AI-accelerated solutions to the plastic waste crisis
Thematic Area: Environment
Mentors: Matt Sigman, Jacob Lessard, Taylor Sparks
Lampkin’s project aims to address plastic pollution by developing plastics that are “degradable and upcyclable on demand.” He’ll use AI models to accelerate the discovery of special additives that can be built into common, durable plastics—like polystyrene—to safely break them down or transform them into new materials when triggered by light or acid. The project hinges on designing and testing classes of highly reactive chemical compounds and using AI to predict their behavior. To enable the discovery process, Lampkin will create a data-efficient AI algorithm that can identify useful additives more rapidly than conventional trial-and-error experimentation. Data efficiency is crucial because datasets for training AI in many areas of chemistry are sparse due to high experimental costs. “Although this work alone will not solve plastic pollution, it should furnish conceptual and practical advances useful for enhancing the sustainability of plastics,” Lampkin said. “In the short term, my study will generate an innovative AI algorithm that can catalyze molecular discovery campaigns across many domains. In the long term, this project should demonstrate a promising approach for addressing the chemical challenge at the core of the plastic waste crisis.”
