Classifying spatially heterogeneous wetland communities using machine learning algorithms and spectral and textural features
Mapping of wetlands (marsh vs. swamp vs. upland) is a common remote sensing application.Yet, discriminating between similar freshwater communities such as graminoid/sedge from remotely sensed imagery is more difficult. Most of this activity has been performed using medium to low resolution imagery....
- Autores:
- Tipo de recurso:
- Fecha de publicación:
- 2015
- Institución:
- Universidad del Rosario
- Repositorio:
- Repositorio EdocUR - U. Rosario
- Idioma:
- eng
- OAI Identifier:
- oai:repository.urosario.edu.co:10336/26050
- Acceso en línea:
- https://doi.org/10.1007/s10661-015-4426-5
https://repository.urosario.edu.co/handle/10336/26050
- Palabra clave:
- wetlands
marsh swamp upland
graminoid communities
- Rights
- License
- Restringido (Acceso a grupos específicos)
| Summary: | Mapping of wetlands (marsh vs. swamp vs. upland) is a common remote sensing application.Yet, discriminating between similar freshwater communities such as graminoid/sedge from remotely sensed imagery is more difficult. Most of this activity has been performed using medium to low resolution imagery. There are only a few studies using high spatial resolution imagery and machine learning image classification algorithms for mapping heterogeneous wetland plant communities. This study addresses this void by analyzing whether machine learning classifiers such as decision trees (DT) and artificial neural networks (ANN) can accurately classify graminoid/sedge communities using high resolution aerial imagery and image texture data in the Everglades National Park, Florida. In addition to spectral bands, the normalized difference vegetation index, and first- and second-order texture features derived from the near-infrared band were analyzed. Classifier accuracies were assessed using confusion tables and the calculated kappa coefficients of the resulting maps. The results indicated that an ANN (multilayer perceptron based on back propagation) algorithm produced a statistically significantly higher accuracy (82.04 %) than the DT (QUEST) algorithm (80.48 %) or the maximum likelihood (80.56 %) classifier (?<0.05). Findings show that using multiple window sizes provided the best results. First-order texture features also provided computational advantages and results that were not significantly different from those using second-order texture features. |
|---|