An automatic classification algorithm for submerged aquatic vegetation in shallow lakes using Landsat imagery
(2021) In Remote Sensing of Environment 260.- Abstract
Submerged aquatic vegetation (SAV) is one of the main producers in inland lakes. Tracking the temporal and spatial changes in SAV is crucial for the identification of state changes in lacustrine ecosystems, such as changes in light, nutrients, and temperature. However, the available SAV classification algorithms based on remote sensing are highly dependent on field survey data and/or human interventions, prohibiting the extraction of large-scale and/or long-term patterns. Here, we developed an automatic SAV classification algorithm using Landsat imagery, where the thresholds of two key parameters (the floating algae index (FAI) and reflectance in the shortwave-infrared (SWIR) band) are automatically determined. The algorithm was applied... (More)
Submerged aquatic vegetation (SAV) is one of the main producers in inland lakes. Tracking the temporal and spatial changes in SAV is crucial for the identification of state changes in lacustrine ecosystems, such as changes in light, nutrients, and temperature. However, the available SAV classification algorithms based on remote sensing are highly dependent on field survey data and/or human interventions, prohibiting the extraction of large-scale and/or long-term patterns. Here, we developed an automatic SAV classification algorithm using Landsat imagery, where the thresholds of two key parameters (the floating algae index (FAI) and reflectance in the shortwave-infrared (SWIR) band) are automatically determined. The algorithm was applied to eight Landsat images of four Yangtze Plain lakes and obtained a mean producer accuracy of 82.9% when gauged against field-surveyed datasets. The algorithm was further employed to obtain long-term SAV areal data from Changdang Lake on the Yangtze Plain from 1984 to 2018, and the result was highly consistent with lake transparency data. Numerical simulations indicated that our developed algorithm is insensitive to the Chl-a concentration of the water column. Yet, it has a detection limit of ~0.35 m below the water surface, and such a limit changes with different fractions of vegetation coverage within a pixel. The automatic classification algorithm proposed in this study has the potential to obtain the temporal and spatial distribution patterns of SAV in other shallow lakes where SAV grows in lakes sharing similar hydrological characteristics as the lakes in the Yangtze Plain.
(Less)
- author
- Dai, Yanhui ; Feng, Lian ; Hou, Xuejiao and Tang, Jing LU
- organization
- publishing date
- 2021-07
- type
- Contribution to journal
- publication status
- published
- subject
- keywords
- Aquatic vegetation, SAV, Remote sensing, FAI, SWIR, Classification, Dynamic threshold, Landsat
- in
- Remote Sensing of Environment
- volume
- 260
- article number
- 112459
- publisher
- Elsevier
- external identifiers
-
- scopus:85104490786
- ISSN
- 0034-4257
- DOI
- 10.1016/j.rse.2021.112459
- language
- English
- LU publication?
- yes
- id
- 1d068f80-f752-476b-8ec8-63456ca1d50d
- date added to LUP
- 2021-04-27 11:35:48
- date last changed
- 2023-02-21 11:24:32
@article{1d068f80-f752-476b-8ec8-63456ca1d50d, abstract = {{<p>Submerged aquatic vegetation (SAV) is one of the main producers in inland lakes. Tracking the temporal and spatial changes in SAV is crucial for the identification of state changes in lacustrine ecosystems, such as changes in light, nutrients, and temperature. However, the available SAV classification algorithms based on remote sensing are highly dependent on field survey data and/or human interventions, prohibiting the extraction of large-scale and/or long-term patterns. Here, we developed an automatic SAV classification algorithm using Landsat imagery, where the thresholds of two key parameters (the floating algae index (FAI) and reflectance in the shortwave-infrared (SWIR) band) are automatically determined. The algorithm was applied to eight Landsat images of four Yangtze Plain lakes and obtained a mean producer accuracy of 82.9% when gauged against field-surveyed datasets. The algorithm was further employed to obtain long-term SAV areal data from Changdang Lake on the Yangtze Plain from 1984 to 2018, and the result was highly consistent with lake transparency data. Numerical simulations indicated that our developed algorithm is insensitive to the Chl-a concentration of the water column. Yet, it has a detection limit of ~0.35 m below the water surface, and such a limit changes with different fractions of vegetation coverage within a pixel. The automatic classification algorithm proposed in this study has the potential to obtain the temporal and spatial distribution patterns of SAV in other shallow lakes where SAV grows in lakes sharing similar hydrological characteristics as the lakes in the Yangtze Plain.</p>}}, author = {{Dai, Yanhui and Feng, Lian and Hou, Xuejiao and Tang, Jing}}, issn = {{0034-4257}}, keywords = {{Aquatic vegetation; SAV; Remote sensing; FAI; SWIR; Classification; Dynamic threshold; Landsat}}, language = {{eng}}, publisher = {{Elsevier}}, series = {{Remote Sensing of Environment}}, title = {{An automatic classification algorithm for submerged aquatic vegetation in shallow lakes using Landsat imagery}}, url = {{http://dx.doi.org/10.1016/j.rse.2021.112459}}, doi = {{10.1016/j.rse.2021.112459}}, volume = {{260}}, year = {{2021}}, }