# A Machine Learning Artificial Neural Network Calibration of the Strong-Line Oxygen Abundance

## TL;DR

This paper introduces a neural network-based calibration method for determining oxygen abundance in HII regions, outperforming traditional linear models and effectively reproducing galaxy metallicity patterns.

## Contribution

It presents the first application of neural networks to calibrate strong-line oxygen abundance, capturing complex non-linear relationships more accurately than previous methods.

## Key findings

- Neural network models outperform linear calibrations in predicting oxygen abundance.
- The new calibration reproduces galaxy metallicity gradients and mass-metallicity relations.
- Complex models are preferred given the current sample size.

## Abstract

The HII region oxygen abundance is a key observable for studying chemical properties of galaxies. Deriving oxygen abundances using optical spectra often relies on empirical strong-line calibrations calibrated to the direct method. Existing calibrations usually adopt linear or polynomial functions to describe the non-linear relationships between strong line ratios and Te oxygen abundances. Here, I explore the possibility of using an artificial neural network model to construct a non-linear strong-line calibration. Using about 950 literature HII region spectra with auroral line detections, I build multi-layer perceptron models under the machine learning framework of training and testing. I show that complex models, like the neural network, are preferred at the current sample size and can better predict oxygen abundance than simple linear models. I demonstrate that the new calibration can reproduce metallicity gradients in nearby galaxies and the mass-metallicity relationship. Finally, I discuss the prospects of developing new neural network calibrations using forthcoming large samples of HII region and also the challenges faced.