Inferring properties of dust in supernovae with neural networks

Abstract

Context. Determining properties of dust formed in and around supernovae from observations remains challenging. This may be due to either incomplete coverage of data in wavelength or time but also due to often inconspicuous signatures of dust in the observed data. Aims. Here we address this challenge using modern machine learning methods to determine the amount, composition and temperature of dust from a large set of simulated data. We aim to determine whether such methods are suitable to infer these properties from future observations of supernovae. Methods. We calculate spectral energy distributions (SEDs) of dusty shells around supernovae. We develop a neural network consisting of eight fully connected layers and an output layer with specified activation functions that allow us to predict the dust mass, temperature and composition and their respective uncertainties from each SED. We conduct a feature importance analysis via SHapley Additive exPlanations (SHAP) to find the minimum set of JWST filters required to accurately predict these properties. Results. We find that our neural network predicts dust masses and temperatures with a root-mean-square error (RMSE) of $\sim$ 0.12 dex and $\sim$ 38 K, respectively. Moreover, our neural network can well distinguish between the different dust species included in our work, reaching a classification accuracy of up to 95\% for carbon and 99\% for silicate dust. Conclusions. Our analysis shows that the JWST filters NIRCam F070W, F140M, F356W, F480M and MIRI F560W, F770W, F1000W, F1130W, F1500W, F1800W are likely the most important needed to determine the properties of dust formed in and around supernovae from future observations. We tested this on selected optical to infrared data of SN 1987A at 615 days past explosion and find good agreement with dust masses and temperatures inferred with standard fitting methods in the literature.

24 pages,19 figures, 7 tables, submitted to A&A 10/01/2022

References in corpus (21)

• The James Webb Space Telescope
• A distance to the Large Magellanic Cloud that is precise to one per cent
• A dusty, normal galaxy in the epoch of reionization
• The Evolution of Dust in the Early Universe with Applications to the Galaxy SDSS J1148+5251
• SN 2006tf: Precursor Eruptions and the Optically Thick Regime of Extremely Luminous Type IIn Supernovae
• Galaxy growth in a massive halo in the first billion years of cosmic history
• Rapid formation of large dust grains in the luminous supernova SN 2010jl
• Dust and the type II-plateau supernova 2004et
• A stubbornly large mass of cold dust in the ejecta of Supernova 1987A
• Thermal Emission from Warm Dust in the Most Distant Quasars
• Rapid dust production in submillimeter galaxies at z>4?
• The timing and location of dust formation in the remnant of SN 1987A
• The dust and gas content of the Crab Nebula
• The Young Supernova Experiment: Survey Goals, Overview, and Operations
• Dust yields in clumpy SN shells: SN 1987A revisited
• The light curve of SN 1987A revisited: constraining production masses of radioactive nuclides
• JINGLE -- IV. Dust, HI gas and metal scaling laws in the local Universe
• Old supernova dust factory revealed at the Galactic center
• The dust content of the Crab Nebula
• Disentangling Dust Components in SN 2010jl: The First 1400 Days
• The dust mass in Cassiopeia A from infrared and optical line flux differences

Cited by in corpus (1)

• Identifying type II quasars at intermediate redshift with few-shot learning photometric classification