DDA-BNN v1.0: a morphology-aware surrogate model for  the optical properties of black carbon-containing particles

Beeler, Payton; Donald, Sam; Fierce, Laura

doi:10.5194/gmd-19-10795-2026

Articles | Volume 19, issue 21

https://doi.org/10.5194/gmd-19-10795-2026

© Author(s) 2026. This work is distributed under
the Creative Commons Attribution 4.0 License.

https://doi.org/10.5194/gmd-19-10795-2026

© Author(s) 2026. This work is distributed under
the Creative Commons Attribution 4.0 License.

Articles | Volume 19, issue 21

Model description paper

|

13 Nov 2026

Model description paper |

| 13 Nov 2026

DDA-BNN v1.0: a morphology-aware surrogate model for the optical properties of black carbon-containing particles

Payton Beeler, Sam Donald, and Laura Fierce

Data sets

Training dataset for DDA-BNN v1.0, accompanying the manuscript "DDA-BNN v1.0: A Morphology-Aware Surrogate Model for the Optical Properties of Black Carbon–Containing Particles." Payton Beeler et al. https://doi.org/10.5281/zenodo.19324185

Model code and software

DDA-BNN v1.0: A Morphology-Aware Surrogate Model for the Optical Properties of Black Carbon–Containing Particles Payton Beeler et al. https://doi.org/10.5281/zenodo.21478183

DDA-BNN pnnl https://github.com/pnnl/DDA-BNN

Short summary

We developed a surrogate model to predict how black carbon particles absorb and scatter light based on their size, shape, and mixing with other aerosol species. The model was trained on detailed physics simulations and also estimates uncertainty caused by limited training data and unresolved internal structures. It outperformed common simplified particle assumptions, especially for scattering, and can help target new simulations to improve predictions of black carbon's radiative effects.