glitterin: Towards Replacing the Role of Lorenz-Mie Theory in Astronomy Using Neural Networks Trained on Light Scattering of Irregularly Shaped Grains

TL;DR

This paper introduces 'glitterin', a neural network model that efficiently predicts light scattering by irregular dust grains, providing a more accurate alternative to traditional spherical models and enabling advanced astrophysical analyses.

Contribution

We developed a neural network trained on DDA simulations to accurately and quickly predict light scattering for irregular dust grains, surpassing spherical models in realism and computational efficiency.

Findings

Neural network achieves millisecond prediction times with high accuracy.

Irregular grains show size and composition-dependent scattering deviations.

Validation confirms improved modeling of dust scattering over spherical assumptions.

Abstract

Light scattering by dust particles is often modeled assuming the dust is spherical for numerical simplicity and speed. However, real dust particles have highly irregular morphologies that significantly affect their scattering properties. We have developed glitterin, a neural network trained to predict light scattering from irregularly shaped dust grains, offering a computationally efficient alternative to Lorenz-Mie theory. We computed scattering properties using the Discrete Dipole Approximation code ADDA for irregularly shaped particles across size parameters x from 0.1 to 65, covering a range in complex refractive index m that includes astrosilicates, pyroxene, enstatite, water-ice, etc. The neural network operates at millisecond timescales while maintaining superior accuracy compared to linear interpolation. Irregular grains exhibit x-dependent deviations from spherical predictions. At small x, cross-sections approach volume-equivalent spheres for low m. At large x, irregular grains show enhanced cross-sections due to greater geometric extension. Increasing m also enhances the absorption cross-section relative to the volume-equivalent spheres. This differential x and m dependence creates mid-IR solid-state features distinct from predictions from spherical grains. Validation against laboratory measurements of forsterite and hematite demonstrates that our neural network captures both qualitative and quantitative behaviors more accurately than spherical models. Millimeter-wavelength applications reveal that spherical grains produce opposite polarization signatures compared to irregular grains, potentially relaxing stringent ~100um grain size constraints in protoplanetary disks. glitterin is publicly available and alleviates the computational barriers to incorporating emission and scattering of realistic grain morphologies.