phytoclass: A pigment-based chemotaxonomic method to determine the biomass of phytoplankton classes

Pigment-based chemotaxonomy is a widely utilized tool to determine the biomass of phytoplankton classes from pigment biomarkers. The CHEMTAX approach is sensitive to the initial estimates of pigment-to-chlorophyll a (Chl a) ratios for the phytoplankton classes required, even though these are modified by the CHEMTAX process. We present an alternative chemotaxonomic method that utilizes simulated annealing with a steepest descent algorithm to derive class abundances and pigment-to-Chl a ratios. The simulated annealing algorithm is tested on two synthetic datasets of Southern Ocean phytoplankton communities. Each dataset is composed of 1000 inversion samples (set of phytoplankton class abundances, pigment ratios, and pigment profiles) with sizes ranging between 5 and 60 individual samples. We show that the new simulated annealing approach displays higher accuracy than two common configurations of the CHEMTAX method, with lower differences between true and estimated class abundances. Symmetric mean absolute percentage error were 4.8-11%, compared to 18-70% with CHEMTAX approaches. Proportions of variance explained (R-2) between true and estimated class abundances using the simulated annealing approach were 0.98-0.99 compared to 0.71-0.89 for CHEMTAX. Overall, this new methodology is capable of determining phytoplankton class abundances at higher accuracy than CHEMTAX without sensitivity to initial estimates of pigment-to-Chl a ratios.