Phytoplankton communities, which can be easily observed by optical sensors deployed on various types of platforms over diverse temporal and spatial scales, are crucial to marine ecosystems and biogeochemical cycles, and accurate pigment concentrations make it possible to effectively derive information from them. To date, there is no practical approach, however, to retrieving concentrations of detailed pigments from phytoplankton absorption coefficients () with acceptable accuracy and robustness in global oceans. In this study, a novel method, which is a stepwise regression method improved by early stopping (the ES-SR method) based on the derivative of hyperspectral , was proposed to retrieve pigment concentrations. This method was developed from an extensive global dataset collected from layers at different depths and contains phytoplankton pigment concentrations and . In the case of the logarithm, strong correlations were found between phytoplankton pigment concentrations and the absolute values of the second derivative ()/the fourth derivative () of . According to these correlations, the ES-SR method is effective in obtaining the characteristic wavelengths of phytoplankton pigments for pigment concentration inversion. Compared with the Gaussian decomposition method and principal component regression method, which are based on the derivatives, the ES-SR method implemented on is the optimum approach with the greatest accuracy for each phytoplankton pigment. More than half of the determination coefficient values () for all pigments, which were retrieved by performing the ES-SR method on , exceeded 0.7. The values retrieved for all pigments fit well to the one-to-one line with acceptable root mean square error (: 0.146–0.508) and median absolute percentage error (: 8.2–28.5%) values. Furthermore, the poor correlations between the deviations from the values retrieved by the ES-SR method and impact factors related to pigment composition and cell size class show that this method has advantageous robustness. Therefore, the ES-SR method has the potential to effectively monitor phytoplankton community information from hyperspectral optical data in global oceans.
2 December 2024 in IEEE Transactions on Geoscience and Remote Sensing
Based on machine learning (ML) methods, a new problem-solving procedure is proposed here to enhance river-plume research, including data collection, data-mining processes, and characteristic analyses. A plume shape recognition model is developed, structured on convolutional neural networks (CNNs), and is named “PlumeCatcher.” This model is shown to extract various river-plume features from satellite images. The random forests (RFs) data-mining method was applied to investigate the significance of the controller on plume development, including dynamic factors such as wind, current, water discharge, and tides, all of which are potential factors that can influence plume properties on daily, seasonal, and annual timescales. Focusing on the Magdalena River in Columbia (South America), the results of the methodology indicate that wind is the factor with maximum sensitivity dominating plume movement starting from the river mouth. Moreover, the plume features including area, direction, and spreading range are varied from short timescales (tidal cycle) to long timescales (yearly) and demonstrate the dynamic nature of plume spreading. ML methods provide an effective and convenient way to map plume features and extract and analyze their properties, which is beneficial for future scientific analyses.
29 September 2025 in Marine Environmental Research
Underwater ultraviolet radiation (UVR), which plays a significant role in photobiological and photochemical processes, is one of the key factors in marine ecosystems. A new algorithm KpcaUV, based on kernel principal component analysis (KPCA) and multiple linear regression (MLR), was proposed in this study for the retrieval of the UVR diffuse attenuation coefficient K d (λ) from remote sensing reflectance R rs (λ) in the global ocean. KPCA can be applied in all areas that principal components analysis (PCA) can be used. More importantly, KPCA can help mapping data into high dimensions and reducing the nonlinearity between inputs and outputs, which will improve the performance and robustness of algorithms when deriving large dynamic ranges parameters. Compared with SeaUVc, which is one of the most successful K d (λ) retrieval algorithms in UVR, the results showed that KpcaUV (with R 2 : 0.970 and RMSE: 14.0%) performed similar to SeaUVc (with R 2 : 0.963 and RMSE: 15.6%) when implemented with high-quality data. Nevertheless, KpcaUV was more robust and consistent than SeaUVc when implemented on the satellite images with different levels of quality control. The RMSD of SeaUVc had a significant reduction from 26.8% (QA ≥ 0.6) to 12.7% (QA = 1.0), and the RMSD of KpcaUV varied less than SeaUVc from 14.6% (QA ≥ 0.6) to 10.1% (QA = 1). Hence, considering its good nonlinear-problem-solving ability and robustness when applied to multiple satellites, KpcaUV proposed by this study can be used to obtain K d (380) for the continuous observation of the large area.