In-line identification of Pb-based pigments in fishing nets and ropes based on hyperspectral imaging and machine learning

Abstract

Fishing lines, nets, and ropes represent a significant portion of plastic pollution in marine environments, and can contain hazardous additives. The development of less laborious and faster methods aiming at identifying plastic-related additives is therefore needed, in order to facilitate effective recycling. This work aims to develop an industrial inline method to identify lead-based pigments in fishnets by an industrial hyperspectral imaging (HSI) system working in visible-near-infrared spectral range (Vis-NIR, 450 to 1050 nm) and machine learning. A Vis-NIR spectral sample set comprising un-contaminated and lead contaminated (143 to 2430 mg L−1) plastic classes were used to build the classification model via Principal Component Analysis and clustering. The content of the samples was characterized by X-ray fluorescence (XRF), Attenuated Total Reflection (ATR-FTIR), differential scanning calorimetry, thermogravimetric analysis, and burning in astmospheric air. Fishnets containing lead-based pigments with lead concentrations > 1000 mg L−1 (0.1 wt%) were accurately identified by the industrial HSI, and the lead content was corroborated with ATR-FTIR and XRF measurements. In addition, lead contaminated plastic area and mass can be estimated via calibration curve using the pixels numbers vs mass of fibrous plastics with a detectability of 120 mg (R2 = 0.997).