Learning to Simulate Aerosol Dynamics with Graph Neural Networks

Journal Article · Mon Jul 14 00:00:00 EDT 2025 · ACS ES&T Air

DOI:https://doi.org/10.1021/acsestair.4c00261· OSTI ID:2587060

Ferracina, Fabiana ^[1]; Beeler, Payton ^[2]; Halappanavar, Mahantesh ^[2]; Krishnamoorthy, Bala ^[3]; Minutoli, Marco ^[2]; Fierce, Laura ^[2]

---

1. Pacific Northwest National Laboratory (PNNL), Richland, WA (United States); Washington State Univ., Vancouver, WA (United States)
2. Pacific Northwest National Laboratory (PNNL), Richland, WA (United States)
3. Washington State Univ., Vancouver, WA (United States)

Aerosol effects on climate, weather, and air quality depend on characteristics of individual particles, which are tremendously diverse and change in time. Particle-resolved models are the only models able to capture this diversity in particle physiochemical properties, and these models are computationally expensive. As a strategy for accelerating particle-resolved microphysics models, we introduce Graph-based Learning of Aerosol Dynamics (GLAD) and use this model to train a surrogate of the particle-resolved model PartMC-MOSAIC. GLAD implements a Graph Network-based Simulator (GNS), a machine learning framework that has been used to simulate particle-based fluid dynamics models. In GLAD, each particle is represented as a node in a graph, and the evolution of the particle population over time is simulated through learned message passing. Here, we demonstrate our GNS approach on a simple aerosol system that includes condensation of sulfuric acid onto particles composed of sulfate, black carbon, organic carbon, and water. A graph with particles as nodes is constructed, and a graph neural network (GNN) is then trained using the model output from PartMC-MOSAIC. The trained GNN can then be used for simulating and predicting aerosol dynamics over time. Results demonstrate the framework's ability to accurately learn chemical dynamics and generalize across different scenarios, achieving efficient training and prediction times. We evaluate the performance across four scenarios, highlighting the framework's robustness and adaptability in modeling aerosol microphysics and chemistry.

• Research Organization: Pacific Northwest National Laboratory (PNNL), Richland, WA (United States)
• Sponsoring Organization: USDOE Laboratory Directed Research and Development (LDRD) Program
• Grant/Contract Number: AC05-76RL01830
• OSTI ID: 2587060
• Report Number(s): PNNL-SA--203852
• Journal Information: ACS ES&T Air, Journal Name: ACS ES&T Air Journal Issue: 8 Vol. 2; ISSN 2837-1402
• Publisher: American Chemical Society (ACS)
• Country of Publication: United States
• Language: English

Related Subjects

aerosol chemistry dynamics
graph-based learning
machine learning
neural networks
particle-based methods
particle-resolved simulation