Development and evaluation of a genetic algorithm-based ocean color inversion model for simultaneously retrieving optical properties and bottom types in coral reef regions

Chih Hua Chang, Cheng Chien Liu, Hsiao Wei Chung, Long Jeng Lee, Wen Chang Yang

Research output: Contribution to journalArticle

7 Citations (Scopus)

Abstract

This work presents a novel approach that integrates a shallow water semi-analytical (SSA) model and a genetic algorithm (GA) to retrieve water column inherent optical properties (IOPs) and identify bottom types simultaneously from measurement of subsurface remote sensing reflectance. This GA - SSA approach is designed based on the assumption that each pixel is homogeneous with regard to the bottom type when viewed at small (centimeter) scales, and it is validated against a synthetic data set (N = 11;250) that consists of five types of bottom, three levels of bottom depth, 15 concentrations of chlorophyll-a (Chl-a), and a wide range of modeled IOP variations in clear and optically complex waters representing the coral reef environment. The results indicate that the GA - SSA approach is accurate and robust in the retrieval of IOPs and its success rate in identifying the real bottom type is limited by the level of Chl-a and bottom depth. When a pixel is homogeneous at a small scale, the maximum allowable concentrations for GA - SSA to perfectly identify all the five bottom types are 0.7 mg/m3at 5 m bottom depth, 0.2 mg/m3at 10 m, and 0.07 mg/m3at 15 m. A promising 80% recognition rate of the benthic community is possible with GA - SSA when an underwater hyperspectral imager is deployed to examine the health status of coral reefs in a clean (Chl-a < 1 mg/m3) and shallow (bottom depth < 10 m) environment. Further study that collects field data for direct validation is required to ensure that the GA - SSA approach is also applicable in real coral reef regions.

Original languageEnglish
Pages (from-to)605-617
Number of pages13
JournalApplied optics
Issue number4
DOIs
Publication statusPublished - 2014 Feb 1

All Science Journal Classification (ASJC) codes

  • Atomic and Molecular Physics, and Optics
  • Engineering (miscellaneous)
  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'Development and evaluation of a genetic algorithm-based ocean color inversion model for simultaneously retrieving optical properties and bottom types in coral reef regions'. Together they form a unique fingerprint.

Cite this