A new algorithm developed by a team at the University of Barcelona can analyse the level of plastic pollution in the ocean with a reliability of 80%
The European Commission recently began to push the Blue Economy, and other major economic players are beginning to pay attention to the situation of the ocean.
If the ocean is polluted or harmed, every community depending on it for food will feel the impact.
Microplastics are notoriously difficult to remove from water, requiring chemical interventions and then disposal of the accumulated particles. They enter the human body, slowly infecting organs as the immune system breaks down these foreign entities – releasing harmful chemicals.
Floating litter is a further dark consequence of ocean pollution. The largest density of floating litter is in the great ocean gyres, where systems of circular currents that spin and catch litter.
‘The remote sensing of floating marine macro-litter’
“The great amount of images of the marine surface obtained by drones and planes in monitoring campaigns on marine litter [also in experimental studies with known floating objects] enabled us to develop and test a new algorithm that reaches a 80% of precision in the remote sensing of floating marine macro-litter,” said Garcia-Garin, member of the Department of Evolutionary Biology, Ecology and Environmental Sciences of the UB and IRBio.
MARLIT is an open access tool created from an algorithm that has deep learning capacity. It is going to enable detection of floating plastic pollution in the ocean, with a reliability of over 80% according to the study.
The experts designed a new algorithm to automate the quantification of floating plastics in the sea through aerial photographs by applying the deep learning techniques and automatic learning methodology with artificial neuronal networks able to learn.
Direct observations versus the immense space to cover
Historically, direct observations are the go-to way to assess the impact of floating marine macro-litter (FMML).
Unfortunately, the ocean’s vastness has made that difficult in recent years. Researchers are experiencing such an influx of available imagery and data that they can’t manually process the information in a timely way.
Odei Garcia-Garin, first author of the article and member of the CRG on Large Marine Mammals, led by Professor Àlex Aguilar, commented: “Automatic aerial photography techniques combined with analytical algorithms are more efficient protocols for the control and study of this kind of pollutants.
“However, automated remote sensing of these materials is at an early stage. There are several factors in the ocean that harden the detection of floating litter automatically with the aerial images of the marine surface. This is why there are only a few studies that made the effort to work on algorithms to apply to this new research context”.
MARLIT enables the analysis of images individually, as well as to divide them into several segments. The tool can identify the presence of floating litter in each certain area and estimate their density with the image metadata, such as height and resolution.
In the future, it is expected the app can even be attached to a drone, to automate the remote sensing process even more seamlessly.