Mapping Invasive <i>Phragmites australis</i> in the Old Woman Creek Estuary Using UAV Remote Sensing and Machine Learning Classifiers
Unmanned aerial vehicles (UAV) are increasingly used for spatiotemporal monitoring of invasive plants in coastal wetlands. Early identification of invasive species is necessary in planning, restoring, and managing wetlands. This study assessed the effectiveness of UAV technology to identify invasive...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2019-06-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/11/11/1380 |
| _version_ | 1819364928129073152 |
|---|---|
| author | Tharindu Abeysinghe Anita Simic Milas Kristin Arend Breann Hohman Patrick Reil Andrew Gregory Angélica Vázquez-Ortega |
| author_facet | Tharindu Abeysinghe Anita Simic Milas Kristin Arend Breann Hohman Patrick Reil Andrew Gregory Angélica Vázquez-Ortega |
| author_sort | Tharindu Abeysinghe |
| collection | DOAJ |
| description | Unmanned aerial vehicles (UAV) are increasingly used for spatiotemporal monitoring of invasive plants in coastal wetlands. Early identification of invasive species is necessary in planning, restoring, and managing wetlands. This study assessed the effectiveness of UAV technology to identify invasive <i>Phragmites australis</i> in the Old Woman Creek (OWC) estuary using machine learning (ML) algorithms: Neural network (NN), support vector machine (SVM), and k-nearest neighbor (kNN). The ML algorithms were compared with the parametric maximum likelihood classifier (MLC) using pixel- and object-based methods. Pixel-based NN was identified as the best classifier with an overall accuracy of 94.80% and the lowest error of omission of 1.59%, the outcome desirable for effective eradication of <i>Phragmites</i>. The results were reached combining Sequoia multispectral imagery (green, red, red edge, and near-infrared bands) combined with the canopy height model (CHM) acquired in the mid-growing season and normalized difference vegetation index (NDVI) acquired later in the season. The sensitivity analysis, using various vegetation indices, image texture, CHM, and principal components (PC), demonstrated the impact of various feature layers on the classifiers. The study emphasizes the necessity of a suitable sampling and cross-validation methods, as well as the importance of optimum classification parameters. |
| first_indexed | 2024-12-24T23:06:44Z |
| format | Article |
| id | doaj.art-76687d15657f40bb9d3afc720b0bf586 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-12-24T23:06:44Z |
| publishDate | 2019-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-76687d15657f40bb9d3afc720b0bf5862022-12-21T16:35:00ZengMDPI AGRemote Sensing2072-42922019-06-011111138010.3390/rs11111380rs11111380Mapping Invasive <i>Phragmites australis</i> in the Old Woman Creek Estuary Using UAV Remote Sensing and Machine Learning ClassifiersTharindu Abeysinghe0Anita Simic Milas1Kristin Arend2Breann Hohman3Patrick Reil4Andrew Gregory5Angélica Vázquez-Ortega6Department of Geology, School of Earth, Environment and Society, Bowling Green State University, 190 Overman Hall, Bowling Green, OH 43403, USADepartment of Geology, School of Earth, Environment and Society, Bowling Green State University, 190 Overman Hall, Bowling Green, OH 43403, USAOhio Department of Natural Resources, Old Woman Creek National Estuarine Research Reserve, Huron, OH 44839, USAFireland Coastal Tributaries, Erie Soil and Water Conservation District, Sandusky, OH 44870, USADepartment of Geology, School of Earth, Environment and Society, Bowling Green State University, 190 Overman Hall, Bowling Green, OH 43403, USADepartment of Geology, School of Earth, Environment and Society, Bowling Green State University, 190 Overman Hall, Bowling Green, OH 43403, USADepartment of Geology, School of Earth, Environment and Society, Bowling Green State University, 190 Overman Hall, Bowling Green, OH 43403, USAUnmanned aerial vehicles (UAV) are increasingly used for spatiotemporal monitoring of invasive plants in coastal wetlands. Early identification of invasive species is necessary in planning, restoring, and managing wetlands. This study assessed the effectiveness of UAV technology to identify invasive <i>Phragmites australis</i> in the Old Woman Creek (OWC) estuary using machine learning (ML) algorithms: Neural network (NN), support vector machine (SVM), and k-nearest neighbor (kNN). The ML algorithms were compared with the parametric maximum likelihood classifier (MLC) using pixel- and object-based methods. Pixel-based NN was identified as the best classifier with an overall accuracy of 94.80% and the lowest error of omission of 1.59%, the outcome desirable for effective eradication of <i>Phragmites</i>. The results were reached combining Sequoia multispectral imagery (green, red, red edge, and near-infrared bands) combined with the canopy height model (CHM) acquired in the mid-growing season and normalized difference vegetation index (NDVI) acquired later in the season. The sensitivity analysis, using various vegetation indices, image texture, CHM, and principal components (PC), demonstrated the impact of various feature layers on the classifiers. The study emphasizes the necessity of a suitable sampling and cross-validation methods, as well as the importance of optimum classification parameters.https://www.mdpi.com/2072-4292/11/11/1380<i>Phragmites australis</i>unmanned aerial vehiclesinvasivemachine learningobject-based classifiers |
| spellingShingle | Tharindu Abeysinghe Anita Simic Milas Kristin Arend Breann Hohman Patrick Reil Andrew Gregory Angélica Vázquez-Ortega Mapping Invasive <i>Phragmites australis</i> in the Old Woman Creek Estuary Using UAV Remote Sensing and Machine Learning Classifiers Remote Sensing <i>Phragmites australis</i> unmanned aerial vehicles invasive machine learning object-based classifiers |
| title | Mapping Invasive <i>Phragmites australis</i> in the Old Woman Creek Estuary Using UAV Remote Sensing and Machine Learning Classifiers |
| title_full | Mapping Invasive <i>Phragmites australis</i> in the Old Woman Creek Estuary Using UAV Remote Sensing and Machine Learning Classifiers |
| title_fullStr | Mapping Invasive <i>Phragmites australis</i> in the Old Woman Creek Estuary Using UAV Remote Sensing and Machine Learning Classifiers |
| title_full_unstemmed | Mapping Invasive <i>Phragmites australis</i> in the Old Woman Creek Estuary Using UAV Remote Sensing and Machine Learning Classifiers |
| title_short | Mapping Invasive <i>Phragmites australis</i> in the Old Woman Creek Estuary Using UAV Remote Sensing and Machine Learning Classifiers |
| title_sort | mapping invasive i phragmites australis i in the old woman creek estuary using uav remote sensing and machine learning classifiers |
| topic | <i>Phragmites australis</i> unmanned aerial vehicles invasive machine learning object-based classifiers |
| url | https://www.mdpi.com/2072-4292/11/11/1380 |
| work_keys_str_mv | AT tharinduabeysinghe mappinginvasiveiphragmitesaustralisiintheoldwomancreekestuaryusinguavremotesensingandmachinelearningclassifiers AT anitasimicmilas mappinginvasiveiphragmitesaustralisiintheoldwomancreekestuaryusinguavremotesensingandmachinelearningclassifiers AT kristinarend mappinginvasiveiphragmitesaustralisiintheoldwomancreekestuaryusinguavremotesensingandmachinelearningclassifiers AT breannhohman mappinginvasiveiphragmitesaustralisiintheoldwomancreekestuaryusinguavremotesensingandmachinelearningclassifiers AT patrickreil mappinginvasiveiphragmitesaustralisiintheoldwomancreekestuaryusinguavremotesensingandmachinelearningclassifiers AT andrewgregory mappinginvasiveiphragmitesaustralisiintheoldwomancreekestuaryusinguavremotesensingandmachinelearningclassifiers AT angelicavazquezortega mappinginvasiveiphragmitesaustralisiintheoldwomancreekestuaryusinguavremotesensingandmachinelearningclassifiers |