A team of researchers from Wageningen University in The Netherlands has developed an advanced Artificial Intelligence (AI) model that exhibits enhanced accuracy in recognizing floating plastics compared to traditional satellite images. What sets this AI model apart is its capability to identify the presence of plastic even when the sites are partially obscured by clouds or weather conditions are hazy.
Published in iScience, the study conducted by the Dutch researchers presents a potential breakthrough in the systematic removal of plastic litter from oceans using ships.
Globally, an estimated 350 million tonnes of plastic waste is produced each year, as per data from the Organization for Economic Co-operation and Development (OECD). Recent studies indicate that between 1 and 2 million tonnes of plastic find their way into oceans annually, accumulating alongside natural materials like driftwood and algae.
While information about the total accumulation of marine debris is readily available, the processing of such data necessitates automated analysis through AI models.
Marc Rußwurm, Assistant Professor at Wageningen University, highlighted, “These models learn from examples provided by oceanographers and remote sensing specialists, who visually identified several thousand instances of marine debris in satellite images on locations across the globe. In this way, they ‘trained’ the model to recognize plastic debris.”
Rußwurm further noted, “The detector remains accurate even in more challenging conditions; for example, when cloud cover and atmospheric haze make it difficult for existing models to identify marine debris precisely.” This development holds promise for more effective and reliable methods of identifying and addressing plastic pollution in oceans.
Post Your Comments