Fast and Automatic Data-Driven Thresholding for Inundation Mapping with Sentinel-2 Data
Satellite data offer the opportunity for monitoring the temporal flooding dynamics of seasonal wetlands, a parameter that is essential for the ecosystem services these areas provide. This study introduces an unsupervised approach to estimate the extent of flooded areas in a satellite image relying o...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2018-06-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | http://www.mdpi.com/2072-4292/10/6/910 |
| _version_ | 1818321642280976384 |
|---|---|
| author | Georgios A. Kordelas Ioannis Manakos David Aragonés Ricardo Díaz-Delgado Javier Bustamante |
| author_facet | Georgios A. Kordelas Ioannis Manakos David Aragonés Ricardo Díaz-Delgado Javier Bustamante |
| author_sort | Georgios A. Kordelas |
| collection | DOAJ |
| description | Satellite data offer the opportunity for monitoring the temporal flooding dynamics of seasonal wetlands, a parameter that is essential for the ecosystem services these areas provide. This study introduces an unsupervised approach to estimate the extent of flooded areas in a satellite image relying on the physics of light interaction with water, vegetation and their combination. The approach detects automatically thresholds on the Short-Wave Infrared (SWIR) band and on a Modified-Normalized Difference Vegetation Index (MNDVI), derived from radiometrically-corrected Sentinel-2 data. Then, it combines them in a meaningful way based on a knowledge base coming out of an iterative trial and error process. Classes of interest concern water and non-water areas. The water class is comprised of the open-water and water-vegetation subclasses. In parallel, a supervised approach is implemented mainly for performance comparison reasons. The latter approach performs a random forest classification on a set of bands and indices extracted from Sentinel-2 data. The approaches are able to discriminate the water class in different types of wetlands (marshland, rice-paddies and temporary ponds) existing in the Doñana Biosphere Reserve study area, located in southwest Spain. Both unsupervised and supervised approaches are examined against validation data derived from Landsat satellite inundation time series maps, generated by the local administration and offered as an online service since 1983. Accuracy assessment metrics show that both approaches have similarly high classification performance (e.g., the combined kappa coefficient of the unsupervised and the supervised approach is 0.8827 and 0.9477, and the combined overall accuracy is 97.71% and 98.95, respectively). The unsupervised approach can be used by non-trained personnel with a potential for transferability to sites of, at least, similar characteristics. |
| first_indexed | 2024-12-13T10:44:09Z |
| format | Article |
| id | doaj.art-d7815c0c95c44872a9f7b81c0c58f4b9 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-12-13T10:44:09Z |
| publishDate | 2018-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-d7815c0c95c44872a9f7b81c0c58f4b92022-12-21T23:50:19ZengMDPI AGRemote Sensing2072-42922018-06-0110691010.3390/rs10060910rs10060910Fast and Automatic Data-Driven Thresholding for Inundation Mapping with Sentinel-2 DataGeorgios A. Kordelas0Ioannis Manakos1David Aragonés2Ricardo Díaz-Delgado3Javier Bustamante4Information Technologies Institute, Centre for Research and Technology Hellas (CERTH), Charilaou-Thermi Rd. 6th km, 57001 Thessaloniki, GreeceInformation Technologies Institute, Centre for Research and Technology Hellas (CERTH), Charilaou-Thermi Rd. 6th km, 57001 Thessaloniki, GreeceRemote Sensing and GIS Laboratory (LAST-EBD), Estación Biologica de Doñana (CSIC), Avda. Américo Vespucio s/n, Isla de la Cartuja, 41092 Sevilla, SpainRemote Sensing and GIS Laboratory (LAST-EBD), Estación Biologica de Doñana (CSIC), Avda. Américo Vespucio s/n, Isla de la Cartuja, 41092 Sevilla, SpainRemote Sensing and GIS Laboratory (LAST-EBD), Estación Biologica de Doñana (CSIC), Avda. Américo Vespucio s/n, Isla de la Cartuja, 41092 Sevilla, SpainSatellite data offer the opportunity for monitoring the temporal flooding dynamics of seasonal wetlands, a parameter that is essential for the ecosystem services these areas provide. This study introduces an unsupervised approach to estimate the extent of flooded areas in a satellite image relying on the physics of light interaction with water, vegetation and their combination. The approach detects automatically thresholds on the Short-Wave Infrared (SWIR) band and on a Modified-Normalized Difference Vegetation Index (MNDVI), derived from radiometrically-corrected Sentinel-2 data. Then, it combines them in a meaningful way based on a knowledge base coming out of an iterative trial and error process. Classes of interest concern water and non-water areas. The water class is comprised of the open-water and water-vegetation subclasses. In parallel, a supervised approach is implemented mainly for performance comparison reasons. The latter approach performs a random forest classification on a set of bands and indices extracted from Sentinel-2 data. The approaches are able to discriminate the water class in different types of wetlands (marshland, rice-paddies and temporary ponds) existing in the Doñana Biosphere Reserve study area, located in southwest Spain. Both unsupervised and supervised approaches are examined against validation data derived from Landsat satellite inundation time series maps, generated by the local administration and offered as an online service since 1983. Accuracy assessment metrics show that both approaches have similarly high classification performance (e.g., the combined kappa coefficient of the unsupervised and the supervised approach is 0.8827 and 0.9477, and the combined overall accuracy is 97.71% and 98.95, respectively). The unsupervised approach can be used by non-trained personnel with a potential for transferability to sites of, at least, similar characteristics.http://www.mdpi.com/2072-4292/10/6/910inundation mappingautomatic thresholdingSentinel-2marshlandrice-paddiestemporary ponds |
| spellingShingle | Georgios A. Kordelas Ioannis Manakos David Aragonés Ricardo Díaz-Delgado Javier Bustamante Fast and Automatic Data-Driven Thresholding for Inundation Mapping with Sentinel-2 Data Remote Sensing inundation mapping automatic thresholding Sentinel-2 marshland rice-paddies temporary ponds |
| title | Fast and Automatic Data-Driven Thresholding for Inundation Mapping with Sentinel-2 Data |
| title_full | Fast and Automatic Data-Driven Thresholding for Inundation Mapping with Sentinel-2 Data |
| title_fullStr | Fast and Automatic Data-Driven Thresholding for Inundation Mapping with Sentinel-2 Data |
| title_full_unstemmed | Fast and Automatic Data-Driven Thresholding for Inundation Mapping with Sentinel-2 Data |
| title_short | Fast and Automatic Data-Driven Thresholding for Inundation Mapping with Sentinel-2 Data |
| title_sort | fast and automatic data driven thresholding for inundation mapping with sentinel 2 data |
| topic | inundation mapping automatic thresholding Sentinel-2 marshland rice-paddies temporary ponds |
| url | http://www.mdpi.com/2072-4292/10/6/910 |
| work_keys_str_mv | AT georgiosakordelas fastandautomaticdatadriventhresholdingforinundationmappingwithsentinel2data AT ioannismanakos fastandautomaticdatadriventhresholdingforinundationmappingwithsentinel2data AT davidaragones fastandautomaticdatadriventhresholdingforinundationmappingwithsentinel2data AT ricardodiazdelgado fastandautomaticdatadriventhresholdingforinundationmappingwithsentinel2data AT javierbustamante fastandautomaticdatadriventhresholdingforinundationmappingwithsentinel2data |