4.7 Article

An automatic classification algorithm for submerged aquatic vegetation in shallow lakes using Landsat imagery

Journal

REMOTE SENSING OF ENVIRONMENT
Volume 260, Issue -, Pages -

Publisher

ELSEVIER SCIENCE INC
DOI: 10.1016/j.rse.2021.112459

Keywords

Aquatic vegetation; SAV; Remote sensing; FAI; SWIR; Classification; Dynamic threshold; Landsat

Funding

  1. National Natural Science Foundation of China [41971304]
  2. High-level Special Funding of the Southern University of Science and Technology [G02296302, G02296402]
  3. Shenzhen Science and Technology Innovation Committee [JCYJ20190809155205559]
  4. Colleges Pearl River Scholar Funded Scheme

Ask authors/readers for more resources

An automatic SAV classification algorithm using Landsat imagery was developed in this study, with automatically determined thresholds for key parameters. The algorithm showed high accuracy in classifying SAV in Yangtze Plain lakes and obtaining long-term SAV areal data. It is insensitive to Chl-a concentration in the water column, but has a detection limit below the water surface.
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 similar to 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.

Authors

I am an author on this paper
Click your name to claim this paper and add it to your profile.

Reviews

Primary Rating

4.7
Not enough ratings

Secondary Ratings

Novelty
-
Significance
-
Scientific rigor
-
Rate this paper

Recommended

No Data Available
No Data Available