Long time series of spatiotemporally continuous phytoplankton functional type (PFT) data are essential for understanding marine ecosystems and global biogeochemical cycles as well as for effective marine management. In this study, we integrated artificial intelligence (AI) technology with multisource marine big data to develop a spatial–temporal–ecological ensemble model based on deep learning (STEE-DL). This model generated the first AI-driven global daily gap-free 4 km PFT chlorophyll a concentration product from 1998 to 2023 (AIGD-PFT). The AIGD-PFT significantly enhances the accuracy and spatiotemporal coverage of quantifying eight major PFTs: diatoms, dinoflagellates, haptophytes, pelagophytes, cryptophytes, green algae, prokaryotes, and Prochlorococcus . The model input encompasses (1) physical oceanographic, biogeochemical, and spatiotemporal information and (2) ocean colour data (OC-CCI v6.0) that have been gap-filled using a discrete cosine transform–penalized least squares (DCT-PLS) approach. The STEE-DL model utilizes an ensemble strategy with 100 residual neural network (ResNet) models, applying Monte Carlo and bootstrapping methods to estimate the optimal PFT chlorophyll a concentration and assess the model uncertainty through ensemble means and standard deviations. The model's performance was validated using multiple cross-validation strategies – random, spatial-block, and temporal-block methods – combined with in situ data, demonstrating STEE-DL's robustness and generalization capability. The daily updates and seamless nature of the AIGD-PFT data product capture the complex dynamics of coastal regions effectively. Finally, through a comparative analysis using a triple-collocation analysis (TCA) approach, the competitive advantages of the AIGD-PFT data product over existing products were validated. The complete product dataset (1998–2023) can be freely downloaded from https://doi.org/10.11888/RemoteSen.tpdc.301164 (Zhang and Shen, 2024a).

In this study, we analyzed the influence of coastal zone engineering on suspended sediment concentration (SSC) in the Yangtze River mouth based on HY-1C and Chinese GaoFen (GF) satellite data. The results show that: (1) SSC in the Yangtze River mouth is mainly in the range of 200–1300 mg/L, which changes due to natural factors as well as coastal zone engineering; (2) The sand blocking engineering effectively protects the channel from siltation, and SSC in the central line of the channel is 100–300 mg/L lower than that near the dikes in the north and south; (3) Qingcaosha Reservoir plays a stabilizing role in the hydrodynamic force, promoting the deposition of suspended matter, so that the water in the reservoir is clear. SSC inside the Qingcaosha Reservoir, located in the center of the estuary, is 100–500 mg/L lower than the high SSC water outside the reservoir; (4) The bridges interact with the current, facilitating the transport of local sediment, resulting in the increase in SSC downstream of these bridges, and obvious vortexes appear with the length up to nearly 2400 m; and (5) Corresponding protection and development suggestions were put forward as follows. A linear array of wind power plants can be built near and parallel to dikes and leading jetties; to increase the depth of the southeast end of the reservoir; and the location of the bridge should be selected in the place of river where siltation is easy. This study aimed to study the SSC distribution under the complex impact of coastal zone engineering with satellite and to provide possible improvement suggestions.

Chlorophyll-a (Chl-a) change details derived from HY-1C/D images in the waters of the Zhoushan archipelago were analyzed. A new Chl-a inverse model was built based on the relationship between the in situ Chl-a and the combination of red, blue and green bands of the coastal zone imager (CZI). Chl-a as well as fishery resources were analyzed. The results showed the following. (1) The Chl-a concentration in the waters of the Zhoushan archipelago was mainly in the range of 0.5~6 μg/L. High Chl-a area distributed in the west side of the study area, with a value of 3.5~5.5 μg/L. The Chl-a concentration in the east side of the study area was relatively lower, with a value of 0.5~2 μg/L. Chl-a around the islands was higher than that in the area far away from the islands. In addition, Chl-a concentration increased obviously downstream of the island. (2) The spawning ground of many fish in the waters of the Zhoushan archipelago was abundant, and its spatial-temporal variation was consistent with the change of Chl-a. (3) The islands interacted with the current, inducing upwelling upstream and vortex streets downstream. The complex hydrodynamic environment promoted a vertical exchange of water bodies, thereby resulting in an increase in suspended sediment concentration, nutrients, Chl-a and attracting fish.

Sea surface currents (SSC) play a pivotal role in material transport, energy exchange, and ecosystem dynamics in coastal marine environments. While traditional methods to obtain wide-range SSC, such as satellite altimetry, often struggle with limited performance in coastal regions due to waveform contamination, deriving SSC from sequential ocean color data using the Maximum Cross Correlation (MCC) has emerged as a promising approach. In this study, an enhanced MCC method called the Tide-Restricted Maximum Cross Correlation (TRMCC) is proposed and implemented on hourly ocean color data obtained from the Geostationary Ocean Color Imager II (GOCI-II) to derive SSC in coastal seas and turbid estuaries. Cross-comparison over three years with buoy data, high-frequency radar, and numerical model products shows that the TRMCC is capable of obtaining high-resolution SSC with good accuracy in coastal and estuarine areas. Both large-scale ocean circulation patterns in seas and fine-scale surface current structures in estuaries can be effectively captured. The deriving accuracy, especially in coastal and estuarine areas, can be significantly improved by integrating tidal current data into the MCC workflow, and the influence of invalid data can be minimized by using a flexible reference window size and the Normalized Cross-Correlation in the Fourier Domain technique. Seasonal SSC structure in Bohai Sea and diurnal SSC variation in the Yangtze River Estuary were depicted via satellite method for the first time. Our study highlights the vast potential of the TRMCC to be able to improve understanding of current dynamics in complex coastal regions.

Sea surface currents (SSCs) play a pivotal role in material transport, energy exchange, and ecosystem dynamics in coastal marine environments. While traditional methods to obtain wide-range SSCs, such as satellite altimetry, often struggle with limited performance in coastal regions due to waveform contamination, deriving SSCs from sequential ocean color data using maximum cross-correlation (MCC) has emerged as a promising approach. In this study, we proposed a novel SSC estimation method, called tide-restricted maximum cross-correlation (TRMCC), and implemented it on hourly ocean color data obtained from the Geostationary Ocean Color Imager II (GOCI-II) and the global tide model FES2014 to derive SSCs in coastal seas and turbid estuaries. Cross-comparison over three years with buoy data, high-frequency radar, and numerical model products shows that TRMCC is capable of obtaining high-resolution SSCs with good accuracy in coastal and estuarine areas. Both large-scale ocean circulation patterns in seas and fine-scale surface current structures in estuaries can be effectively captured. The deriving accuracy, especially in coastal and estuarine areas, can be significantly improved by integrating tidal current data into the MCC workflow, and the influence of invalid data can be minimized by using a flexible reference window size and normalized cross-correlation in the Fourier domain technique. Seasonal SSC structure in the Bohai Sea and diurnal SSC variation in the Yangtze River Estuary were depicted via the satellite method, for the first time. Our study highlights the vast potential of TRMCC to improve the understanding of current dynamics in complex coastal regions.

Long time series of spatiotemporally continuous phytoplankton functional type (PFT) products are essential for understanding marine ecosystems, global biogeochemical cycles, and effective marine management. In this study, by integrating artificial intelligence (AI) technology with multi-source marine big data, we have developed a Spatial–Temporal–Ecological Ensemble model based on Deep Learning (STEE-DL), and then generated the first AI-driven Global Daily gap-free 4 km PFTs product from 1998 to 2023 (AIGD-PFT), significantly enhancing the accuracy and spatiotemporal coverage of quantifying eight major PFTs (i.e., Diatoms, Dinoflagellates, Haptophytes, Pelagophytes, Cryptophytes, Green Algae, Prokaryotes, and Prochlorococcus). The input data encompass physical oceanographic, biogeochemical, spatiotemporal information, and ocean color data (OC-CCI v6.0) that have been gap-filled using a Discrete Cosine Transform with a Penalized Least Square (DCT-PLS) approach. The STEE-DL model utilizes an ensemble strategy with 100 ResNet models, applying Monte Carlo and bootstrapping methods to estimate optimal PFT values and assess model uncertainty through ensemble means and standard deviations. The model's performance was validated using multiple cross-validation strategies—random, spatial-block, and temporal-block—combined with in-situ data, demonstrating STEE-DL's robustness and generalization capability. The daily updates and seamless nature of the AIGD-PFT product capture the complex dynamics of coastal regions effectively. Finally, through a comparative analysis using a triple-collocation (TC) approach, the competitive advantages of the AIGD-PFT product over existing products were validated. The AIGD-PFT product not only provides the foundation for detailed analyses of PFT trends, interannual variability, and the impacts of climate change on phytoplankton composition across various temporal and spatial scales, but also has the potential to facilitate precise quantification of marine carbon flux and enhances the accuracy of biogeochemical models. A video demonstration is available at https://doi.org/10.5446/67366 (Zhang and Shen, 2024a). The complete product dataset (1998–2023) can be freely downloaded at https://doi.org/10.11888/RemoteSen.tpdc.301164 (Zhang and Shen, 2024b).