Associate Prof. Jiajia Shan's Team at the School of Chemical Engineering, Ocean and Life Sciences has recently made significant progress in understanding the aging process of microplastics. Leveraging multimodal deep learning techniques, the team was able to track the diverse types of microplastic aging and accurately predict the factors contributing to the early stages of aging. This has significantly enhanced our comprehension of how the surface physicochemical properties of microplastics evolve over time and subsequently influence crucial environmental behaviors such as the release and adsorption of contaminants.
The research, bearing the title "Tracking Microplastic Aging Using Multimodal Deep Learning," was prestigiously published as a cover paper in Environmental Science & Technology, which stands as a preeminent journal within the environmental domain. Notably, this study represents the pioneering effort in integrating a wide range of aging characteristics into a cohesive and unified framework, thereby establishing a fundamental and essential model for effectively tracing the aging process of microplastics in the natural environment.