Linhua Deng

Linhua Deng

Auto-generated profile, based on publicly available information

Linhua Deng

School of Mathematics and Computer Science, Yunnan Minzu University, Kunming, China

Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
5 March 2024 in Astronomy & Astrophysics
Verified
Journal Article
Open access
PDF file
JCJie Cao
Jie Cao
TXTingting Xu
Tingting Xu
YDYuhe Deng
Yuhe Deng
LDLinhua Deng
Linhua Deng
MYMingcun Yang
Mingcun Yang
WZWeihong Zhou
Weihong Zhou
Context.The classification of galaxy morphology is among the most active fields in astronomical research today. With the development of artificial intelligence technology, deep learning is a useful tool in the classification of the morphology of galaxies and significant progress has been made in this domain. However, there is still some room for improvement in terms of classification accuracy, automation, and related issues.Aims.Convolutional vision Transformer (CvT) is an improved version of the Vision Transformer (ViT) model. It improves the performance of the ViT model by introducing a convolutional neural network (CNN). This study explores the performance of the CvT model in the area of galaxy morphology classification.Methods.In this work, the CvT model was applied, for the first time, in a five-class classification task of galaxy morphology. We added different types and degrees of noise to the original galaxy images to verify that the CvT model achieves good classification performance, even in galaxy images with low signal-to-noise ratios (S/Ns). Then, we also validated the classification performance of the CvT model for galaxy images at different redshifts based on the low-redshift dataset GZ2 and the high-redshift dataset Galaxy Zoo CANDELS. In addition, we visualized and analyzed the classification results of the CvT model based on the t-distributed stochastic neighborhood -embedding (t-SNE) algorithm.Results.We find that (1) compared with other five-class classification models of galaxy morphology based on CNN models, the average accuracy, precision, recall, and F1_score evaluation metrics of the CvT classification model are all higher than 98%, which is an improvement of at least 1% compared with those based on CNNs; (2) the classification visualization results show that different categories of galaxies are separated from each other in multi-dimensional space.Conclusions.The application of the CvT model to the classification study of galaxy morphology is a novel undertaking that carries important implications for future studies.

1 December 2021 in The Astrophysical Journal
Verified
Journal Article
Closed access
ZDZheng Deng
Zheng Deng
FWFeng Wang
Feng Wang
HDHui Deng
Hui Deng
LTLei. Tan
Lei. Tan
LDLinhua Deng
Linhua Deng
SFSong Feng
Song Feng
Improving the performance of solar flare forecasting is a hot topic in the solar physics research field. Deep learning has been considered a promising approach to perform solar flare forecasting in recent years. We first used the generative adversarial networks (GAN) technique augmenting sample data to balance samples with different flare classes. We then proposed a hybrid convolutional neural network (CNN) model (M) for forecasting flare eruption in a solar cycle. Based on this model, we further investigated the effects of the rising and declining phases for flare forecasting. Two CNN models, i.e., M rp and M dp, were presented to forecast solar flare eruptions in the rising phase and declining phase of solar cycle 24, respectively. A series of testing results proved the following. (1) Sample balance is critical for the stability of the CNN model. The augmented data generated by GAN effectively improved the stability of the forecast model. (2) For C-class, M-class, and X-class flare forecasting using Solar Dynamics Observatory line-of-sight magnetograms, the means of the true skill statistics (TSS) scores of M are 0.646, 0.653, and 0.762, which improved by 20.1%, 22.3%, and 38.0% compared with previous studies. (3) It is valuable to separately model the flare forecasts in the rising and declining phases of a solar cycle. Compared with model M, the means of the TSS scores for No-flare, C-class, M-class, and X-class flare forecasting of the M rp improved by 5.9%, 9.4%, 17.9%, and 13.1%, and those of the M dp improved by 1.5%, 2.6%, 11.5%, and 12.2%.

18 June 2019 in Monthly Notices of the Royal Astronomical Society
Verified
Journal Article
Open access
PDF file
LDL H Deng
L H Deng
XZX J Zhang
X J Zhang
GLG Y Li
G Y Li
HDH Deng
H Deng
FWF Wang
F Wang
Quasi-biennial oscillation (QBO) of solar magnetic activities is intrinsic to dynamo mechanism, but still far from fully understood. In this work, the phase and amplitude asymmetry of solar QBO of Hα flare activity in the northern and southern hemispheres is studied by the ensemble empirical mode decomposition, the cross-correlation analysis, and the wavelet transform technique. The following results are found: (1) solar QBO of Hα flare index in the two hemispheres has a complicated phase relationship, but does not show any systematic regularity; and (2) the solar cycle mode of solar Hα flare index in the northern hemisphere generally leads that in the southern one by nine months for the time interval from 1966 to 2014. The possible origin of these results is discussed.

9 March 2022 in Monthly Notices of the Royal Astronomical Society
Verified
Journal Article
Closed access
PDF file
HSHaomin Sun
Haomin Sun
HDHui Deng
Hui Deng
FWFeng Wang
Feng Wang
YMYing Mei
Ying Mei
TXTingting Xu
Tingting Xu
SWShoulin Wei
Shoulin Wei
The rapid development of new generation radio interferometers such as the Square Kilometer Array (SKA) has opened up unprecedented opportunities for astronomical research. However, anthropogenic radio frequency interference (RFI) from communication technologies and other human activities severely affects the fidelity of observational data. It also significantly reduces the sensitivity of the telescopes. We proposed a robust convolutional neural network (CNN) model to identify RFI based on machine-learning methods. We overlaid RFI on the simulation data of SKA1-LOW to construct three visibility function data sets. One data set was used for modelling, and the other two were used for validating the model’s usability. The experimental results show that the area under the curve reaches 0.93, with satisfactory accuracy and precision. We then further investigated the effectiveness of the model by identifying the RFI in the actual observational data from LOFAR and MeerKAT. The results show that the model performs well. The overall effectiveness is comparable to AOFlagger software and provides an improvement over existing methods in some instances.

1 June 2023 in The Astrophysical Journal Supplement Series
Verified
Journal Article
Open access
HUHuanbin焕斌Chi迟
Huanbin焕斌Chi迟
FEFeng锋Wang王
Feng锋Wang王
WEWenting雯婷Wang王
Wenting雯婷Wang王
HUHui辉Deng邓
Hui辉Deng邓
ZHZhongmu忠木Li李
Zhongmu忠木Li李
Studying open clusters (OCs) may help to provide a comprehensive understanding of the structure and evolution of the Milky Way. Many previous studies have systematically searched for OCs near the solar system within 1.2 kpc or 20° of Galactic latitude. However, few studies have searched for OCs at higher Galactic latitudes and deeper distances. In this study, based on a hybrid unsupervised clustering algorithm (friends-of-friends and pyUPMASK) and a binary classification algorithm (random forest), we extended the search region (i.e., Galactic latitude b ≥ 20 ° ) and performed a fine-grained blind search for Galactic clusters in Gaia DR3. After crossmatching, the newly discovered cluster candidates are fitted using isochrone fitting to estimate the main physical parameters (i.e., age and metallicity) of these clusters. These cluster candidates were then checked using manual visual inspection. Their statistical properties were also compared with previously exposed cluster catalogs. We found 1179 new clusters with considerable confidence within 5 kpc.

22 December 2017 in Journal of Space Weather and Space Climate
Verified
Journal Article
Open access
LDLinhua Deng
Linhua Deng
XZXiaojuan Zhang
Xiaojuan Zhang
JAJianmei An
Jianmei An
YCYunfang Cai
Yunfang Cai
Magnetic field structures on the solar atmosphere are not symmetric distribution in the northern and southern hemispheres, which is an important aspect of quasi-cyclical evolution of magnetic activity indicators that are related to solar dynamo theories. Three standard analysis techniques are applied to analyze the hemispheric coupling (north-south asymmetry and phase asynchrony) of monthly averaged values of solar Hα flare activity over the past 49 years (from 1966 January to 2014 December). The prominent results are as follows: (1) from a global point of view, solar Hα flare activity on both hemispheres are strongly correlated with each other, but the northern hemisphere precedes the southern one with a phase shift of 7 months; (2) the long-range persistence indeed exists in solar Hα flare activity, but the dynamical complexities in the two hemispheres are not identical; (3) the prominent periodicities of Hα flare activity are 17 years full-disk activity cycle and 11 years Schwabe solar cycle, but the short- and mid-term periodicities cannot determined by monthly time series; (4) by comparing the non-parametric rescaling behavior on a point-by-point basis, the hemispheric asynchrony of solar Hα flare activity are estimated to be ranging from several months to tens of months with an average value of 8.7 months. The analysis results could promote our knowledge on the long-range persistence, the quasi-periodic variation, and the hemispheric asynchrony of solar Hα flare activity on both hemispheres, and possibly provide valuable information for the hemispheric interrelation of solar magnetic activity.