Study of Star/Galaxy Classification Based on the XGBoost Algorithm

Machine learning has achieved great success in many areas today. The lifting algorithm has a strong ability to adapt to various scenarios with a high accuracy, and has played a great role in many fields. But in astronomy, the application of lifting algorithms is still rare. In response to the low classification accuracy of the dark star/galaxy source set in the Sloan Digital Sky Survey (SDSS), a new research result of machine learning, eXtreme Gradient Boosting (XGBoost), has been introduced. The complete photometric data set is obtained from the SDSS-DR7, and divided into a bright source set and a dark source set according to the star magnitude. Firstly, the ten-fold cross-validation method is used for the bright source set and the dark source set respectively, and the XGBoost algorithm is used to establish the star/galaxy classification model. Then, the grid search and other methods are used to adjust the XGBoost parameters. Finally, based on the galaxy classification accuracy and other indicators, the classification results are analyzed, by comparing with the models of function tree (FT), Adaptive boosting (Adaboost), Random Forest (RF), Gradient Boosting Decision Tree (GBDT), Stacked Denoising AutoEncoders (SDAE), and Deep Belief Nets (DBN). The experimental results show that, the XGBoost improves the classification accuracy of galaxies in the dark source classification by nearly 10% as compared to the function tree algorithm, and improves the classification accuracy of sources with the darkest magnitudes in the dark source set by nearly 5% as compared to the function tree algorithm. Compared with other traditional machine learning algorithms and deep neural networks, the XGBoost also has different degrees of improvement.     

The Sloan Digital Sky Survey monitor telescope pipeline

The photometric calibration of the Sloan Digital Sky Survey (SDSS) is a multi‐step process which involves data from three different telescopes: the 1.0‐m telescope at the US Naval Observatory (USNO), Flagstaff Station, Arizona (which was used to establish the SDSS standard star network); the SDSS 0.5‐m Photometric Telescope (PT) at the Apache Point Observatory (APO), NewMexico (which calculates nightly extinctions and calibrates secondary patch transfer fields); and the SDSS 2.5‐m telescope at APO (which obtains the imaging data for the SDSS proper). In this paper, we describe the Monitor Telescope Pipeline, MTPIPE, the software pipeline used in processing the data from the single‐CCD telescopes used in the photometric calibration of the SDSS (i.e., the USNO 1.0‐m and the PT). We also describe transformation equations that convert photometry on the USNO‐1.0m u ′g ′r ′i ′z ′ system to photometry the SDSS 2.5m ugriz system and the results of various validation tests of the MTPIPE software. Further, we discuss the semi‐automated PT factory, which runs MTPIPE in the day‐to‐day standard SDSS operations at Fermilab. Finally, we discuss the use of MTPIPE in current SDSS‐related projects, including the Southern u ′g ′r ′i ′z ′ Standard Star project, the u ′g ′r ′i ′z ′ Open Star Clusters project, and the SDSS extension (SDSS‐II). (© 2006 WILEY‐VCH Verlag GmbH & Co. KGaA, Weinheim)     

Database of molecular masers and variable stars

We present the database of maser sources in H2 O, OH and Si O lines that can be used to identify and study variable stars at evolved stages. Detecting the maser emission in H2 O, OH and Si O molecules toward infrared-excess objects is one of the methods for identifing long-period variables(LPVs, including miras and semiregulars), because these stars exhibit maser activity in their circumstellar shells. Our sample contains 1803 known LPV objects. Forty-six percent of these stars(832 objects) manifest maser emission in the line of at least one molecule: H2 O, OH or Si O. We use the database of circumstellar masers in order to search for LPVs which are not included in the General Catalogue of Variable Stars(GCVS). Our database contains 4806 objects(3866 objects without associations in GCVS) with maser detection in at least one molecule. Therefore it is possible to use the database in order to locate and study the large sample of LPV stars. The database can be accessed at http://maserdb.net.     

Retrieving volume FeO and TiO_2 abundances of lunar regolith with CE-2 CELMS data using BPNN method

The volume FeO and TiO_2 abundances(FTAs) of lunar regolith can be more important for understanding the geological evolution of the Moon compared to the optical and gamma-ray results. In this paper, the volume FTAs are retrieved with microwave sounder(CELMS) data from the Chang'E-2 satellite using the back propagation neural network(BPNN) method. Firstly, a three-layered BPNN network with five-dimensional input is constructed by taking nonlinearity into account. Then, the brightness temperature(TB) and surface slope are set as the inputs and the volume FTAs are set as the outputs of the BPNN network.Thereafter, the BPNN network is trained with the corresponding parameters collected from Apollo, Luna,and Surveyor missions. Finally, the volume FTAs are retrieved with the trained BPNN network using the four-channel TBderived from the CELMS data and the surface slope estimated from Lunar Orbiter Laser Altimeter(LOLA) data. The rationality of the retrieved FTAs is verified by comparing with the Clementine UV-VIS results and Lunar Prospector(LP) GRS results. The retrieved volume FTAs enable us to re-evaluate the geological features of the lunar surface. Several important results are as follows. Firstly, very-low-Ti(<1.5 wt.%) basalts are the most spatially abundant, and the surfaces with TiO_2> 5 wt.% constitute less than 10% of the maria. Also, two linear relationships occur between the FeO abundance(FA) and the TiO_2 abundance before and after the threshold, 16 wt.% for FA. Secondly, a new perspective on mare volcanism is derived with the volume FTAs in several important mare basins, although this conclusion should be verified with more sources of data. Thirdly, FTAs in the lunar regolith change with depth to the uppermost surface,and the change is complex over the lunar surface. Finally, the distribution of volume FTAs hints that the highlands crust is probably homogeneous, at least in terms of the microwave thermophysical parameters.     

A method for aligning the plastic scintillator detector on DAMPE

The Plastic Scintillator Detector(PSD) onboard the DArk Matter Particle Explorer(DAMPE)is designed to measure cosmic ray charge(Z) and to act as a veto detector for gamma ray identification.To fully exploit the charge identification potential of PSD and to enhance its capability to identify gamma ray events, we develop an alignment method for the PSD. The path length of a given track in the volume of a PSD bar is derived taking into account the shift and rotation alignment corrections. By examining energy spectra of corner-passing events and fully contained events, position shifts and rotations of all PSD bars are obtained, and are found to be on average about 1 mm and 0.0015 radian respectively. To validate the alignment method, we introduce artificial shifts and rotations of PSD bars into the detector simulation.These shift and rotation parameters can be recovered successfully by the alignment procedure. As a result of the PSD alignment procedure, the charge resolution of the PSD is improved from 4% to 8%, depending on the nuclei.     

Radiative association in Li+H revisited: the role of quasi-bound states

The role in radiative association of narrow resonances arising from quasi-bound levels is examined. For the rate coefficient the contribution from such levels is readily calculated in terms of the Einstein A -coefficient from bound rovibrational levels generated using a suitable alternative boundary condition. By locating systematically all the quasi-bound levels, an enhancement by more than an order of magnitude of the rate coefficient for Li(2s) + H(1s) association above about 600 K is obtained. The effect on the LiH abundance in the early Universe is no more than an increase of a factor of 3 for limited ranges of values of the redshift. For the Li(2p) state the effect of narrow resonances appears to have been taken into account in previous calculations.