Since 2007, a massive floating green tide has occurred repeatedly in the Yellow Sea. The work involved in monitoring and clearing such a phenomenon requires highly precise spatial information. Satellite remote sensing data can provide such detail but they can be limited by long revisit periods and small-scale observational coverage. Therefore, in operational monitoring of green tides, Moderate Resolution Imaging Spectroradiometer (MODIS) data have an important role because of their short revisit period (twice daily) and large-scale observational coverage (viewing swath width: 2330 km). However, errors exist in MODIS-derived areal detection of green tides because its coarse spatial resolution (250–1000 m) can lead to mixed-pixel problems (i.e. in many cases, the limit of spatial resolution results in single pixels covering multiple ground objects). In this study, a method for spectral unmixing was developed for remote green tide detection. This method is based on mathematical morphology, and it integrates both the spatial and spectral characteristics of the image in the process of endmember extraction. Experiments using simulated and actual MODIS images were undertaken to illustrate the advantages of the proposed method. Compared with traditional linear unmixing methods, the abundance and area of green tides extracted by the proposed method were closer to the ‘real’ condition. The average relative deviation of green tide area decreased from 84.0% to 21.0%. The results illustrate that the proposed method is able to work efficiently and that it can provide improved information on green tide abundance and area.

In 2017, large-scale macroalgae blooms with different dominant species of Ulva prolifera and Sargassum 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 U. prolifera and Sargassum from satellite images. In this study, the spectral difference between U. prolifera and Sargassum 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 U. prolifera whether it is floating in clear open water or turbid nearshore water. However, the reflectance of Sargassum floating in clear and turbid water shows totally different characteristics, because most of Sargassum body is submerged in the water and the observed Sargassum 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 U. prolifera and Sargassum . Based on the spectral difference analysis, we propose a random forest-based algorithm to distinguish U. prolifera and Sargassum from GF-1 WFV images with an overall accuracy of 97.6% except when U. prolifera and Sargassum mix together. The algorithm is more robust than the existing ones as it allowed more Sargassum 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 U. prolifera and Sargassum in the Yellow and East China Seas in May and June 2017 and in detecting Sargassum 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.

Existing red tide detection methods have mainly been developed for ocean color satellite data with low spatial resolution and high spectral resolution. Higher spatial resolution satellite images are required for red tides with fine scale and scattered distribution. However, red tide detection methods for ocean color satellite data cannot be directly applied to medium–high spatial resolution satellite data owing to the shortage of red tide responsive bands. Therefore, a new red tide detection method for medium–high spatial resolution satellite data is required. This study proposes the red tide detection U−Net (RDU−Net) model by considering the HY−1D Coastal Zone Imager (HY−1D CZI) as an example. RDU−Net employs the channel attention model to derive the inter−channel relationship of red tide information in order to reduce the influence of the marine environment on red tide detection. Moreover, the boundary and binary cross entropy (BBCE) loss function, which incorporates the boundary loss, is used to obtain clear and accurate red tide boundaries. In addition, a multi−feature dataset including the HY−1D CZI radiance and Normalized Difference Vegetation Index (NDVI) is employed to enhance the spectral difference between red tides and seawater and thus improve the accuracy of red tide detection. Experimental results show that RDU−Net can detect red tides accurately without a precedent threshold. Precision and Recall of 87.47% and 86.62%, respectively, are achieved, while the F1−score and Kappa are 0.87. Compared with the existing method, the F1−score is improved by 0.07–0.21. Furthermore, the proposed method can detect red tides accurately even under interference from clouds and fog, and it shows good performance in the case of red tide edges and scattered distribution areas. Moreover, it shows good applicability and can be successfully applied to other satellite data with high spatial resolution and large bandwidth, such as GF−1 Wide Field of View 2 (WFV2) images.

Chlorophyll a concentration and suspended matter concentration, as typical water quality parameters related to spectral characteristics, are essential for characterizing the degree of eutrophication in water bodies. They have become crucial indicators for water quality assessment of inland water bodies. The support vector regression model (SVR) is suitable for small samples, has excellent generalization ability, and has high prediction accuracy. Still, it has the problem of difficult selection of model parameters and quickly falling into local extremes. To solve this problem, a hybrid Differential Evolution-Grey Wolf Optimizer (DE-GWO) algorithm is introduced into the parameter selection process of the support vector regression model, and an improved SVR algorithm (DE-GWO-SVR) is proposed for the remote sensing inversion of chlorophyll a concentration and suspended sediment concentration in water bodies. In this paper, the spectral reflectance of the water surface and the chlorophyll a and broken matter concentration values were obtained by field measurements in the Tangdao Bay waters of Qingdao, Shandong Province. The inverse model between the concentration values of the two water quality parameters and the corresponding sensitive factors was established by first determining the sensitive factors based on the response of the spectral reflectance to the two water quality parameters and introducing the DE-GWO optimization algorithm into the parameter selection process of the SVR model. Finally, the accuracy of the model was verified using Sentinel II satellite remote sensing spectral data, and then the inverse accuracy of the two water quality parameters was obtained. The mean relative error (MRE) of the chlorophyll a prediction model built by the DE-GWO algorithm optimizing the SVR is 25.1%, and the mean relative error (MRE) of the suspended matter prediction model is 32.5%. The inversion results were all better than the other models (linear regression, SVR, and GWO-SVR model). When the best model, built from the measured water surface spectral data, was applied to the Sentinel II satellite data, the improved SVR model outperformed the other models in terms of mean relative error. The experimental results confirm that the DE-GWO-SVR algorithm is an effective method for remote sensing inversion of chlorophyll a and suspended matter concentrations in water bodies, which can provide a reference for remote sensing inversion of chlorophyll a and suspended matter concentrations in Chinese offshore waters and subsequent scientific management of waters.

<!-- *** Custom HTML *** --> Liang, X.-J.; Qin, P.; Xiao, Y.-F.; Kim, K.-Y.; Liu, R.-J.; Chen, X.-Y., and Wang, Q,-B., 2019. Automatic remote sensing detection of floating macroalgae in the yellow and east china seas using extreme learning machine. In: Jung, H.-S.; Lee, S.; Ryu, J.-H., and Cui, T. (eds.), Advances in Remote Sensing and Geoscience Information Systems of Coastal Environments. Journal of Coastal Research, Special Issue No. 90, pp.272-281. Coconut Creek (Florida), ISSN 0749-0208. In the past 10 years, floating macroalgae blooms have occurred repeatedly in the Yellow Sea. For the purpose of disaster prevention and mitigation, it is very important to monitor floating macroalgae blooms using satellite imagery. The traditional macroalgae remote sensing detection methods based on the vegetation indices are very sensitive to the threshold value which is affected by many factors in the complex atmospheric–oceanic environment. The threshold has obvious temporal and spatial variations, and is difficult to determine accurately. The expert experience is required to assist the value of threshold which leads to the low automation of detection. Aiming at this problem, this study introduces an Extreme Learning Machine (ELM) into the field of macroalgae remote sensing detection. Taking the four-bands GF-1 WFV optical images with 16-m resolution as an example, an automatic remote sensing detection model of macroalgae is constructed. The evaluation based on independent data shows that the accuarcy of this method is up to 86 %. The method is not disturbed by thin clouds, sun glint, high-turbidity water, and other factors. In addition, no manual intervention is required which suggests that the proposed method has strong potential of automated detection for the floating macroalgae blooms.