Return of the features. Efficient feature selection and interpretation for photometric redshifts

Abstract

The explosion of data in recent years has generated an increasing need for new analysis techniques in order to extract knowledge from massive datasets. Machine learning has proved particularly useful to perform this task. Fully automatized methods have recently gathered great popularity, even though those methods often lack physical interpretability. In contrast, feature based approaches can provide both well-performing models and understandable causalities with respect to the correlations found between features and physical processes. Efficient feature selection is an essential tool to boost the performance of machine learning models. In this work, we propose a forward selection method in order to compute, evaluate, and characterize better performing features for regression and classification problems. Given the importance of photometric redshift estimation, we adopt it as our case study. We synthetically created 4,520 features by combining magnitudes, errors, radii, and ellipticities of quasars, taken from the SDSS. We apply a forward selection process, a recursive method in which a huge number of feature sets is tested through a kNN algorithm, leading to a tree of feature sets. The branches of the tree are then used to perform experiments with the random forest, in order to validate the best set with an alternative model. We demonstrate that the sets of features determined with our approach improve the performances of the regression models significantly when compared to the performance of the classic features from the literature. The found features are unexpected and surprising, being very different from the classic features. Therefore, a method to interpret some of the found features in a physical context is presented. The methodology described here is very general and can be used to improve the performance of machine learning models for any regression or classification task.

arXiv comment21 pages, 11 figures, accepted for publication on A&A, final version after language revision

References in corpus (34)

• The Seventh Data Release of the Sloan Digital Sky Survey
• LOFAR: The LOw-Frequency ARray
• The Ninth Data Release of the Sloan Digital Sky Survey: First Spectroscopic Data from the SDSS-III Baryon Oscillation Spectroscopic Survey
• A Cosmology Calculator for the World Wide Web
• A Modified Magnitude System that Produces Well-Behaved Magnitudes, Colors, and Errors Even for Low Signal-to-Noise Ratio Measurements
• EMU: Evolutionary Map of the Universe
• Efficient Photometric Selection of Quasars from the Sloan Digital Sky Survey: II. ~1,000,000 Quasars from Data Release Six
• PHAT: PHoto-z Accuracy Testing
• 2MASS Photometric Redshift catalog: a comprehensive three-dimensional census of the whole sky
• The third data release of the Kilo-Degree Survey and associated data products
• KiDS-450: Testing extensions to the standard cosmological model
• KiDS-450: The tomographic weak lensing power spectrum and constraints on cosmological parameters
• Photometric redshift estimation via deep learning
• Redshift distributions of galaxies in the DES Science Verification shear catalogue and implications for weak lensing
• Photometric Redshifts of Quasars
• Robust Machine Learning Applied to Astronomical Datasets III: Probabilistic Photometric Redshifts for Galaxies and Quasars in the SDSS and GALEX
• Feature Representation in Convolutional Neural Networks
• A blind test of photometric redshifts on ground-based data
• On the realistic validation of photometric redshifts, or why Teddy will never be Happy
• Feature importance for machine learning redshifts applied to SDSS galaxies
• Hierarchical progressive surveys. Multi-resolution HEALPix data structures for astronomical images, catalogues, and 3-dimensional data cubes
• Photometric classification of emission line galaxies with Machine Learning methods
• Mining the SDSS archive. I. Photometric redshifts in the nearby universe
• An analysis of feature relevance in the classification of astronomical transients with machine learning methods
• Towards a census of super-compact massive galaxies in the Kilo Degree Survey
• Automated classification of Hipparcos unsolved variables
• Astroinformatics of galaxies and quasars: a new general method for photometric redshifts estimation
• Photometric redshift estimation based on data mining with PhotoRApToR
• Automated Probabilistic Classification of Transients and Variables
• KiDS-450: Tomographic Cross-Correlation of Galaxy Shear with {\it Planck} Lensing
• Feature Selection based on Machine Learning in MRIs for Hippocampal Segmentation
• Estimating Photometric Redshifts of Quasars via K-nearest Neighbor Approach Based on Large Survey Databases
• Automatic Survey-Invariant Variable Star Classification
• Genetic Algorithm Modeling with GPU Parallel Computing Technology

Cited by in corpus (26)

• Probabilistic Random Forest: A machine learning algorithm for noisy datasets
• Galaxy morphological classification in deep-wide surveys via unsupervised machine learning
• KiDS-SQuaD II: Machine learning selection of bright extragalactic objects to search for new gravitationally lensed quasars
• Photometric selection and redshifts for quasars in the Kilo-Degree Survey Data Release 4
• Photometric Redshifts from SDSS Images with an Interpretable Deep Capsule Network
• Improving the reliability of photometric redshift with machine learning
• Photometric redshifts with machine learning, lights and shadows on a complex data science use case
• Photometric redshifts for X-ray-selected active galactic nuclei in the eROSITA era
• A Comparison of Photometric Redshift Techniques for Large Radio Surveys
• The PAU Survey: narrowband photometric redshifts using Gaussian processes
• Foreword to the Focus Issue on Machine Learning in Astronomy and Astrophysics
• Galaxy morphoto-Z with neural Networks (GaZNets). I. Optimized accuracy and outlier fraction from Imaging and Photometry
• CircleZ: Reliable Photometric redshifts for AGN computed using only photometry from Legacy Survey Imaging for DESI
• Unsupervised Classification of Galaxies. I. ICA feature selection
• Morpho-Photometric Redshifts
• Estimation of Photometric Redshifts. I. Machine Learning Inference for Pan-STARRS1 Galaxies Using Neural Networks
• ULISSE: A Tool for One-shot Sky Exploration and its Application to Active Galactic Nuclei Detection
• Data Deluge in Astrophysics: Photometric Redshifts as a Template Use Case
• Machine learning technique for morphological classification of galaxies from SDSS. II. The image-based morphological catalogs of galaxies at 0.02<z<0.1
• Machine learning technique for morphological classification of galaxies from the SDSS. III. Image-based inference of detailed features
• Anomaly detection in Astrophysics: a comparison between unsupervised Deep and Machine Learning on KiDS data
• Rejection criteria based on outliers in the KiDS photometric redshifts and PDF distributions derived by machine learning
• Machine learning applications in astrophysics: Photometric redshift estimation
• Navigating AGN variability with self-organizing maps
• Interpreting deep learning-based stellar mass estimation via causal analysis and mutual information decomposition
• A Quantum Genetic Algorithm with application to Cosmological Parameters Estimation