Machine learning for estimating phytoplankton size structure from satellite ocean color imagery in optically complex Pacific Arctic waters

Abstract. In response to recent advances in satellite ocean color remote sensing, the present study developed a chlorophyll-a size distribution (CSD) model using machine learning (ML) approaches for optically complex Pacific Arctic waters. Previous CSD models capture the spectral features of satellite-estimated phytoplankton absorption coefficient (a_ph(λ)) through principal component analysis (PCA) and assume a strong correlation between the spectral features and phytoplankton size structure determined from the exponent of the CSD (η). A weakness of this approach is that relies on satellite retrievals of a_ph(λ), which can be highly uncertain due to the optical effects of water constituents other than phytoplankton. Therefore, we tested the utility of remote sensing reflectance (R_rs(λ)) for directly deriving η and ML methods to identify other viable algorithm formulations besides PCA. Results show superior performance of the ML-based CSD models compared to the PCA-based model utilizing both R_rs(λ) and a_ph(λ) as predictors of η. Considering the large uncertainties in the inversion of a_ph(λ) from R_rs(λ), the CSD model with R_rs(λ) based on multivariable linear regression produced the best performance among all models considered. Another key finding is that more complex ML approaches do not always produce more effective models than standard linear regression. Indeed, simple linear regression outperformed other ML approaches for retrieving η directly from R_rs(λ), whereas support vector machine performed the best among diverse ML approaches in the case of a_ph(λ). Overall, this study found benefits in using R_rs(λ) with ML to improve the retrieval accuracy of η for Pacific Arctic waters.