Beyond mirkwood: Enhancing SED Modeling with Conformal Predictions (2312.14212v2)
Abstract: Traditional spectral energy distribution (SED) fitting techniques face uncertainties due to assumptions in star formation histories and dust attenuation curves. We propose an advanced machine learning-based approach that enhances flexibility and uncertainty quantification in SED fitting. Unlike the fixed NGBoost model used in mirkwood, our approach allows for any sklearn-compatible model, including deterministic models. We incorporate conformalized quantile regression to convert point predictions into error bars, enhancing interpretability and reliability. Using CatBoost as the base predictor, we compare results with and without conformal prediction, demonstrating improved performance using metrics such as coverage and interval width. Our method offers a more versatile and accurate tool for deriving galaxy physical properties from observational data.
- Simultaneous estimation of photometric redshifts and sed parameters: Improved techniques and a realistic error budget. The Astrophysical Journal, 804(1): 8.
- Breiman, L. 2001. Random forests. Machine learning, 45(1): 5–32.
- Galaxy stellar and total mass estimation using machine learning. arXiv:2311.10351.
- Conroy, C. 2013. Modeling the panchromatic spectral energy distributions of galaxies. Annual Review of Astronomy and Astrophysics, 51: 393–455.
- SIMBA: Cosmological simulations with black hole growth and feedback. Monthly Notices of the Royal Astronomical Society, 486(2): 2827–2849.
- CatBoost: gradient boosting with categorical features support. arXiv preprint arXiv:1810.11363.
- Gilda, S. 2019. Feature Selection for Better Spectral Characterization or: How I Learned to Start Worrying and Love Ensembles. arXiv preprint arXiv:1902.07215.
- Gilda, S. 2023. deep-REMAP: Parameterization of Stellar Spectra Using Regularized Multi-Task Learning. arXiv preprint arXiv:2311.03738.
- Unsupervised domain adaptation for constraining star formation histories. arXiv preprint arXiv:2112.14072.
- Uncertainty-aware learning for improvements in image quality of the Canada–France–Hawaii Telescope. Monthly Notices of the Royal Astronomical Society, 510(1): 870–902.
- Parameterization of MARVELS Spectra Using Deep Learning. In American Astronomical Society Meeting Abstracts #231, volume 231 of American Astronomical Society Meeting Abstracts, 349.02.
- mirkwood: Fast and Accurate SED Modeling Using Machine Learning. arXiv e-prints, arXiv:2101.04687.
- Astronomical Image Quality Prediction based on Environmental and Telescope Operating Conditions. arXiv e-prints, arXiv:2011.03132.
- Prospector: Stellar population inference from spectra and SEDs. ascl:1905.025.
- The EAGLE simulations of galaxy formation: Public release of halo and galaxy catalogues. Astronomy and Computing, 15: 72–89.
- Scikit-learn: Machine Learning in Python. Journal of Machine Learning Research, 12: 2825–2830.
- Gaussian processes for machine learning. Adaptive computation and machine learning. MIT Press. ISBN 026218253X.
- Conformalized quantile regression. Advances in neural information processing systems, 32.
- The EAGLE simulations of galaxy formation: the importance of the hydrodynamics scheme. Monthly Notices of the Royal Astronomical Society, 454(3): 2277–2291.
- The EAGLE project: simulating the evolution and assembly of galaxies and their environments. Monthly Notices of the Royal Astronomical Society, 446(1): 521–554.
- A Tutorial on Conformal Prediction. Journal of Machine Learning Research, 9(3).
- Parametrising Star Formation Histories. arXiv preprint arXiv:1404.0402.
- Soentpiet, R.; et al. 1999. Advances in kernel methods: support vector learning. MIT press.
- Introducing the Illustris Project: simulating the coevolution of dark and visible matter in the Universe. Monthly Notices of the Royal Astronomical Society, 444(2): 1518–1547.
- Fitting the integrated spectral energy distributions of galaxies. Astrophysics and Space Science, 331(1): 1–51.
Collections
Sign up for free to add this paper to one or more collections.
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.