An effective method for the rapid detection of microplastics in soil

Abstract

Microplastic accumulation in the soil may have a negative impact on environmental security and human health. The lack of standardized method to identify and quantify microplastics in the soil is an obstacle to research. Existing techniques are time-consuming and cumbersome. We took the mixture of soil and low-density polyethylene (LDPE)∖polyvinyl chloride (PVC) as the research object to explore its spectral characteristics in the 0.6–1.8 THz (THz) band. We have proposed the new method to establish the Least Squares Support Vector Machine (LS-SVM) model using THz spectral data to quickly detect the microplastic pollution level in the soil from different regions. The local model is based on local soil training data set to predict local microplastic pollution, for LDPE, the average correlation coefficient (R) is 0.9833, and the average root mean square error (RMSE) is 0.0050, whereas for PVC, the average R is 0.9686, and the average RMSE is 0.0071. However, it seems to be useful only for local regions. The multisource model is that nine training sets are combined into one training set to simultaneously predict the degree of microplastic pollution in each area, for LDPE, the average R is 0.9895, and the average RMSE is 0.0007, for PVC, the average R is 0.9831, and the average RMSE is 0.0009. The results indicated that terahertz combined with LS-SVM model have a good effect on predicting the degree of soil microplastic pollution.