How to set up your first machine learning project in astronomy
arXiv:2502.08222 · doi:10.1038/s42254-024-00743-y
Abstract
Large, freely available, well-maintained data sets have made astronomy a popular playground for machine learning projects. Nevertheless, robust insights gained to both machine learning and physics could be improved by clarity in problem definition and establishing workflows that critically verify, characterize and calibrate machine learning models. We provide a collection of guidelines to setting up machine learning projects to make them likely useful for science, less frustrating and time-intensive for the scientist and their computers, and more likely to lead to robust insights. We draw examples and experience from astronomy, but the advice is potentially applicable to other areas in science.
Full-text access of the published version: https://rdcu.be/dQl5O
References in corpus (19)
- Machine learning and the physical sciences
- GIZMO: A New Class of Accurate, Mesh-Free Hydrodynamic Simulation Methods
- Smoothed Particle Hydrodynamics in Astrophysics
- AutoGluon-Tabular: Robust and Accurate AutoML for Structured Data
- Surveying the reach and maturity of machine learning and artificial intelligence in astronomy
- The eROSITA Final Equatorial-Depth Survey (eFEDS): Identification and characterization of the counterparts to the point-like sources
- Data Science Methodologies: Current Challenges and Future Approaches
- Deblending and Classifying Astronomical Sources with Mask R-CNN Deep Learning
- Astronomaly: Personalised Active Anomaly Detection in Astronomical Data
- Machine Learning Classification of SDSS Transient Survey Images
- A review of unsupervised learning in astronomy
- STACCATO: A Novel Solution to Supernova Photometric Classification with Biased Training Sets
- Data mining techniques on astronomical spectra data. II : Classification Analysis
- Data mining techniques on astronomical spectra data. I : Clustering Analysis
- Reducing model bias in a deep learning classifier using domain adversarial neural networks in the MINERvA experiment
- Astrophysics and Big Data: Challenges, Methods, and Tools
- GaMPEN: A Machine Learning Framework for Estimating Bayesian Posteriors of Galaxy Morphological Parameters
- Stellar Karaoke: deep blind separation of terrestrial atmospheric effects out of stellar spectra by velocity whitening
- Systematics in the SED Fitting Parameter Estimation of Composite Galaxies