We present a machine learning (ML) approach for the prediction of galaxies’ dark matter halo masses which achieves an improved performance over conventional methods. We train three ML algorithms (XGBoost, random forests, and neural network) to predict halo masses using a set of synthetic galaxy catalogues that are built by populating dark matter haloes in N-body simulations with galaxies and that match both the clustering and the joint distributions of properties of galaxies in the Sloan Digital Sky Survey (SDSS). We explore the correlation of different galaxy- and group-related properties with halo mass, and extract the set of nine features that contribute the most to the prediction of halo mass. We find that mass predictions from the ML algorithms are more accurate than those from halo abundance matching (HAM) or dynamical mass estimates (DYN). Since the danger of this approach is that our training data might not accurately represent the real Universe, we explore the effect of testing the model on synthetic catalogues built with different assumptions than the ones used in the training phase. We test a variety of models with different ways of populating dark matter haloes, such as adding velocity bias for satellite galaxies. We determine that, though training and testing on different data can lead to systematic errors in predicted masses, the ML approach still yields substantially better masses than either HAM or DYN. Finally, we apply the trained model to a galaxy and group catalogue from the SDSS DR7 and present the resulting halo masses.
The total masses of galaxy clusters characterize many aspects of astrophysics and the underlying cosmology. It is crucial to obtain reliable and accurate mass estimates for numerous galaxy clusters over a wide range of redshifts and mass scales. We present a transfer-learning approach to estimate cluster masses using the ugriz-band images in the SDSS Data Release 12. The target masses are derived from X-ray or SZ measurements that are only available for a small subset of the clusters. We designed a semisupervised deep learning model consisting of two convolutional neural networks. In the first network, a feature extractor is trained to classify the SDSS photometric bands. The second network takes the previously trained features as inputs to estimate their total masses. The training and testing processes in this work depend purely on real observational data. Our algorithm reaches a mean absolute error (MAE) of 0.232 dex on average and 0.214 dex for the best fold. The performance is comparable to that given by redMaPPer, 0.192 dex. We have further applied a joint integrated gradient and class activation mapping method to interpret such a two-step neural network. The performance of our algorithm is likely to improve as the size of training data set increases. This proof-of-concept experiment demonstrates the potential of deep learning in maximizing the scientific return of the current and future large cluster surveys.
more » « less- NSF-PAR ID:
- 10365501
- Publisher / Repository:
- Oxford University Press
- Date Published:
- Journal Name:
- Monthly Notices of the Royal Astronomical Society
- Volume:
- 512
- Issue:
- 3
- ISSN:
- 0035-8711
- Format(s):
- Medium: X Size: p. 3885-3894
- Size(s):
- ["p. 3885-3894"]
- Sponsoring Org:
- National Science Foundation
More Like this
-
more » « less
ABSTRACT -
more » « less
ABSTRACT Cosmological simulations are an important theoretical pillar for understanding non-linear structure formation in our Universe and for relating it to observations on large scales. In several papers, we introduce our MillenniumTNG (MTNG) project that provides a comprehensive set of high-resolution, large-volume simulations of cosmic structure formation aiming to better understand physical processes on large scales and to help interpret upcoming large-scale galaxy surveys. We here focus on the full physics box MTNG740 that computes a volume of $740\, \mathrm{Mpc}^3$ with a baryonic mass resolution of $3.1\times ~10^7\, \mathrm{M_\odot }$ using arepo with 80.6 billion cells and the IllustrisTNG galaxy formation model. We verify that the galaxy properties produced by MTNG740 are consistent with the TNG simulations, including more recent observations. We focus on galaxy clusters and analyse cluster scaling relations and radial profiles. We show that both are broadly consistent with various observational constraints. We demonstrate that the SZ-signal on a deep light-cone is consistent with Planck limits. Finally, we compare MTNG740 clusters with galaxy clusters found in Planck and the SDSS-8 RedMaPPer richness catalogue in observational space, finding very good agreement as well. However, simultaneously matching cluster masses, richness, and Compton-y requires us to assume that the SZ mass estimates for Planck clusters are underestimated by 0.2 dex on average. Due to its unprecedented volume for a high-resolution hydrodynamical calculation, the MTNG740 simulation offers rich possibilities to study baryons in galaxies, galaxy clusters, and in large-scale structure, and in particular their impact on upcoming large cosmological surveys.
-
more » « less
ABSTRACT The circum-galactic medium (CGM) can feasibly be mapped by multiwavelength surveys covering broad swaths of the sky. With multiple large data sets becoming available in the near future, we develop a likelihood-free Deep Learning technique using convolutional neural networks (CNNs) to infer broad-scale physical properties of a galaxy’s CGM and its halo mass for the first time. Using CAMELS (Cosmology and Astrophysics with MachinE Learning Simulations) data, including IllustrisTNG, SIMBA, and Astrid models, we train CNNs on Soft X-ray and 21-cm (H i) radio two-dimensional maps to trace hot and cool gas, respectively, around galaxies, groups, and clusters. Our CNNs offer the unique ability to train and test on ‘multifield’ data sets comprised of both H i and X-ray maps, providing complementary information about physical CGM properties and improved inferences. Applying eRASS:4 survey limits shows that X-ray is not powerful enough to infer individual haloes with masses log (Mhalo/M⊙) < 12.5. The multifield improves the inference for all halo masses. Generally, the CNN trained and tested on Astrid (SIMBA) can most (least) accurately infer CGM properties. Cross-simulation analysis – training on one galaxy formation model and testing on another – highlights the challenges of developing CNNs trained on a single model to marginalize over astrophysical uncertainties and perform robust inferences on real data. The next crucial step in improving the resulting inferences on the physical properties of CGM depends on our ability to interpret these deep-learning models.
-
null (Ed.)Introduction: Vaso-occlusive crises (VOCs) are a leading cause of morbidity and early mortality in individuals with sickle cell disease (SCD). These crises are triggered by sickle red blood cell (sRBC) aggregation in blood vessels and are influenced by factors such as enhanced sRBC and white blood cell (WBC) adhesion to inflamed endothelium. Advances in microfluidic biomarker assays (i.e., SCD Biochip systems) have led to clinical studies of blood cell adhesion onto endothelial proteins, including, fibronectin, laminin, P-selectin, ICAM-1, functionalized in microchannels. These microfluidic assays allow mimicking the physiological aspects of human microvasculature and help characterize biomechanical properties of adhered sRBCs under flow. However, analysis of the microfluidic biomarker assay data has so far relied on manual cell counting and exhaustive visual morphological characterization of cells by trained personnel. Integrating deep learning algorithms with microscopic imaging of adhesion protein functionalized microfluidic channels can accelerate and standardize accurate classification of blood cells in microfluidic biomarker assays. Here we present a deep learning approach into a general-purpose analytical tool covering a wide range of conditions: channels functionalized with different proteins (laminin or P-selectin), with varying degrees of adhesion by both sRBCs and WBCs, and in both normoxic and hypoxic environments. Methods: Our neural networks were trained on a repository of manually labeled SCD Biochip microfluidic biomarker assay whole channel images. Each channel contained adhered cells pertaining to clinical whole blood under constant shear stress of 0.1 Pa, mimicking physiological levels in post-capillary venules. The machine learning (ML) framework consists of two phases: Phase I segments pixels belonging to blood cells adhered to the microfluidic channel surface, while Phase II associates pixel clusters with specific cell types (sRBCs or WBCs). Phase I is implemented through an ensemble of seven generative fully convolutional neural networks, and Phase II is an ensemble of five neural networks based on a Resnet50 backbone. Each pixel cluster is given a probability of belonging to one of three classes: adhered sRBC, adhered WBC, or non-adhered / other. Results and Discussion: We applied our trained ML framework to 107 novel whole channel images not used during training and compared the results against counts from human experts. As seen in Fig. 1A, there was excellent agreement in counts across all protein and cell types investigated: sRBCs adhered to laminin, sRBCs adhered to P-selectin, and WBCs adhered to P-selectin. Not only was the approach able to handle surfaces functionalized with different proteins, but it also performed well for high cell density images (up to 5000 cells per image) in both normoxic and hypoxic conditions (Fig. 1B). The average uncertainty for the ML counts, obtained from accuracy metrics on the test dataset, was 3%. This uncertainty is a significant improvement on the 20% average uncertainty of the human counts, estimated from the variance in repeated manual analyses of the images. Moreover, manual classification of each image may take up to 2 hours, versus about 6 minutes per image for the ML analysis. Thus, ML provides greater consistency in the classification at a fraction of the processing time. To assess which features the network used to distinguish adhered cells, we generated class activation maps (Fig. 1C-E). These heat maps indicate the regions of focus for the algorithm in making each classification decision. Intriguingly, the highlighted features were similar to those used by human experts: the dimple in partially sickled RBCs, the sharp endpoints for highly sickled RBCs, and the uniform curvature of the WBCs. Overall the robust performance of the ML approach in our study sets the stage for generalizing it to other endothelial proteins and experimental conditions, a first step toward a universal microfluidic ML framework targeting blood disorders. Such a framework would not only be able to integrate advanced biophysical characterization into fast, point-of-care diagnostic devices, but also provide a standardized and reliable way of monitoring patients undergoing targeted therapies and curative interventions, including, stem cell and gene-based therapies for SCD. Disclosures Gurkan: Dx Now Inc.: Patents & Royalties; Xatek Inc.: Patents & Royalties; BioChip Labs: Patents & Royalties; Hemex Health, Inc.: Consultancy, Current Employment, Patents & Royalties, Research Funding.more » « less
-
more » « less
Abstract We derive distances and masses of stars from the Sloan Digital Sky Survey (SDSS) Apache Point Observatory Galactic Evolution Experiment Data Release 17 using simple neural networks. Training data for distances comes from Gaia EDR3, supplemented by literature distances for star clusters. For masses, the network is trained using asteroseismic masses for evolved stars and isochrone masses for main-sequence stars. The models are trained on effective temperature, surface gravity, metallicity, and carbon and nitrogen abundances. We found that our distance predictions have median fractional errors that range from ≈20% at low log
g and ≈10% at higher logg with a standard deviation of ≈11%. The mass predictions have a standard deviation of ±12%. Using the masses, we derive ages for evolved stars based on the correspondence between mass and age for giant stars given by isochrones. The results are compiled into a Value Added Catalog called DistMass that contains distances and masses for 733,901 independent spectra, plus ages for 396,548 evolved stars.
