Extending Galactic foreground emission with neural networks
Giuseppe Puglisi, Avinash Anand, Marina Migliaccio
TLDR
This paper uses Cycle-GANs to simulate Carbon Monoxide emissions by learning from thermal dust and HI data, improving models, especially in high-Galactic latitudes.
Key contributions
- Introduces Cycle Generative Adversarial Networks (Cycle-GANs) for simulating Carbon Monoxide (CO) emissions.
- Learns features from Planck thermal dust emission and HI4PI survey data, targeting CO rotational lines.
- Validates generated emissions using angular power spectra and Minkowski functionals, confirming statistical accuracy.
- Aims to improve CO emission models in high-Galactic latitude areas where observations are sparse.
Why it matters
This research offers a novel method to simulate galactic CO emissions, addressing limitations in current models, especially for unobserved high-latitude regions. By leveraging neural networks with observational data, it paves the way for more accurate and comprehensive astrophysical simulations.
Original Abstract
We introduce an innovative approach employing Cycle Generative Adversarial Networks (Cycle-GANs) to accurately simulate Carbon Monoxide (CO) emissions by learning features identified in thermal dust emission maps from the Planck satellite alongside HI data from HI4PI survey. Our training dataset is complemented by the targets represented by the two rotational transition lines of CO (J:1-0, J:2-1) provided by the Planck satellite. We ensure the robustness of our dataset by focusing on regions with a signal-to-noise ratio (SNR) exceeding 8. The outcomes, assessed utilizing angular power spectra and Minkowski functionals, confirm that our algorithm proficiently achieves the set goals, indicating that the amplitudes of the generated emission accurately reproduce the angular correlations and share the statistical properties of the employed CO targets. We thus aim at improving the current models of CO emission specifically in the high-Galactic latitude areas that have been hardly observed by the most recent surveys, and, in doing so, to address and overcome the limitations affecting current models regions. This research lays the groundwork for creating transformative synthetic simulations, leveraging convolutional neural networks tied to data procured from latest observations.
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.