A Machine-learning Approach to Integral Field Unit Spectroscopy Observations. III. Disentangling Multiple Components in H ii Regions

In the first two papers of this series, we demonstrated the dynamism of machine learning applied to optical spectral analysis by using neural networks to extract kinematic parameters and emission-line ratios directly from the spectra observed by the SITELLE instrument located at the Canada-France-Hawai'i Telescope. In this third installment, we develop a framework using a convolutional neural network trained on synthetic spectra to determine the number of line-of-sight components present in the SN3 filter (656-683 nm) spectral range of SITELLE. We compare this methodology to standard practice using Bayesian inference. Our results demonstrate that a neural network approach returns more accurate results and uses fewer computational resources over a range of spectral resolutions. Furthermore, we apply the network to SITELLE observations of the merging galaxy system NGC 2207/IC 2163. We find that the closest interacting sector and the central regions of the galaxies are best characterized by two line-of-sight components while the outskirts and spiral arms are well-constrained by a single component. Determining the number of resolvable components is crucial in disentangling different galactic components in merging systems and properly extracting their respective kinematics.

Automated summary

In this series, machine learning is demonstrated to extract kinematic parameters and emission-line ratios from spectra with neural networks, and a new framework using a convolutional neural network for determining the number of line-of-sight components is developed. Results show that the neural network approach is more accurate and efficient compared to traditional methods, particularly in analyzing merging galaxy systems like NGC 2207/IC 2163.