In recent decades, the automatic study and analysis of plankton communities using imaging techniques has advanced significantly. The effectiveness of these automated systems appears to have improved, reaching acceptable levels of accuracy. However, plankton ecologists often find that classification systems do not work as well as expected when applied to new samples. This paper proposes a methodology to assess the efficacy of learned models which takes into account the fact that the data distribution (the plankton composition of the sample) can vary between the model building phase and the production phase. As opposed to most validation methods that consider the individual organism as the unit of validation, our approach uses a validation‐by‐sample, which is more appropriate when the objective is to estimate the abundance of different morphological groups. We argue that, in these cases, the base unit to correctly estimate the error is the sample, not the individual. Thus, model assessment processes require groups of samples with sufficient variability in order to provide precise error estimates.
In unicellular phytoplankton, the size scaling exponent of chlorophyll content per cell decreases with increasing light limitation. Empirical studies have explored this allometry by combining data from several species, using average values of pigment content and cell size for each species. The resulting allometry thus includes phylogenetic and size scaling effects. The possibility of measuring single-cell fluorescence with imaging-in-flow cytometry devices allows the study of the size scaling of chlorophyll content at both the inter- and intraspecific levels. In this work, the changing allometry of chlorophyll content was estimated for the first time for single phytoplankton populations by using data from a series of incubations with monocultures exposed to different light levels. Interspecifically, our experiments confirm previous modeling and experimental results of increasing size scaling exponents with increasing irradiance. A similar pattern was observed intraspecifically but with a larger variability in size scaling exponents. Our results show that size-based processes and geometrical approaches explain variations in chlorophyll content. We also show that the single-cell fluorescence measurements provided by imaging-in-flow devices can be applied to field samples to understand the changes in the size dependence of chlorophyll content in response to environmental variables affecting primary production. The chlorophyll concentrations in phytoplankton register physiological adjustments in cellular pigmentation arising mainly from changes in light conditions. The extent of these adjustments is constrained by the size of the phytoplankton cells, even within single populations. Hence, variations in community chlorophyll derived from photoacclimation are also dependent on the phytoplankton size distribution.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.