Changes in the environment, due to the global warming, including pollution and acidification present a challenge for some species. Their growth and survival depends on their potential to adapt to the new conditions. In the bivalves, growth patterns remain imprinted in their shell and therefore bivalve shell presents a great archive of environmental changes.
By analysing growth patterns of the bivalves and getting them in relation to the environmental variables we can better understand the ecology of certain species. Knowledge of the growth performance of the commercial bivalve species is very valuable as it provides important information that could be used in the assessment, management and protection of the exploited stocks.
In the frame of the CSF project BIVACME we want to find a connection between environmental parameters and growth pattern of commercially important scallop species. This is a two-step process, first growth pattern needs to be determinated, and second, those patterns need to be related to the available environmental data. The growth dynamic of the scallop species could be analysed from the daily growth lines on the scallop shell.
As measuring daily growth lines is a time-consuming process we hope that by using picture recognition and machine learning technology this process could be automated. The next step will be correlating obtained growth data with the available environmental data and finding what has positive/negative effect on the scallop’s growth.