A Statistical Algorithm for Estimating Chlorophyll Concentration in the New Caledonian Lagoon

摘要: Spatial and temporal dynamics of phytoplankton biomass water turbidity can provide crucial information about the function, health vulnerability lagoon ecosystems (coral reefs, sea grasses, etc.). A statistical algorithm is proposed to estimate chlorophyll-a concentration ([chl-a]) in optically complex waters New Caledonian from MODIS-derived " remote-sensing reflectance (R rs). The developed via supervised learning on match-ups gathered 2002 2010. best performance obtained by combining two models, selected according ratio R rs spectral bands centered 488 555 nm: a log-linear model for low [chl-a] (AFLC) support vector machine (SVM) or classic (OC3) high [chl-a]. based SVM regression analysis. This approach outperforms classical OC3 approach, especially shallow waters, with root mean squared error 30% lower. enables more accurate assessments its variability this typical oligo-to meso-trophic tropical lagoon, coastal nearby reefs deeper open ocean.