Published February 2, 2026 | Version v1
Preprint Open

A Lagrangian Time-Series Machine Learning Framework for Predicting Concentrations and Exploring Drivers of Atmospheric Aerosols: Model Development and Application to Cloud Condensation Nuclei in Marine Boundary Layer

Authors/Creators

  • 1. Department of Energy, Environmental and Chemical Engineering, Washington University in St. Louis
  • 2. Department of Computer Science, Washington University in St. Louis

Description

This preprint presents a Lagrangian time-series machine learning framework for predicting atmospheric aerosol concentrations and investigating their environmental drivers. We demonstrate the advantages of this approach through an application to marine boundary layer cloud condensation nuclei.

Files

Manuscript_Lagrangian_LSTM_combined.pdf

Files (7.5 MB)

Name Size Download all
md5:bdbce57a8a6db1d5f8b7ed6d069f3e3b
7.5 MB Preview Download