2 = 0.61, nRMSEr = 17.14; DMY: R2 = 0.59, nRMSEr = 19.37). Higher performance was gained by models derived from 3d laser data (FMY: R2 = 0. 76, nRMSEr = 13.3; DMY: R2 = 0. 74, nRMSEr = 15.1). A fusion of both sensor systems increased the FMY prediction performance up to R2 = 0.8; nRMSEr = 12.02 and the DMY prediction performance to R2 = 0.81 and nRMSEr = 12.06. The fusion of complementary sensor systems can increase the power to predict biomass yields of heterogenous and extensively managed grasslands. It is a novel alternative to labour-intensive, traditional biomass prediction methods and to remote sensing methods using only single sensor data. open access Schulze-Brüninghoff, Damian Wachendorf, Michael Astor, Thomas doi:10.1002/rse2.182 Deutsche Bundesstiftung Umwelt. Grant Number: 32886/01-33/2 Biomasse Grünland Lidar Fernerkundung Datenfusion Vielblättrige Lupine publishedVersion eissn:2056-3485 Issue 2 Remote Sensing in Ecology and Conservation 198-213 Volume 7 false
Die folgenden Lizenzbestimmungen sind mit dieser Ressource verbunden: