Abstract A support vector machine (SVM) regression algorithm was developed for estimating the chlorophyll-a concentration (Cchla) in the turbid estuarine waters of the Pearl River estuary (PRE) based on visible infrared imaging radiometer suite (VIIRS) ocean color data. The proposed SVM algorithm outperformed the OC3 algorithm in the turbid waters. The temporal variation and spatial distribution of SVM-based monthly Cchla products were determined during 2012 and 2018. By analyzing the monthly average Cchla products and ancillary data, the underlying mechanisms of the Cchla coastal summer plume jet and winter bloom were revealed. The Cchla coastal plume jet was often observed in June, when the zonal wind direction changed from westward to eastward and the river runoff reached its maximum value of the year. The winter bloom in the ocean area was attributed to strong mixing in the upper layer, which resulted from cooling-induced buoyancy changes.

中文翻译：

---

基于 VIIRS 影像的珠江口浮游植物变异性

摘要 基于可见红外成像辐射仪套件（VIIRS）海洋颜色数据，开发了一种支持向量机（SVM）回归算法，用于估计珠江口（PRE）浑浊河口水域叶绿素a浓度（Cchla）。所提出的 SVM 算法在混浊水域中的性能优于 OC3 算法。确定了 2012 年和 2018 年基于 SVM 的月 Cchla 产品的时间变化和空间分布。通过分析月平均 Cchla 产品和辅助数据，揭示了 Cchla 沿海夏季羽流和冬季水华的潜在机制。6月常观测到Cchla海岸羽状急流，纬向风向由西向东转变，河流径流达到年度最大值。