Due to overuse of plastic products, decomposed microplastics (MPs) are widely spread in aquatic ecosystems, and will cause irreparable harm to the human body through the food chain. Traditional MP detection methods require cumbersome sample pre-processing procedures and complex instruments, so there is an urgent demand to develop methods to achieve simple on-site detection. Herein, a simple, sensitive, accurate, and stable MP detection method based on surface-enhanced Raman scattering (SERS) is investigated. Considering the hydrophobic problems of MPs, gold nanoparticle (AuNP) doped filter paper as a flexible SERS substrate is applied to capture MPs in the fiber pores. Benefitting from the electromagnetic (EM) hot spots generated by AuNPs, the Raman signal of MPs can be effectively enhanced. Meanwhile, the flexible SERS substrate has good sensitivity to a minimum detectable concentration of 0.1 g L⁻¹ for polyethylene terephthalate (PET) in water, and the maximum enhancement factor (EF) can reach 360.5. Furthermore, the practicability of the developed method has been proved by the successful detection of MPs in tap water and pond water. This research provides an easy process, high sensitivity, and good reproducibility method for MP detection.

The development of patterned graphene metasurface absorbers (PGMAs) offers potential solutions for achieving light weight, thinness, wide absorption bandwidth, and tunable terahertz (THz) absorption properties. In order to optimize the absorption properties of PGMA, the absorption spectrum is usually used as an important evaluation metric, which can provide many important properties of PGMA such as absorption bandwidth, absorption magnitude, etc. However, analysis of the absorption spectra corresponding to a large number of variable structural parameters is required when designing the structure, which consumes a lot of resources, since the electromagnetic (EM) wave absorption in PGMA involves complex impedance matching and electric field excitation processes. To address this issue, this study proposes a machine learning (ML) approach based on the random forest (RF) algorithm to predict the absorption bandwidth and structural parameters for designing PGMA, reducing the need for unnecessary numerical simulation and spectra analysis time. With the RF model, a very large effective absorption bandwidth of 3.83 THz and a perfect absorption bandwidth of 2.52 THz are predicted with the R² of 0.938 and 0.907, and the forecast absolute percentage errors (APEs) are only 1.56% and 1.16%, respectively, which is much better than other classical ML algorithms. Furthermore, the proposed PGMA has the advantages of being thin, polarization insensitive, with a large stable incident angle of 60°, and excellent electrical tuning capabilities. This study provides a feasible and effective approach for the sophisticated design of complex systems related to EM wave propagation of absorption, reflection, and transmission.