Accurate Noctiluca scintillans bloom (NSB) recognition from space is of great significance for marine ecological monitoring and underwater target detection. However, most existing NSB recognition models require expert visual interpretation or manual adjustment of model thresholds, which limits model application in operational NSB monitoring. To address these problems, we developed a Noctiluca scintillans Bloom Recognition Network (NSBRNet) incorporating an Inception Conv Block (ICB) and a Swin Attention Block (SAB) based on the latest deep learning technology, where ICB uses convolution to extract channel and local detail features, and SAB uses self-attention to extract global spatial features. The model was applied to Coastal Zone Imager (CZI) data onboard Chinese ocean color satellites (HY1C/D). The results show that NSBRNet can automatically identify NSB using CZI data. Compared with other common semantic segmentation models, NSBRNet showed better performance with a precision of 92.22%, recall of 88.20%, F1-score of 90.10%, and IOU of 82.18%.

The construction of a radiometric degradation model is vital for elucidating the performance alterations of ocean color satellite sensors following in-orbit operations. The Chinese ocean color satellites HaiYang-1C (HY1C) and HaiYang-1D (HY1D), operating as afternoon and morning satellites, respectively, conduct networked observations of the global ocean. However, there has been limited analysis of the radiometric performance of each ocean color sensor on HY1C/D. Therefore, to understand the performance change sensor, this study relies on the satellite calibration spectrometer (SCS), a hyperspectral sensor mounted on HY1C/D. The radiometric degradation model of each sensor is constructed, to realize the tracking of the long-term radiometric performance trend of the sensors. First, the SCS ensures the accuracy of its observations through a high-precision solar calibration method. Using the abundant simultaneous Earth observation data gathered by the SCS, this study realizes the radiometric calibration of each sensor, and the radiometric degradation model is further constructed to adjust the radiometric level and track and correct the sensor performance trend. The Chinese Ocean Color and Temperature Scanner (COCTS) is taken as an example, and the results show that the annual average radiometric degradation rate of COCTS-HY1C after launch ranges from 0.8% to 2.4% yr−1, while that of COCTS-HY1D ranges from 0.5% to 3.9% yr−1. These degradations were achieved by the SCS that allowed the sensors onboard HY1C/D to perform in-orbit radiometric calibration independently of external data sources and continuously generate high-quality climate data records (CDRs).