Study On The Correction Of Total Suspended Particles Monitoring Results Based On Machine Learning Method

Instruments based on light scattering to measure total suspended particulate（TSP）concentrations have advantages of fast response,small size and low cost as compared to the gravimetric reference method.However,the relationship between scattering intensity and TSP mass concentration varies nonlinearly with both environmental conditions and particle properties,making it difficult to make corrections.This study applied four machine learning models（i.e.,support vector machine,random forest,gradient boosting regression trees and artificial neural network）to correct scattering measurements for TSP mass concentrations.A total of 1141 hourly records of collocated gravimetric and light scattering measurements at 17 urban sites in Shanghai,China were used for model training and validation.All four machine learning models improved linear regressions between scattering and gravimetric mass by increasing slopes from 0.4 to 0.9-1.1 and coefficients of determination from 0.1 to 0.8-0.9.Partial dependence plots indicate that TSP concentrations by light scattering instruments increased continuously in the PM_2.5concentration range of～0-80μg/m³;however,they leveled off above PM₁₀and TSP concentrations of～60 and 200μg/m³,respectively.The TSP mass concentrations by scattering showed an exponential growth after relative humidity exceeded 70%,in agreement with previous studies on hygroscopic growth of fine particles.This study demonstrates that machine learning models can effectively improve correlation between light scattering measurements for TSP mass concentrations with filter-based methods.Interpretation analysis further provides scientific insights into major factors（e.g.,hygroscopic growth）that cause scattering measurements to deviate from TSP mass concentrations besides other factors like fluctuation of mass density and refractive index.