The abundance of phytoplankton is generally estimated by measuring the chlorophyll-a concentration (C_chla), which is an important factor in photosynthesis and can be used to analyze the density and biomass of phytoplankton in the ecosystem. The band-ratio-based empirical or semi-analytical algorithms are operationally applied to retrieve C_chla in global oceans, which generally experience difficulties from the diversity of optical properties and the complexity of the radiative transfer equations in analytical analyses, respectively. With an attempt to develop an accurate C_chla retrieval model for the optically complex coastal and estuarine waters, this study aimed to explore the deep learning (DL) methods in satellite retrieval of C_chla. A two-stage convolutional neural network (CNN), named C_chla-Net, was proposed, which utilized the spectral information of remote sensing reflectances at MODIS/Aqua’s visible bands. In the first-stage phase, the C_chla-Net was pretrained by a set of remote sensing patches, in which the C_chla was generated from an existing model (OC3M). The pretrained results were than used as the initial values to refine the network with the synthetic oversampled in-situ dataset in the second-stage training phase. Using in-situ samples for training with the new initial values has a higher probability to reach the global optimum. The quantitative analyses showed that the two-stage training was more likely to achieve a global optimum in the optimization than the one-stage training. Matchups of the in-situ C_chla measurements were used to evaluate the retrieval models. Results showed that the proposed C_chla-Net produced obvious better performance than the empirical and semi-analytical algorithms, implying the DL method was more effective for optically complex waters with extremely high C_chla. This study provided an applicable method for remote sensing retrieval of C_chla, which should be helpful for studying the spatial distribution and temporal variability in the productive Pearl River estuary (PRE) waters.

We evaluated six empirical and semianalytical models of the diffuse attenuation coefficient at 490 nm (K_d(490)) using an in situ dataset collected in the Pearl River estuary (PRE). A combined model with the most accurate performance (correlation coefficient, R² = 0.92) was selected and applied for long-term estimation from 2003 to 2017. Physical and biological processes in the PRE over the 14-year period were investigated by applying satellite observations (MODIS/Aqua data) and season-reliant empirical orthogonal function analysis (S-EOF). In winter, the average K_d(490) was significantly higher than in the other three seasons. A slight increasing trend was observed in spring and summer, whereas a decreasing trend was observed in winter. In summer, a tongue with a relatively high K_d(490) was found in southeastern Lingdingyang Bay. In Eastern Guangdong province (GDP), the relatively higher K_d(490) value was found in autumn and winter. Based on the second mode of S-EOF, we found that the higher values in the eastern GDP extended westward and formed a distinguishable tongue in winter. The grey relational analysis revealed that chlorophyll-a concentration (C_chla) and total suspended sediment concentration (C_tsm) were two dominant contributors determining the magnitude of K_d(490) values. The C_tsm-dominated waters were generally located in coastal and estuarine turbid waters; the C_chla-dominated waters were observed in open clear ocean. The distribution of constituents-dominated area was different in the four seasons, which was affected by physical forces, including wind field, river runoff, and sea surface temperature.

An empirical algorithm is proposed to estimate suspended particulate matter (SPM) ranging from 0.675 to 25.7 mg L⁻¹ in the turbid Pearl River estuary (PRE). Comparisons between model predicted and in situ measured SPM resulted in R²s of 0.97 and 0.88 and mean absolute percentage errors (MAPEs) of 23.96% and 29.69% by using the calibration and validation data sets, respectively. The developed algorithm demonstrated the highest accuracy when compared with existing ones for turbid coastal waters. The diurnal dynamics of SPM was revealed by applying the proposed algorithm to reflectance data collected by a moored buoy in the PRE. The established algorithm was implemented to Hyperspectral Imager for the Coastal Ocean (HICO) data and the distribution pattern of SPM in the PRE was elucidated. Validation of HICO-derived reflectance data by using concurrent MODIS/Aqua data as a benchmark indicated their reliability. Factors influencing variability of SPM in the PRE were analyzed, which implicated the combined effects of wind, tide, rainfall, and circulation as the cause.

An attention U-Net was proposed to reconstruct the missing chlorophyll-a concentration (C_chla) data. The U-Net is a lightweight full convolution neural network architecture consisting of an enccoder-decoder (i.e., down-sampling and up-sampling). The attention gates (AGs) were integrated into the U-Net. Training the U-Net with AGs could implicitly teach it to suppress irrelevant areas and highlight the salient features in the missing data areas, which would increase the network sensitivity and reconstruction accuracy. The neural network uses the satellite-derived C_chla anomalies and its variance as the input, and the reconstructed fields along with their variances as outputs. The trained network was applied to long-term daily MODIS/Aqua C_chla products in the Pearl River estuary (PRE) and adjacent continental shelf area. The model performance was evaluated by using an independent test dataset from both satellite-derived and in-situ measurements. The results showed that the proposed neural network not only had good performance in the reconstruction of valid pixels, but also provided a more reasonable reconstruction compared to the standard U-Net without AGs. This study provided a feasible method for the reconstruction task in the field of ocean color, which should be helpful in producing a creditable dataset to study the ecological effects of extreme weather conditions such as typhoons on the upper ocean in the PRE waters. Based on the reconstructed C_chla products, the footprints of the typhoons were studied. An increase in surface C_chla near the typhoons’ track and a decrease in estuary were found. The composite results illustrated that the C_chla increases occurred for almost the entire area within a radius of 100 km. The time series analysis showed that the C_chla peak appeared on the fifth day after the typhoon’s passage.

Mapping bathymetry with satellite-based imagery for optically shallow waters is important for the management of coastal areas. However, mapping ultra-high-spatial-resolution bathymetry (spatial-resolution < 5 m) for a wide range of coastal optically shallow waters is limited by high cost and the absence of in situ data. Therefore, in this study, a new downscaled bathymetric mapping approach (DBMA-RGB) was established using freely accessed Landsat-8 (spatial-resolution = 30 m) and cost-effective Google Earth Pro-exported ultra-high-spatial-resolution red-green-blue (RGB) imagery. The new approach introduced the scale-invariance assumption that the log-ratio model (LRM) which is calibrated at a high scale is valid at a low scale. To reduce the inversion errors from Landsat-8 imagery, a theoretical maximum detection depth (MDD) model was proposed for the optimization-based inversion method, which is the foundation of DBMA-RGB for working without in situ bathymetric data. The theoretical MDDs overall matched the true MDDs except for the abnormal values, with root mean square error and correlation coefficient values of 3.30 m and 0.68, respectively. Additionally, a set of correction coefficients was obtained to improve the accuracy of the water depth derived from Landsat-8 imagery. Finally, the DBMA-RGB was applied to the RGB imagery of sixteen coastal areas around the world, incorporating the bathymetric results from Landsat-8 imagery. The comparison results indicated that the DBMA-RGB yielded similar results to the LRM calibrated using in situ bathymetric data. In summary, DBMA-RGB demonstrated its feature in accurately mapping ultra-high-spatial-resolution bathymetry for a wide range of coastal optically shallow waters without in situ bathymetric data.