A Random Forest-Based Algorithm to Distinguish <i>Ulva prolifera</i> and <i>Sargassum</i> From Multispectral Satellite Images
Yanfang Xiao, Rongjie Liu, Keunyong Kim, Jie Zhang, Tingwei Cui
Abstract
In 2017, large-scale macroalgae blooms with different dominant species of <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Ulva prolifera</i> and <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Sargassum</i> occurred concurrently in the Yellow and East China Seas, which poses a challenge to the cognition and control of macroalgae disaster. Therefore, it is necessary to develop an algorithm to distinguish <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">U. prolifera</i> and <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Sargassum</i> from satellite images. In this study, the spectral difference between <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">U. prolifera</i> and <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Sargassum</i> and the capability of several multispectral satellite missions to distinguish them is first analyzed. The results show that the reflectance peak in visible wavelength is always in ~550 nm for <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">U. prolifera</i> whether it is floating in clear open water or turbid nearshore water. However, the reflectance of <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Sargassum</i> floating in clear and turbid water shows totally different characteristics, because most of <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Sargassum</i> body is submerged in the water and the observed <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Sargassum</i> reflectance is seriously affected by water reflectance. Compared with Landsat 8 Operational Land Imager (OLI), HuanJing-1, Charge-Coupled Devices (HJ-1 CCD), Aqua Moderate-resolution Imaging Spectroradiometer (MODIS), and Sentinel 2 Multi-Spectral Instrument (MSI), GaoFen-1, Wide Field of View (GF-1 WFV) can preferably capture the spectral difference between <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">U. prolifera</i> and <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Sargassum</i> . Based on the spectral difference analysis, we propose a random forest-based algorithm to distinguish <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">U. prolifera</i> and <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Sargassum</i> from GF-1 WFV images with an overall accuracy of 97.6% except when <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">U. prolifera</i> and <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Sargassum</i> mix together. The algorithm is more robust than the existing ones as it allowed more <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Sargassum</i> samples from different ocean regions to be used in the training; in addition, it avoids negative effects caused by the selection of a threshold. The proposed algorithm is proved effective in distinguishing <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">U. prolifera</i> and <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Sargassum</i> in the Yellow and East China Seas in May and June 2017 and in detecting <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Sargassum</i> in the Atlantic Ocean. Thus, this method can be used in researches including floating macroalgae traceability and competition and succession between different macroalgae species in different regions of the ocean with similar environments.