The most problematic issue in the ocean color application is the presence of heavy clouds, especially in polar regions. For that reason, the demand for the ocean color application in polar regions is increased. As a way to overcome such issues, we conducted the reconstruction of the chlorophyll-a concentration (CHL) data using the machine learning-based models to raise the usability of CHL data. This analysis was first conducted on a regional scale and focused on the biologically-valued Cape Hallett, Ross Sea, Antarctica. Environmental factors and geographical information associated with phytoplankton dynamics were considered as predictors for the CHL reconstruction, which were obtained from cloud-free microwave and reanalysis data. As the machine learning models used in the present study, the ensemble-based models such as Random forest (RF) and Extremely randomized tree (ET) were selected with 10-fold cross-validation. As a result, both CHL reconstructions from the two models showed significant agreement with the standard satellite-derived CHL data. In addition, the reconstructed CHLs were close to the actual CHL value even where it was not observed by the satellites. However, there is a slight difference between the CHL reconstruction results from the RF and the ET, which is likely caused by the difference in the contribution of each predictor. In addition, we examined the variable importance for the CHL reconstruction quantitatively. As such, the sea surface and atmospheric temperature, and the photosynthetically available radiation have high contributions to the model developments. Mostly, geographic information appears to have a lower contribution relative to environmental predictors. Lastly, we estimated the partial dependences for the predictors for further study on the variable contribution and investigated the contributions to the CHL reconstruction with changes in the predictors.

Polar regions are too harsh to be continuously observed using ocean color (OC) sensors because of various limitations due to low solar elevations, ice effects, peculiar phytoplankton photosynthetic parameters, optical complexity of seawater and persistence of clouds and fog. Therefore, the OC data undergo a quality-control process, eventually accompanied by considerable data loss. We attempted to reconstruct these missing values for chlorophyll-a concentration (CHL) data using a machine-learning technique based on multiple datasets (satellite and reanalysis datasets) in the Ross Sea, Antarctica. This technique—based on an ensemble tree called random forest (RF)—was used for the reconstruction. The performance of the RF model was robust, and the reconstructed CHL data were consistent with satellite measurements. The reconstructed CHL data allowed a high intrinsic resolution of OC to be used without specific techniques (e.g., spatial average). Therefore, we believe that it is possible to study multiple characteristics of phytoplankton dynamics more quantitatively, such as bloom initiation/termination timings and peaks, as well as the variability in time scales of phytoplankton growth. In addition, because the reconstructed CHL showed relatively higher accuracy than satellite observations compared with the in situ data, our product may enable more accurate planktonic research.