Datum
2021-10-28Schlagwort
600 Technik 630 Landwirtschaft, Veterinärmedizin Invasive ArtVielblättrige LupineGrünlandMaschinelles LernenSensorDatenMetadata
Zur Langanzeige
Aufsatz
Potentials and Limitations of WorldView-3 Data for the Detection of Invasive Lupinus polyphyllus Lindl. in Semi-Natural Grasslands
Zusammenfassung
Semi-natural grasslands contribute highly to biodiversity and other ecosystem services, but they are at risk by the spread of invasive plant species, which alter their habitat structure. Large area grassland monitoring can be a powerful tool to manage invaded ecosystems. Therefore, WorldView-3 multispectral sensor data was utilized to train multiple machine learning algorithms in an automatic machine learning workflow called ‘H2O AutoML’ to detect L. polyphyllus in a nature protection grassland ecosystem. Different degree of L. polyphyllus cover was collected on 3 × 3 m² reference plots, and multispectral bands, indices, and texture features were used in a feature selection process to identify the most promising classification model and machine learning algorithm based on mean per class error, log loss, and AUC metrics. The best performance was achieved with a binary classification of lupin-free vs. fully invaded 3 × 3 m² plot classification with a set of 7 features out of 763. The findings reveal that L. polyphyllus detection from WorldView-3 sensor data is limited to large dominant spots and not recommendable for lower plant coverage, especially single plant detection. Further research is needed to clarify if different phenological stages of L. polyphyllus as well as time series increase classification performance.
Zitierform
In: Remote Sensing Volume 13 / Issue 21 (2021-10-28) eissn:2072-4292Förderhinweis
Gefördert durch den Publikationsfonds der Universität KasselZitieren
@article{doi:10.17170/kobra-202112235346,
author={Schulze-Brüninghoff, Damian and Wachendorf, Michael and Astor, Thomas},
title={Potentials and Limitations of WorldView-3 Data for the Detection of Invasive Lupinus polyphyllus Lindl. in Semi-Natural Grasslands},
journal={Remote Sensing},
year={2021}
}
0500 Oax 0501 Text $btxt$2rdacontent 0502 Computermedien $bc$2rdacarrier 1100 2021$n2021 1500 1/eng 2050 ##0##http://hdl.handle.net/123456789/13489 3000 Schulze-Brüninghoff, Damian 3010 Wachendorf, Michael 3010 Astor, Thomas 4000 Potentials and Limitations of WorldView-3 Data for the Detection of Invasive Lupinus polyphyllus Lindl. in Semi-Natural Grasslands / Schulze-Brüninghoff, Damian 4030 4060 Online-Ressource 4085 ##0##=u http://nbn-resolving.de/http://hdl.handle.net/123456789/13489=x R 4204 \$dAufsatz 4170 5550 {{Invasive Art}} 5550 {{Vielblättrige Lupine}} 5550 {{Grünland}} 5550 {{Maschinelles Lernen}} 5550 {{Sensor}} 5550 {{Daten}} 7136 ##0##http://hdl.handle.net/123456789/13489
2022-01-05T14:38:15Z 2022-01-05T14:38:15Z 2021-10-28 doi:10.17170/kobra-202112235346 http://hdl.handle.net/123456789/13489 Gefördert durch den Publikationsfonds der Universität Kassel eng Namensnennung 4.0 International http://creativecommons.org/licenses/by/4.0/ invasive species WorldView-3 grassland machine learning feature selection 600 630 Potentials and Limitations of WorldView-3 Data for the Detection of Invasive Lupinus polyphyllus Lindl. in Semi-Natural Grasslands Aufsatz Semi-natural grasslands contribute highly to biodiversity and other ecosystem services, but they are at risk by the spread of invasive plant species, which alter their habitat structure. Large area grassland monitoring can be a powerful tool to manage invaded ecosystems. Therefore, WorldView-3 multispectral sensor data was utilized to train multiple machine learning algorithms in an automatic machine learning workflow called ‘H2O AutoML’ to detect L. polyphyllus in a nature protection grassland ecosystem. Different degree of L. polyphyllus cover was collected on 3 × 3 m² reference plots, and multispectral bands, indices, and texture features were used in a feature selection process to identify the most promising classification model and machine learning algorithm based on mean per class error, log loss, and AUC metrics. The best performance was achieved with a binary classification of lupin-free vs. fully invaded 3 × 3 m² plot classification with a set of 7 features out of 763. The findings reveal that L. polyphyllus detection from WorldView-3 sensor data is limited to large dominant spots and not recommendable for lower plant coverage, especially single plant detection. Further research is needed to clarify if different phenological stages of L. polyphyllus as well as time series increase classification performance. open access Schulze-Brüninghoff, Damian Wachendorf, Michael Astor, Thomas doi:10.3390/rs13214333 Invasive Art Vielblättrige Lupine Grünland Maschinelles Lernen Sensor Daten publishedVersion eissn:2072-4292 Issue 21 Remote Sensing Volume 13 false 4333
Die folgenden Lizenzbestimmungen sind mit dieser Ressource verbunden: