The spectral power exponent of the particulate backscattering coefficient (bbp), η, is a crucial parameter for assessing particle size distribution in the ocean, particularly for high-precision estimation of marine biogeochemical cycles. The development of remote sensing inversion models for η has been constrained by insufficient in situ data or faulty model mechanisms. In this study, biogeochemical Argo (BGC-Argo) data were effectively utilized to address the limitations of traditional observations, and the superior XGBoost method was employed to construct a global ocean η remote sensing inversion model (XGB model). In the 5-fold cross-validation, the Pearson correlation coefficient (R), root mean square error (RMSE), mean absolute error (MAE), and median absolute percentage deviation (MAPD) of the XGB model remained stable at approximately 0.65, 0.3, 0.25, and 16%, respectively, demonstrating high robustness. Via independent sample verification and comparison with major inversion models from the literature, the XGB model exhibited a high R value of 0.66 and the lowest RMSE, MAPD, and MAE, with values of 0.33, 16.81%, and 0.25, respectively, indicating its superior inversion capability. High η values were primarily found in oligotrophic regions and the iron-limited Southern Ocean, whereas low values were observed in coastal waters, exhibiting seasonal variation. The distribution of η in other ocean areas remained relatively stable, with nonsignificant seasonal changes. This study demonstrates the significant contributions of BGC-Argo observations in enhancing remote sensing estimation of global ocean η values, thereby providing valuable support for biogeochemical cycling research.
Read full abstract