Deep-Learning-Based Cloud Masking on Multispectral Ocean Color Imagery for Floating Macroalgae Monitoring

Intensive blooms of floating macroalgae have been widely reported during the past decades. Multispectral satellite imagery serves as an important data source for bloom monitoring, but its capacities are often hindered by the difficulties in accurate cloud or cloud shadow masking. Imperfect masking not only leads to a lack of bloom observations but also induces uncertainties in their biomass estimations. To reduce false detections and to retain more valid satellite measurements, the feedback attention network (FANet) was applied to mask cloud and cloud shadow pixels on Moderate Resolution Imaging Spectroradiometer (MODIS) imagery. Satisfactory performance was achieved on the images taken in the Caribbean Sea, where cloud and sun glint contaminations frequently occur. The overall cloud detection accuracy is similar to 96%, as referred to manually prepared "ground truth". Cloud shadows are effectively detected while overmasking near sun glint regions is reduced. Compared with the commonly used SeaWiFS Data Analysis System (SeaDAS) cloud products, the FANet-derived cloud products retain 44% more valid MODIS measurements in summer 2021. Consequently, they consistently provide more macroalgal features on each single MODIS image. However, the monthly mean macroalgae biomass statistics derived from these two cloud masking approaches are consistently close despite their large differences in the number of valid measurements, suggesting that the mean-value composite strategy can minimize the impact of missing observations and provide reliable long-term trends. The proposed cloud masking method is also applicable to other similar multispectral sensors [i.e., Visible Infrared Imaging Radiometer Suite (VIIRS)] for monitoring floating macroalgae in the global open oceans.