Using X-Ray Morphological Parameters to Strengthen Galaxy Cluster Mass Estimates via Machine Learning

Abstract

We present a machine-learning approach for estimating galaxy cluster masses, trained using both Chandra and eROSITA mock X-ray observations of 2041 clusters from the Magneticum simulations. We train a random forest (RF) regressor, an ensemble learning method based on decision tree regression, to predict cluster masses using an input feature set. The feature set uses core-excised X-ray luminosity and a variety of morphological parameters, including surface brightness concentration, smoothness, asymmetry, power ratios, and ellipticity. The regressor is cross-validated and calibrated on a training sample of 1615 clusters (80% of sample), and then results are reported as applied to a test sample of 426 clusters (20% of sample). This procedure is performed for two different mock observation series in an effort to bracket the potential enhancement in mass predictions that can be made possible by including dynamical state information. The first series is computed from idealized Chandra-like mock cluster observations, with high spatial resolution, long exposure time (1 Ms), and the absence of background. The second series is computed from realistic-condition eROSITA mocks with lower spatial resolution, short exposures (2 ks), instrument effects, and background photons modeled. We report a 20% reduction in the mass estimation scatter when either series is used in our RF model compared to a standard regression model that only employs core-excised luminosity. The morphological parameters that hold the highest feature importance are smoothness, asymmetry, and surface brightness concentration. Hence these parameters, which encode the dynamical state of the cluster, can be used to make more accurate predictions of cluster masses in upcoming surveys, offering a crucial step forward for cosmological analyses.

Aging haloes: implications of the magnitude gap on conditional statistics of stellar and gas properties of massive haloes

“…For example, with a luminosity thresholded sample of 41 nearby clusters, Mulroy et al (2019) have shown that there is a strong correlation between the central gas entropy and residual of cluster observables about the mean relation. Morphological properties of the hot gas can also be employed to construct a more complex mass-observable relation to reduce the scatter (Green et al 2019). An interesting direction would be to check if the X-ray morphological parameters are a better indicator of the age or can more efficiently reduce the scatter.…”

The Three Hundred project: quest of clusters of galaxies morphology and dynamical state through Zernike polynomials

“…To be mentioned also other approaches based on wavelets analysis (Pierre & Starck 1998), on the Minkowski functionals (Beisbart et al 2001), or on machine learning (see e.g. Cohn & Battaglia 2019;Green et al 2019;Gupta & Reichardt 2020).…”

Deep learning for Sunyaev–Zel’dovich detection inPlanck

“…For galaxy cluster studies only, ML algorithms have been extensively used to successfully compute their properties such as their masses (e.g., Ntampaka et al 2015Ntampaka et al , 2016 Article number, page 1 of 11 arXiv:1911.10778v1 [astro-ph.CO] 25 Nov 2019 A&A proofs: manuscript no. aanda Green et al 2019;Calderon & Berlind 2019;Ho et al 2019). Therefore, those very powerful algorithms may help us in the near future to deal with the huge amount of data the community is collecting, and to answer some open questions in astrophysics and cosmology.…”