Residual 1D CNN for Low SFR Surface Density Regression: A Design Note

TL;DR

This paper presents a modular 1D CNN based on residual networks, tailored for low SFR surface density regression in astronomy, emphasizing design, implementation, and diagnostic tools without external data analysis.

Contribution

Introduces a residual 1D CNN architecture optimized for sparse targets in photometric regression, with modular design and diagnostic features for astronomy applications.

Findings

Effective residual block structures for sparse targets

Optional loss weighting improves regression accuracy

Diagnostic tools aid residual analysis

Abstract

This technical note describes the design and modular implementation of a one-dimensional convolutional neural network (1D CNN) adapted from residual networks (ResNet), developed for photometric regression tasks with an emphasis on low star formation rate surface density ($\Sigma_{\mathrm{SFR}}$) inference. The model features residual block structures optimized for sparse targets, with optional loss weighting and diagnostic tools for analyzing residual behavior. The implementation (version \texttt{v1.4}) originated during a collaborative project and is documented here independently. No external data are reproduced or analyzed. This note provides a reusable architectural reference for scalar regression problems in astronomy and related domains.