Classification of Single Particles Analyzed by ATOFMS Using an Artificial Neural Network, ART-2A

Abstract

Aerosol particles have received significant public and scientific attention in recent years due to studies linking them to global climatic changes and human health effects. In 1994, Prather et al. (Prather, K. A.; Nordmeyer, T.; Salt, K. Anal. Chem. 1994, 66, 1403−1407) developed aerosol time-of-flight mass spectrometry (ATOFMS), the first technique capable of simultaneously determining both size and chemical composition of polydisperse single particles in real time. ATOFMS can typically analyze between 50 and 100 particles/min under typical atmospheric conditions. This significant volume of data requires automated data analysis for efficient processing. This paper reports the successful analysis of ATOFMS data acquired during a 1996 field study in Southern California using an adaptive resonance theory-based neural network, ART-2a. The ART-2a network revealed particle categories consistent with those obtained previously by manual analysis. The classification was accomplished in less time than the acquisition, rendering it possible to develop a data acquisition system using an on-line ART-2a that classifies particles as they are acquired.