SpecLess: A Multi Survey Python Package for Machine Learning Classification of Galaxy Morphology and Activity from Photometry
Abstract
Broad band photometry enables scalable galaxy classification without spectroscopy at inference time, yet strong within survey performance may not transfer when the same galaxies are measured by another survey. We present SpecLess, an open source Python package implementing two photometric classification tasks: high confidence Galaxy Zoo 1 elliptical and spiral morphologies, and four SDSS spectroscopic activity reference classes (starforming, starburst, Seyfert, and LINER). Using SDSS+AllWISE, KiDS+VIKING, and DESI Legacy Imaging Surveys photometry, survey specific XGBoost classifiers achieve held out macro F1 scores of 0.9332 (SDSS; 35,554 galaxies) and 0.9237 (KiDS; 3,269) for morphology, and 0.7637 (SDSS; 16,931) and 0.7398 (DESI; 11,975) for activity. Starforming and starburst references are recovered more effectively than Seyfert and LINER, while feature ablations reveal complementary contributions from optical and mid infrared photometry. We quantify catalogue dependence using separately trained common feature models evaluated on matched galaxies with identical labels and data partitions. Relative to target trained models, macro F1 deficits are 0.0153 (SDSS to KiDS) and 0.0354 (KiDS to SDSS) for morphology (12,301 galaxies; 20 splits), and 0.0660 (SDSS to DESI) and 0.0406 (DESI to SDSS) for activity (11,975 test galaxies). Colour only refits, additive corrections, and optical infrared substitutions reveal direction dependent sensitivity without consistently recovering target trained performance. SpecLess v0.3.0 distributes four pretrained, survey specific classifiers through a unified Python interface. The package provides a reproducible baseline for photometric galaxy classification across multiple surveys while establishing an extensible, open source foundation for future developments in classification methods and photometric catalogue support.
Related
- Morphology classification for galaxies in the Kilo Degree Survey using a label-efficient self-supervised learning framework
- Morphology Classification for Galaxies in the Kilo Degree Survey Using a Label-efficient Self-supervised Learning Framework
- Time-domain photometry and activity evolution of interstellar comet 3I/ATLAS with BHTOM
- An Efficient Galaxy Morphology Classification Framework updated with Two-Stage Feature Extraction with AlexNet Encoding and UMAP
- Halo mass, star formation, and morphology in galaxies: A morphology-dependent connection between halo environment and star formation activity
BibTeX
@misc{aydin2026specless,
title = {{SpecLess: A Multi Survey Python Package for Machine Learning Classification of Galaxy Morphology and Activity from Photometry}},
author = {Uzay Aydin and Mehmet Tanriver},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.31545},
eprint = {2610.31545},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.31545},
}
RIS
TY - UNPB
TI - SpecLess: A Multi Survey Python Package for Machine Learning Classification of Galaxy Morphology and Activity from Photometry
AU - Uzay Aydin
AU - Mehmet Tanriver
PY - 2026
DA - 2026/10/22
PB - arXiv
DO - 10.48550/arxiv.2610.31545
UR - https://arxiv.org/abs/2610.31545
AB - Broad band photometry enables scalable galaxy classification without spectroscopy at inference time, yet strong within survey performance may not transfer when the same galaxies are measured by another survey. We present SpecLess, an open source Python package implementing two photometric classification tasks: high confidence Galaxy Zoo 1 elliptical and spiral morphologies, and four SDSS spectroscopic activity reference classes (starforming, starburst, Seyfert, and LINER). Using SDSS+AllWISE, KiDS+VIKING, and DESI Legacy Imaging Surveys photometry, survey specific XGBoost classifiers achieve held out macro F1 scores of 0.9332 (SDSS; 35,554 galaxies) and 0.9237 (KiDS; 3,269) for morphology, and 0.7637 (SDSS; 16,931) and 0.7398 (DESI; 11,975) for activity. Starforming and starburst references are recovered more effectively than Seyfert and LINER, while feature ablations reveal complementary contributions from optical and mid infrared photometry. We quantify catalogue dependence using separately trained common feature models evaluated on matched galaxies with identical labels and data partitions. Relative to target trained models, macro F1 deficits are 0.0153 (SDSS to KiDS) and 0.0354 (KiDS to SDSS) for morphology (12,301 galaxies; 20 splits), and 0.0660 (SDSS to DESI) and 0.0406 (DESI to SDSS) for activity (11,975 test galaxies). Colour only refits, additive corrections, and optical infrared substitutions reveal direction dependent sensitivity without consistently recovering target trained performance. SpecLess v0.3.0 distributes four pretrained, survey specific classifiers through a unified Python interface. The package provides a reproducible baseline for photometric galaxy classification across multiple surveys while establishing an extensible, open source foundation for future developments in classification methods and photometric catalogue support.
ER -