| one publication added to basket [101353] | Sediment type unsupervised classification of the Molenplaat, Westerschelde estuary, The Netherlands
Adam, S.; Vitse, I.; Johannsen, C.; Monbaliu, J. (2006). Sediment type unsupervised classification of the Molenplaat, Westerschelde estuary, The Netherlands. EARSeL eProc. 5(2): 146-160
In: EARSeL eProceedings. European Association of Remote Sensing Laboratories: Paris. ISSN 1729-3782; e-ISSN 1729-3782, meer
|   |
| Auteurs | | Top |
- Adam, S., meer
- Vitse, I.
- Johannsen, C.
- Monbaliu, J., meer
|
|
|
| Abstract |
Sediment stability or erosion resistance of intertidal zones depend on sediment physical characteristics and on biological factors. Obtaining accurate data on the basic biological, chemical and physical processes in sediments is expensive and difficult. Remote sensing methods can produce detailed information on ecological functioning in a cost-effective manner. A hyperspectral image of the Molenplaat, an intertidal flat in the Westerschelde estuary, the Netherlands, was acquired with the HyMap sensor in June 2004. The goal of this research is to perform, analyse and evaluate unsupervised classification methods for sediment types on the imagery. The unsupervised methods are based on Principal Component Analysis (PCA) or Iterative Self-Organizing Data Analysis Technique (ISODATA), and consist of three steps: (a) classification into spectrally distinct clusters, (b) post-clustering treatment, and (c) assignment of labels to the clusters. The result consists of 13 clusters after the post-clustering treatment, and of 8 or 9 classes after labelling for either the PCA or ISODATA method. A supervised Spectral Angle Mapper (SAM) classification was performed using field data to evaluate the unsupervised classification results. The labelling of the unsupervised clusters was also partly based on the SAM results, due to limited field data.The comparison of the results reveals that 69% and 73% of the pixels of PCA and ISODATA classification respectively were identically labelled in the supervised classification. Moreover, the mismatches were mainly found in two classes, while the other classes showed high similarities, indicating the plausibility of using unsupervised classification methods for intertidal sediment types. Additional strengths of the unsupervised classification methods are (a) the distinction of classes that were not visited during field work and not classified in the supervised classification, (b) the identification of spectrally distinct areas that should be characterised during field campaigns, and (c) the user-friendliness thanks to limited required field knowledge and short calculation time. |
|
