Enabling a large-scale assessment of litter along Saudi Arabian red sea shores by combining drones and machine learning. (15th May 2021)

• Record Type: Journal Article
• Authors: Martin, Cecilia; Zhang, Qiannan; Zhai, Dongjun; Zhang, Xiangliang; Duarte, Carlos M.
• Is Part Of: Environmental pollution. Volume 277(2021)
• Publication Date: 2021-05-15
• Subjects: Unmanned aerial vehicles -- Deep neural network -- Beach litter -- Plastic -- Marine debris; Pollution -- Periodicals; Pollution -- Environmental aspects -- Periodicals; Environmental Pollution -- Periodicals; Pollution -- Périodiques; Pollution -- Aspect de l'environnement -- Périodiques; Pollution -- Effets physiologiques -- Périodiques; Pollution; Pollution -- Environmental aspects; Periodicals; Electronic journals; 363.73
• DOI: 10.1016/j.envpol.2021.116730
• Languages: English
• ISSNs: 0269-7491

Abstract

Abstract: Beach litter assessments rely on time inefficient and high human cost protocols, mining the attainment of global beach litter estimates. Here we show the application of an emerging technique, the use of drones for acquisition of high-resolution beach images coupled with machine learning for their automatic processing, aimed at achieving the first national-scale beach litter survey completed by only one operator. The aerial survey had a time efficiency of 570 ± 40 m 2 min −1 and the machine learning reached a mean (±SE) detection sensitivity of 59 ± 3% with high resolution images. The resulting mean (±SE) litter density on Saudi Arabian shores of the Red Sea is of 0.12 ± 0.02 litter items m −2, distributed independently of the population density in the area around the sampling station. Instead, accumulation of litter depended on the exposure of the beach to the prevailing wind and litter composition differed between islands and the main shore, where recreational activities are the major source of anthropogenic debris. Graphical abstract: Image 1 Highlights: We surveyed 26 ha of shore in just 8 h. 60% of litter on high-resolution images was identified by deep learning. It is the first time that litter objects are automatically classified in types. We show that litter distribution is determined by exposure to the prevailing wind. Recreational activities are the major contributors of beach litter on the mainland. Abstract : A national-scale monitoring of beach litter along the Red Sea coast of Saudi Arabia, conducted by a single drone operator, shows that litter distributes according to wind exposure.