Machine learning-based data inversion method for the bipolar differential mobility particle spectrometer

doi:10.1016/j.jaerosci.2026.106856

Machine learning-based data inversion method for the bipolar differential mobility particle spectrometer

2026-07-18

0

PRE

AI

DOI：10.1016/j.jaerosci.2026.106856

Original

Original request for help

Save

Abstract

En 中文

• A two-stage ML framework is developed for bipolar SMPS data inversion. • GPR accurately estimates ion mobility ratios without conventional bias. • A novel GBDT-MLP hybrid model effectively retrieves accurate PNSDs. • The framework is validated on both simulated and ambient aerosol data.

Keywords:

Differential mobility particle spectrometer

Bipolar charging

Machine learning

Data inversion

Particle number size distribution

Machine learning-based data inversion method for the bipolar differential mobility particle spectrometer

Abstract

Journal

Organization

Cited Papers