Sargassum Detection Using Machine Learning Models: A Case Study with the First 6 Months of GOCI-II Imagery

Abstract

A record-breaking agglomeration of Sargassum was packed along the northern Jeju coast in Korea in 2021, and laborers suffered from removing them from the beach. If remote sensing can be used to detect the locations at which Sargassum accumulated in a timely and accurate manner, we could remove them before their arrival and reduce the damage caused by Sargassum. This study aims to detect Sargassum distribution on the coast of Jeju Island using the Geostationary KOMPSAT 2B (GK2B) Geostationary Ocean Color Imager-II (GOCI-II) imagery that was launched in February 2020, with measurements available since October 2020. For this, we used GOCI-II imagery during the first 6 months and machine learning models including Fine Tree, a Fine Gaussian support vector machine (SVM), and Gentle adaptive boosting (GentleBoost). We trained the models with the GOCI-II Rayleigh-corrected reflectance (RhoC) image and a ground truth map extracted from high-resolution images as input and output, respectively. Qualitative and quantitative assessments were carried out using the three machine learning models and traditional methods such as Sargassum indexes. We found that GentleBoost showed a lower false positive (6.2%) and a high F-measure level (0.82), and a more appropriate Sargassum distribution compared to other methods. The application of the machine learning model to GOCI-II images in various atmospheric conditions is therefore considered successful for mapping Sargassum extent quickly, enabling reduction of laborers’ efforts to remove them.

Recent Developments in Artificial Intelligence in Oceanography

“…Experimental results showed that SRSe-Net is able to obtain more accurate segmentation with fewer network parameters. Shin et al [73] trained three machine learning models with Rayleigh-corrected reflection images and a ground truth map obtained from Geostationary Ocean Color Imager-II (GOCI-II) imagery during the agglomeration of Sargassum along the northern Jeju coast in Korea in 2021, including fine tree, fine Gaussian support vector machine (SVM), and gentle adaptive boosting (Gentle-Boost). Among these, the authors determined that Gentle-Boost was best at detecting the location of Sargassum (Figure 5).…”

“…In the forecasting of oceanic variables, methodologies broadly fall into two types. The first type of methodology Figure 5: Ground-truth maps and Sargassum maps generated using traditional methods (DVI, SRG, and SI) and machine learning models (fine tree, fine Gaussian SVM, and GentleBoost) from GOCI-II images obtained on 27 January, adapted from Shin et al [73]. Ocean-Land-Atmosphere Research includes traditional numerical models that rely on expert knowledge to develop complex dynamic and thermodynamic equations.…”

A Systematic Review of the Application of GOCI to Water Quality Monitoring of Inland and Coastal Waters

“…Subsequently, South Korea launched GOCI-II in 2020. GOCI-II has many improvements over GOCI, with more watercolor bands and higher spatial resolution [56][57][58].…”

U-Net Super-Resolution Model of GOCI to GOCI-II Image Conversion

“…CEAN color remote sensing data have been widely used for short-and long-term monitoring of water quality [1], [2], [3], [4], ocean productivity [5], ocean fronts [6], and blooms such as red [7], [8], [9], green, and golden tide blooms [10], [11], [12]. Monitoring and assessing water changes are carried out using ocean color sensors such as the Moderate Resolution Imaging Spectroradiometer (MODIS; Terra:1999-present; Aqua:2002-present), Sea-viewing Wide Manuscript received XXX; revised XXX; accepted XXX.…”