Similarity-Based Analysis of Atmospheric Organic Compounds for Machine Learning Applications

TL;DR

This paper presents a similarity analysis connecting atmospheric organic compounds to existing molecular datasets, highlighting the need for curated atmospheric data to improve machine learning applications in atmospheric chemistry.

Contribution

It introduces a similarity-based method to relate atmospheric molecules to large molecular datasets, revealing their out-of-domain nature and guiding future dataset curation efforts.

Findings

Small overlap between atmospheric and non-atmospheric molecules.

Atmospheric compounds have distinct functional groups and atomic compositions.

Highlights the need for collaborative atmospheric molecular data collection.

Abstract

The formation of aerosol particles in the atmosphere impacts air quality and climate change, but many of the organic molecules involved remain unknown. Machine learning could aid in identifying these compounds through accelerated analysis of molecular properties and detection characteristics. However, such progress is hindered by the current lack of curated datasets for atmospheric molecules and their associated properties. To tackle this challenge, we propose a similarity analysis that connects atmospheric compounds to existing large molecular datasets used for machine learning development. We find a small overlap between atmospheric and non-atmospheric molecules using standard molecular representations in machine learning applications. The identified out-of-domain character of atmospheric compounds is related to their distinct functional groups and atomic composition. Our investigation underscores the need for collaborative efforts to gather and share more molecular-level atmospheric chemistry data. The presented similarity based analysis can be used for future dataset curation for machine learning development in the atmospheric sciences.