One of the factors affecting the amount of phytoplankton in the sea is the mass die-off of jellyfish. Research has shown that microbial degradation of jellyfish causes the release of nutrients, which in turn causes a phytoplankton response and a consequent increase in the concentration of chlorophyll a. Our hypothesis is that with the help of satellite images, it is possible to detect a correlation between the concentration of chlorophyll a in images and the mass die-off of jellyfish in the Adriatic Sea. To this end, we applied two methods for anomaly detection in images, principal component analysis and thresholding. We compared the two algorithms and found that they both have their own advantages and weaknesses. We also tested the performance of the algorithms on recorded mass die-offs of jellyfish and concluded that both algorithms showed promising results.
|
