Mapping Invasive <i>Spartina alterniflora</i> Using Phenological Information and Red-Edge Bands of Sentinel-2 Time-Series Data

The accurate mapping of <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Spartina alterniflora</i> (<italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">S. alterniflora</i>) invasion is crucial for controlling its spread and reducing severe ecological problems. Satellite images have been extensively employed for <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">S. alterniflora</i> invasion monitoring; however, there are still several issues that need to be addressed. The spectral similarities between <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">S. alterniflora</i> and surrounding ground objects make it challenging for traditional classifiers to achieve satisfactory extraction accuracy. Since the phenological information and red-edge spectral differences have been considered as informative features for identifying <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">S. alterniflora</i>, current studies mainly used them separately as classification features and seldom considered the differences of red-edge information at different phenological periods. Therefore, we proposed a pixel-based phenological and red-edge feature composite method (PpRef-CM) for <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">S. alterniflora</i> extraction considering both phenological information and red-edge bands derived from Sentinel-2 time series based on the existing pixel-based phenological feature composite method (Ppf-CM). The proposed PpRef-CM and machine-learning algorithms were employed for <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">S. alterniflora</i> extraction in two typical mangrove forests along coastal China. Results indicated that red-edge information at different phenological periods is essential for detecting <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">S. alterniflora</i>. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">S. alterniflora</i> extraction achieved the highest accuracy of 96.57% by using the eXtreme gradient boost algorithm when compared with other machine-learning algorithms. The PpRef-CM gave 2.72% and 2.61% more extraction accuracies of <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">S. alterniflora</i> than the Ppf-CM in two study sites, separately. These findings provide insights for selecting suitable classification features for <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">S. alterniflora</i> extraction studies and serve as an effective control and management of <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">S. alterniflora</i>.