The recent surge in computer vision and deep learning has attracted significant attention within the galaxy morphology community.Various models have been implemented for galaxy morphology prediction with nearperfect a...The recent surge in computer vision and deep learning has attracted significant attention within the galaxy morphology community.Various models have been implemented for galaxy morphology prediction with nearperfect accuracy for certain classes.However,many studies treat deep learning models as black-box entities,lacking interpretability of their predictions.To address these limitations while ensuring good performance,we introduced an Improved SqueezeNet(I-SqueezeNet)by incorporating unique residual connections to improve the prediction performance,and we utilize Local Interpretable Model-Agnostic Explanations(LIME)to understand the interpretability.We evaluated the simplified SqueezeNet and I-SqueezeNet,with both channel and vertical concatenation,and compared their performances with those of some exiting methods such as Dieleman’s CNN,VGG13,DenseNet121,ResNet50,ResNext50,ResNext101,DSCNN and customized CNN in classifying galaxy objects using a dataset from the publicly available Galaxy Zoo Data Challenge Project.Our experiments showed that I-SqueezeNet with vertical concatenation achieved the highest average accuracy of 94.08%compared to other methods.Beyond achieving high accuracy,the application of LIME for model interpretation sheds light on the machine learning features and reasoning processes behind the model’s predictions.This information provides valuable insight into the galaxy morphology decision-making process,paving the way for further functional enhancements.展开更多
Hot subdwarf stars are important celestial objects in the study of stellar physics,but the population remains limited.The LAMOST DR12-V1,released in 2025 March,is currently the world’s largest spectroscopic database,...Hot subdwarf stars are important celestial objects in the study of stellar physics,but the population remains limited.The LAMOST DR12-V1,released in 2025 March,is currently the world’s largest spectroscopic database,holding great potential for the search of hot subdwarf stars.In this study,we propose a two-stage deep learning model called the hot subdwarf network(HsdNet),which integrates multiple advanced techniques,comprising a binary classification model in stage one and a five-class classification model in stage two.HsdNet not only achieves high precision with 94.33%and 94.00%in the binary and the five-class classification stages,respectively,but also quantifies the predicted uncertainty,enhancing the interpretability of the classification results through visualizing the model’s key focus regions.We applied HsdNet to the 601,217 spectra from the LAMOST DR12-V1 database,conducting a two-stage search for hot subdwarf candidates.In stage one,we initially identified candidates using the binary classification model.In stage two,the five-class classification model was used to further refine these candidates.Finally,we confirmed 1008 newly identified hot subdwarf stars.The distribution of their atmospheric parameters is consistent with that of known hot subdwarf stars.These efforts are expected to significantly advance the research on hot subdwarf stars.展开更多
We tested a new model of CMOS detector manufactured by the Gpixel Inc,for potential space astronomical application.In laboratory,we obtain some bias images under the typical application environment.In these bias image...We tested a new model of CMOS detector manufactured by the Gpixel Inc,for potential space astronomical application.In laboratory,we obtain some bias images under the typical application environment.In these bias images,clear random row noise pattern is observed.The row noise also contains some characteristic spatial frequencies.We quantitatively estimated the impact of this feature to photometric measurements,by making simulated images.We compared different bias noise types under strict parameter control.The result shows the row noise will significantly deteriorate the photometric accuracy.It effectively increases the readout noise by a factor of2-10.However,if it is properly removed,the image quality and photometric accuracy will be significantly improved.展开更多
A 30-m TeraHertz（THz） radio telescope is proposed to operate at 200 μm with an active primary surface.This paper presents sensitivity analysis of active surface panel positioning errors with optical performance in ...A 30-m TeraHertz（THz） radio telescope is proposed to operate at 200 μm with an active primary surface.This paper presents sensitivity analysis of active surface panel positioning errors with optical performance in terms of the Strehl ratio.Based on Ruze＇s surface error theory and using a Monte Carlo simulation,the effects of six rigid panel positioning errors,such as piston,tip,tilt,radial,azimuthal and twist displacements,were directly derived.The optical performance of the telescope was then evaluated using the standard Strehl ratio.We graphically illustrated the various panel error effects by presenting simulations of complete ensembles of full reflector surface errors for the six different rigid panel positioning errors.Study of the panel error sensitivity analysis revealed that the piston error and tilt/tip errors are dominant while the other rigid errors are much less important.Furthermore,as indicated by the results,we conceived of an alternative Master-Slave Concept-based（MSC-based） active surface by implementating a special Series-Parallel Concept-based（SPC-based） hexapod as the active panel support mechanism.A new 30-m active reflector based on the two concepts was demonstrated to achieve correction for all the six rigid panel positioning errors in an economically feasible way.展开更多
An empirical stellar spectral library with large coverage of stellar parameters is essential for stellar population synthesis and studies of stellar evolution.In this work,we present Stellar Spectra Factory(SSF),a too...An empirical stellar spectral library with large coverage of stellar parameters is essential for stellar population synthesis and studies of stellar evolution.In this work,we present Stellar Spectra Factory(SSF),a tool to generate empirical-based stellar spectra from arbitrary stellar atmospheric parameters.The relative flux-calibrated empirical spectra can be predicted by SSF given arbitrary effective temperature,surface gravity,and metallicity.SSF constructs the interpolation approach based on the Stellar LAbel Machine,using ATLAS-A library,which contains spectra covering from O type to M type,as the training data set.SSF is composed of four data-driven sub-models to predict empirical stellar spectra.Sub-model SSF-N can generate spectra from A to K type and some M giant stars,covering 3700<T_(eff)<8700 K,0<logg<dex,and-1.5<[M/H]<0.5 dex.Sub-model SSF-gM is mainly used to predict M giant spectra with 3520<T_(eff)<4000 K and-1.5<[M/H]<0.4 dex.Sub-model SSF-dM is for generating M dwarf spectra with 3295<T_(eff)<4040 K,-1.0<[M/H]<0.1 dex.Sub-model SSF-B can predict B-type spectra with 9000<T_(eff)<24,000 K and-5.2<M_(G)<1.5 mag.The accuracy of the predicted spectra is validated by comparing the flux of predicted spectra to those with same stellar parameters selected from the known spectral libraries,MILES and MaStar.The averaged difference of flux over optical wavelength between the predicted spectra and the corresponding ones in MILES and MaStar is less than 5%.More verification is conducted between the magnitudes calculated from the integration of the predicted spectra and the observations in PS1 and APASS bands with the same stellar parameters.No significant systematic difference is found between the predicted spectra and the photometric observations.The uncertainty is 0.08 mag in the r band for SSF-gM when comparing with the stars with the same stellar parameters selected from PS1.The uncertainty becomes 0.31 mag in the i band for SSF-dM when comparing with the stars with the same stellar parameters selected from APASS.展开更多
Spectral classification plays a crucial role in the analysis of astronomical data.Currently,stellar spectral classification primarily relies on one-dimensional(1D)spectra and necessitates a sufficient signal-to-noise ...Spectral classification plays a crucial role in the analysis of astronomical data.Currently,stellar spectral classification primarily relies on one-dimensional(1D)spectra and necessitates a sufficient signal-to-noise ratio(S/N).However,in cases where the S/N is low,obtaining valuable information becomes impractical.In this paper,we propose a novel model called DRC-Net(Double-branch celestial spectral classification network based on residual mechanisms)for stellar classification,which operates solely on two-dimensional(2D)spectra.The model consists of two branches that use 1D convolutions to reduce the dimensionality of the 2D spectral composed of both blue and red arms.In the following,the features extracted from both branches are fused,and the fused result undergoes further feature extraction before being fed into the classifier for final output generation.The data set is from the Large Sky Area Multi-Object Fiber Spectroscopic Telescope,comprising 15,680 spectra of F,G,and K types.The preprocessing process includes normalization and the early stopping mechanism.The experimental results demonstrate that the proposed DRC-Net achieved remarkable classification precision of 93.0%,83.5%,and86.9%for F,G,and K types,respectively,surpassing the performance of 1D spectral classification methods.Furthermore,different S/N intervals are tested to judge the classification ability of DRC-Net.The results reveal that DRC-Net,as a 2D spectral classification model,can deliver superior classification outcomes for the spectra with low S/Ns.These experimental findings not only validate the efficiency of DRC-Net but also confirm the enhanced noise resistance ability exhibited by 2D spectra.展开更多
In order to find the physical parameters which determine the accuracy of pho- tometric redshifts, we compare the spectroscopic and photometric redshifts （photo-z＇s） for a large sample of -80000 SDSS-2MASS galaxies....In order to find the physical parameters which determine the accuracy of pho- tometric redshifts, we compare the spectroscopic and photometric redshifts （photo-z＇s） for a large sample of -80000 SDSS-2MASS galaxies. Photo-z＇s in this paper are estimated by using the artificial neural network photometric redshift method （ANNz）. For a subset of -40000 randomly selected galaxies, we find that the photometric redshift recovers the spectroscopic redshift distribution very well with rms of 0.016. Our main results are as follows： （1） Using magnitudes directly as input parameters produces more accurate photo-z＇s than using colors; （2） The inclusion of 2MASS （J, H, Ks） bands does not improve photo-z＇s significantly, which indicates that near infrared data might not be important for the low-redshift sample; （3） Adding the concentration index （essentially the steepness of the galaxy brightness profile） as an extra input can improve the photo-z＇s estimation up to -10 percent; （4） Dividing the sample into early- and late-type galaxies by using the concentration index, normal and abnormal galaxies by using the emission line flux ratios, and red and blue galaxies by using color index （g - r）, we can improve the accuracy of photo-z＇s significantly; （5） Our analysis shows that the outliers （where there is a big difference between the spectroscopic and photometric redshifts） are mainly correlated with galaxy types, e.g., most outliers are late-type （blue） galaxies.展开更多
文摘The recent surge in computer vision and deep learning has attracted significant attention within the galaxy morphology community.Various models have been implemented for galaxy morphology prediction with nearperfect accuracy for certain classes.However,many studies treat deep learning models as black-box entities,lacking interpretability of their predictions.To address these limitations while ensuring good performance,we introduced an Improved SqueezeNet(I-SqueezeNet)by incorporating unique residual connections to improve the prediction performance,and we utilize Local Interpretable Model-Agnostic Explanations(LIME)to understand the interpretability.We evaluated the simplified SqueezeNet and I-SqueezeNet,with both channel and vertical concatenation,and compared their performances with those of some exiting methods such as Dieleman’s CNN,VGG13,DenseNet121,ResNet50,ResNext50,ResNext101,DSCNN and customized CNN in classifying galaxy objects using a dataset from the publicly available Galaxy Zoo Data Challenge Project.Our experiments showed that I-SqueezeNet with vertical concatenation achieved the highest average accuracy of 94.08%compared to other methods.Beyond achieving high accuracy,the application of LIME for model interpretation sheds light on the machine learning features and reasoning processes behind the model’s predictions.This information provides valuable insight into the galaxy morphology decision-making process,paving the way for further functional enhancements.
基金the Natural Science Foundation of Shandong Province with grant Nos.ZR2024MA063,ZR2022MA076 and ZR2022MA089Additional support was provided by the science research grants from the China Manned Space Project with grant Nos.CMS-CSST-2021-B05 and CMS-CSST-2021-A08+1 种基金supported by the National Natural Science Foundation of China(NSFC)under grant Nos.11873037 and 11803016Furthermore,the Young Scholars Program of Shandong University,Weihai(2016WHWLJH09)provided support for this research.
文摘Hot subdwarf stars are important celestial objects in the study of stellar physics,but the population remains limited.The LAMOST DR12-V1,released in 2025 March,is currently the world’s largest spectroscopic database,holding great potential for the search of hot subdwarf stars.In this study,we propose a two-stage deep learning model called the hot subdwarf network(HsdNet),which integrates multiple advanced techniques,comprising a binary classification model in stage one and a five-class classification model in stage two.HsdNet not only achieves high precision with 94.33%and 94.00%in the binary and the five-class classification stages,respectively,but also quantifies the predicted uncertainty,enhancing the interpretability of the classification results through visualizing the model’s key focus regions.We applied HsdNet to the 601,217 spectra from the LAMOST DR12-V1 database,conducting a two-stage search for hot subdwarf candidates.In stage one,we initially identified candidates using the binary classification model.In stage two,the five-class classification model was used to further refine these candidates.Finally,we confirmed 1008 newly identified hot subdwarf stars.The distribution of their atmospheric parameters is consistent with that of known hot subdwarf stars.These efforts are expected to significantly advance the research on hot subdwarf stars.
基金support by the National Key R&D Program of China No.2022YFF0503400。
文摘We tested a new model of CMOS detector manufactured by the Gpixel Inc,for potential space astronomical application.In laboratory,we obtain some bias images under the typical application environment.In these bias images,clear random row noise pattern is observed.The row noise also contains some characteristic spatial frequencies.We quantitatively estimated the impact of this feature to photometric measurements,by making simulated images.We compared different bias noise types under strict parameter control.The result shows the row noise will significantly deteriorate the photometric accuracy.It effectively increases the readout noise by a factor of2-10.However,if it is properly removed,the image quality and photometric accuracy will be significantly improved.
基金the National Natural Science Foundation of China (Grant Nos. 10973025 and 10833004)
文摘A 30-m TeraHertz（THz） radio telescope is proposed to operate at 200 μm with an active primary surface.This paper presents sensitivity analysis of active surface panel positioning errors with optical performance in terms of the Strehl ratio.Based on Ruze＇s surface error theory and using a Monte Carlo simulation,the effects of six rigid panel positioning errors,such as piston,tip,tilt,radial,azimuthal and twist displacements,were directly derived.The optical performance of the telescope was then evaluated using the standard Strehl ratio.We graphically illustrated the various panel error effects by presenting simulations of complete ensembles of full reflector surface errors for the six different rigid panel positioning errors.Study of the panel error sensitivity analysis revealed that the piston error and tilt/tip errors are dominant while the other rigid errors are much less important.Furthermore,as indicated by the results,we conceived of an alternative Master-Slave Concept-based（MSC-based） active surface by implementating a special Series-Parallel Concept-based（SPC-based） hexapod as the active panel support mechanism.A new 30-m active reflector based on the two concepts was demonstrated to achieve correction for all the six rigid panel positioning errors in an economically feasible way.
基金supported by the National Key R&D Program of China No.2019YFA0405500the National Natural Science Foundation of China(NSFC)with grant No.11835057+1 种基金Guo Shou Jing Telescope(the Large Sky Area Multi-Object Fiber Spectroscopic Telescope LAMOST)is a National Major Scientific Project built by the Chinese Academy of SciencesFunding for the project has been provided by the National Development and Reform Commission。
文摘An empirical stellar spectral library with large coverage of stellar parameters is essential for stellar population synthesis and studies of stellar evolution.In this work,we present Stellar Spectra Factory(SSF),a tool to generate empirical-based stellar spectra from arbitrary stellar atmospheric parameters.The relative flux-calibrated empirical spectra can be predicted by SSF given arbitrary effective temperature,surface gravity,and metallicity.SSF constructs the interpolation approach based on the Stellar LAbel Machine,using ATLAS-A library,which contains spectra covering from O type to M type,as the training data set.SSF is composed of four data-driven sub-models to predict empirical stellar spectra.Sub-model SSF-N can generate spectra from A to K type and some M giant stars,covering 3700<T_(eff)<8700 K,0<logg<dex,and-1.5<[M/H]<0.5 dex.Sub-model SSF-gM is mainly used to predict M giant spectra with 3520<T_(eff)<4000 K and-1.5<[M/H]<0.4 dex.Sub-model SSF-dM is for generating M dwarf spectra with 3295<T_(eff)<4040 K,-1.0<[M/H]<0.1 dex.Sub-model SSF-B can predict B-type spectra with 9000<T_(eff)<24,000 K and-5.2<M_(G)<1.5 mag.The accuracy of the predicted spectra is validated by comparing the flux of predicted spectra to those with same stellar parameters selected from the known spectral libraries,MILES and MaStar.The averaged difference of flux over optical wavelength between the predicted spectra and the corresponding ones in MILES and MaStar is less than 5%.More verification is conducted between the magnitudes calculated from the integration of the predicted spectra and the observations in PS1 and APASS bands with the same stellar parameters.No significant systematic difference is found between the predicted spectra and the photometric observations.The uncertainty is 0.08 mag in the r band for SSF-gM when comparing with the stars with the same stellar parameters selected from PS1.The uncertainty becomes 0.31 mag in the i band for SSF-dM when comparing with the stars with the same stellar parameters selected from APASS.
基金supported by the Natural Science Foundation of Tianjin Municipality(22JCYBJC00410)the National Natural Science Foundation of China-Chinese Academy of Sciences Joint Fund for Astronomy(U1931134)。
文摘Spectral classification plays a crucial role in the analysis of astronomical data.Currently,stellar spectral classification primarily relies on one-dimensional(1D)spectra and necessitates a sufficient signal-to-noise ratio(S/N).However,in cases where the S/N is low,obtaining valuable information becomes impractical.In this paper,we propose a novel model called DRC-Net(Double-branch celestial spectral classification network based on residual mechanisms)for stellar classification,which operates solely on two-dimensional(2D)spectra.The model consists of two branches that use 1D convolutions to reduce the dimensionality of the 2D spectral composed of both blue and red arms.In the following,the features extracted from both branches are fused,and the fused result undergoes further feature extraction before being fed into the classifier for final output generation.The data set is from the Large Sky Area Multi-Object Fiber Spectroscopic Telescope,comprising 15,680 spectra of F,G,and K types.The preprocessing process includes normalization and the early stopping mechanism.The experimental results demonstrate that the proposed DRC-Net achieved remarkable classification precision of 93.0%,83.5%,and86.9%for F,G,and K types,respectively,surpassing the performance of 1D spectral classification methods.Furthermore,different S/N intervals are tested to judge the classification ability of DRC-Net.The results reveal that DRC-Net,as a 2D spectral classification model,can deliver superior classification outcomes for the spectra with low S/Ns.These experimental findings not only validate the efficiency of DRC-Net but also confirm the enhanced noise resistance ability exhibited by 2D spectra.
基金Supported by the National Natural Science Foundation of China
文摘In order to find the physical parameters which determine the accuracy of pho- tometric redshifts, we compare the spectroscopic and photometric redshifts （photo-z＇s） for a large sample of -80000 SDSS-2MASS galaxies. Photo-z＇s in this paper are estimated by using the artificial neural network photometric redshift method （ANNz）. For a subset of -40000 randomly selected galaxies, we find that the photometric redshift recovers the spectroscopic redshift distribution very well with rms of 0.016. Our main results are as follows： （1） Using magnitudes directly as input parameters produces more accurate photo-z＇s than using colors; （2） The inclusion of 2MASS （J, H, Ks） bands does not improve photo-z＇s significantly, which indicates that near infrared data might not be important for the low-redshift sample; （3） Adding the concentration index （essentially the steepness of the galaxy brightness profile） as an extra input can improve the photo-z＇s estimation up to -10 percent; （4） Dividing the sample into early- and late-type galaxies by using the concentration index, normal and abnormal galaxies by using the emission line flux ratios, and red and blue galaxies by using color index （g - r）, we can improve the accuracy of photo-z＇s significantly; （5） Our analysis shows that the outliers （where there is a big difference between the spectroscopic and photometric redshifts） are mainly correlated with galaxy types, e.g., most outliers are late-type （blue） galaxies.
