In order to use in situ sensed reflectance to monitor the concentrations of chlorophyll-a (Chl-a) and total suspended particulate (TSP) of waters in the Pearl River Delta, which is featured by the highly developed network of rivers, channels and ponds, 135 sets of simultaneously collected water samples and reflectance were used to test the performance of the traditional empirical models (band ratio, three bands) and the machine learning models of a back-propagation neural network (BPNN). The results of the laboratory analysis with the water samples show that the Chl-a ranges from 3 to 256 µg·L⁻¹ with an average of 39 µg·L⁻¹ while the TSP ranges from 8 to 162 mg·L⁻¹ and averages 42.5 mg·L⁻¹. Ninety sets of 135 samples are used as training data to develop the retrieval models, and the remaining ones are used to validate the models. The results show that the proposed band ratio models, the three-band combination models, and the corresponding BPNN models are generally successful in estimating the Chl-a and the TSP, and the mean relative error (MRE) can be lower than 30% and 25%, respectively. However, the BPNN models have no better performance than the traditional empirical models, e.g., in the estimation of TSP on the basis of the reflectance at 555 and 750 nm (R555 and R750, respectively), the model of BPNN (R555, R750) has an MRE of 23.91%, larger than that of the R750/R555 model. These results suggest that these traditional empirical models are usable in monitoring the optically active water quality parameters of Chl-a and TSP for eutrophic and turbid waters, while the machine learning models have no significant advantages, especially when the cost of training samples is considered. To improve the performance of machine learning models in future applications on the basis of ground sensor networks, large datasets covering various water situations and optimization of input variables of band configuration should be strengthened.

Satellite images with different spatial resolutions are widely used in the observations of floating macroalgae booms in sea surface. In this study, semi-synchronous satellite images with different resolutions (10 m, 16 m, 30 m, 50 m, 100 m, 250 m and 500 m) acquired over the Yellow Sea, are used to quantitatively assess the effects of spatial resolution on the observation of floating macroalgae blooms of Ulva prolifera. Results indicate that the covering area of macroalgae-mixing pixels (MM-CA) detected from high resolution images is smaller than that from low resolution images; however, the area affected by macroalgae blooms (AA) is larger in high resolution images than in low resolution ones. The omission rates in the MM-CA and the AA increase with the decrease of spatial resolution. These results indicate that satellite remote sensing on the basis of low resolution images (especially, 100 m, 250 m, 500 m), would overestimate the covering area of macroalgae while omit the small patches in the affected zones. To reduce the impacts of overestimation and omission, high resolution satellite images are used to show the seasonal changes of macroalgae blooms in 2018 and 2019 in the Yellow Sea.

Ulva pertusa (U. pertusa) is a benthic macroalgae in submerged conditions, and it is relatively difficult to monitor with the remote sensing approaches for floating macroalgae. In this work, a novel remote-sensing approach is proposed for monitoring the U. pertusa green tide, which applies a deep learning method to high-resolution RGB images acquired with unmanned aerial vehicle (UAV). The results of U. pertusa extraction from semi-simultaneous UAV, Landsat-8, and Gaofen-1 (GF-1) images demonstrate the superior accuracy of the deep learning method in extracting U. pertusa from UAV images, achieving an accuracy of 96.46%, a precision of 94.84%, a recall of 92.42%, and an F1 score of 0.92, surpassing the algae index-based method. The deep learning method also performs well in extracting U. pertusa from satellite images, achieving an accuracy of 85.11%, a precision of 74.05%, a recall of 96.44%, and an F1 score of 0.83. In the cross-validation between the results of Landsat-8 and UAV, the root mean square error (RMSE) of the portion of macroalgae (POM) model for U. pertusa is 0.15, and the mean relative difference (MRD) is 25.01%. The POM model reduces the MRD in Ulva pertusa area extraction from Landsat-8 imagery from 36.08% to 6%. This approach of combining deep learning and UAV remote sensing tends to enable automated, high-precision extraction of U. pertusa, overcoming the limitations of an algae index-based approach, to calibrate the satellite image-based monitoring results and to improve the monitoring frequency by applying UAV remote sensing when the high-resolution satellite images are not available.