C-4 trains neural networks on simulated cluster injections into real images to learn continuous, non-separable completeness functions, demonstrated in a pilot on NGC 628 to extend usable mass and age ranges and correct flattening in observed distributions.
Although the validation loss begins to plateau at𝑁≈5×104, the curves continue to decrease slightly up to𝑁=2.5×105, while the improvement beyond this point is minimal
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
astro-ph.IM 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
The Cluster Completeness Correction Calculator (C-4): A Neural-Network framework and pilot application to the LEGUS Survey of NGC 628
C-4 trains neural networks on simulated cluster injections into real images to learn continuous, non-separable completeness functions, demonstrated in a pilot on NGC 628 to extend usable mass and age ranges and correct flattening in observed distributions.