(270a) AI Methods for Improved Polymer Sorting

The exponential rise in the production and use of polymers, particularly in single use applications, has led to a dramatic increase in the environmental prevalence of plastics and problems with waste management. The potential reuse of this waste has attracted a great deal of attention because it represents substantial embodied carbon and energy that could potentially be exploited to great environmental and economic benefit. However, the purity of this waste represents a major challenge, decreasing the value of recyclate due to challenges with color and mechanical property degradation due to mixed streams. These streams result because our waste handling system is built around single stream recycling where all plastics are mixed together with non-plastic waste, which makes separation a key challenge for increasing the value and recyclability of this waste. Here, we describe the development of two different classification algorithms that enable new capabilities in mixed plastic waste sorting. First, a spectral classifier is developed that enables the sorting of different polyesters, potentially expanding the number of polyesters that can be considered recyclable and the efficacy with which they can be sorted. The goal of this classifier is to enable emergent new bioplastics and biodegradable polyesters to be included within mixed plastics recycling streams, enabling these polymers to be reused before being discarded and degraded. This classifier demonstrates greater than 95% efficacy at separating similar polymers such as poly(ethylene terephthalate) and poly(lactic acid) based on only a few wavelengths within the IR spectrum. Second, machine vision is explored as a method to separate different polymers. In this case, the high recognizability of consumer packaging provides a zero-cost method for effectively “barcoding” different plastics, allowing labeling to be used as an effective proxy for plastic type, including the full details of formulation ingredients such as dyes and fillers. This sorting can then enable reaggregation of similar or identical waste from the same producers, allowing it to be reused in the specific product lines for which it was originally produced. This provides a useful method for achieving scalable separation consistent with extended producer responsibility. Separately and in combination, these two methods can dramatically expand the quantity of recycled plastics.