cluster - 用户贡献 [zh-cn]

Seminar Plan(2023)

2024-04-17T06:52:12Z

Mi Chen：

{| class="wikitable"
|+ 2023
|-

! Date !! Speaker !! Title
|-
| 2024/4/17 || 陈宓 || Galaxy Decomposition [[:File:Galaxy decomposition 240417组会.pdf|pdf]]
|-
| 2024/1/24 || 秦松梅 || Unveiling the Binary Nature of NGC 2323
|-
| 2024/1/17 || 徐权峰|| --
|-
| 2024/1/10 || 王岚 (NAOC) || Formation of massive disk galaxies and bulge galaxies
|-
| 2024/1/3 || 王左磊 || 仿真中光锥的构建
|-
| 2023/12/27 || 梁晋宁 (Durham University) || Connection between galaxy morphology and dark-matter halo structure
|-
| 2023/12/20 || 钱永忠 (University of Minnesota) || The Origin and Evolution of the Elements: A Modern Perspective
|-
| 2023/12/13 || 李智 (SHNU) || Gas Dynamics in the Milky Way: Total Mass Distribution and the Bar Pattern Speed
|-
| 2023/11/22 || 刘桂梅 || OC formation triggered by supernovae
|-
| 2023/11/15 || 邱佳杰 || --
|-
| 2023/11/8 || 郑云亮（SJTU） || Measuring the X-Ray Properties of DESI Groups from eROSITA Final Equatorial-Depth Survey
|-
| 2023/11/1 || 姜方周 (PKU) || Galaxy-halo connection and near-field cosmology with numerical and semi-analytic methods 
|-
| 2023/10/25 || 唐通 || --
|-
| 2023/10/18 || 潘翠云 || --
|-
| 2023/10/11 || 刘成则 (SJTU) || 通过大样本研究超致密矮星系的性质
|-
| 2023/09/27 || 蒋悦悦 || --
|-
| 2023/09/20 || 陈宓 || --
|-
| 2023/09/13 || 李春燕 || --
|-
| 2023/09/06 || 郑赟 (SJTU) || PAC V. The Roles of Mass and Environment in the Quenching of Satellite Galaxies
|-
| 2023/08/30 || Kartick Sarkar (Tel Aviv University) || Supernovae bubbles and winds
|-
| 2023/08/15 || Hugh Jones (University of Hertfordshire) || A blue depression in M dwarfs - a tale of two M5 dwarfs
|-
| 2023/07/19 || 赵倩文 || --
|-
| 2023/07/12 || 张茜 || --
|-
| 2023/07/07 || Judit Donada Oliu (University of Barcelona) || The multiplicity fraction in 202 open clusters from Gaia
|-
| 2023/06/21 || 简明杰 (Stockholm University) || Dispersing star-light in the near-infrared: stellar parameters and abundances
|-
| 2023/07/12 || 秦松梅 || Split Main-sequence of Galactic open clusters
|-
| 2023/06/07 || 陈丙秋 (YNU) || 银河系与麦哲伦云的尘埃和气体分布
|}

Seminar Plan(2023)

2024-04-17T06:50:34Z

Mi Chen：

{| class="wikitable"
|+ 2023
|-

! Date !! Speaker !! Title
|-
| 2024/4/17 || 陈宓 || Galaxy Decomposition
|-
| 2024/1/24 || 秦松梅 || Unveiling the Binary Nature of NGC 2323
|-
| 2024/1/17 || 徐权峰|| --
|-
| 2024/1/10 || 王岚 (NAOC) || Formation of massive disk galaxies and bulge galaxies
|-
| 2024/1/3 || 王左磊 || 仿真中光锥的构建
|-
| 2023/12/27 || 梁晋宁 (Durham University) || Connection between galaxy morphology and dark-matter halo structure
|-
| 2023/12/20 || 钱永忠 (University of Minnesota) || The Origin and Evolution of the Elements: A Modern Perspective
|-
| 2023/12/13 || 李智 (SHNU) || Gas Dynamics in the Milky Way: Total Mass Distribution and the Bar Pattern Speed
|-
| 2023/11/22 || 刘桂梅 || OC formation triggered by supernovae
|-
| 2023/11/15 || 邱佳杰 || --
|-
| 2023/11/8 || 郑云亮（SJTU） || Measuring the X-Ray Properties of DESI Groups from eROSITA Final Equatorial-Depth Survey
|-
| 2023/11/1 || 姜方周 (PKU) || Galaxy-halo connection and near-field cosmology with numerical and semi-analytic methods 
|-
| 2023/10/25 || 唐通 || --
|-
| 2023/10/18 || 潘翠云 || --
|-
| 2023/10/11 || 刘成则 (SJTU) || 通过大样本研究超致密矮星系的性质
|-
| 2023/09/27 || 蒋悦悦 || --
|-
| 2023/09/20 || 陈宓 || --
|-
| 2023/09/13 || 李春燕 || --
|-
| 2023/09/06 || 郑赟 (SJTU) || PAC V. The Roles of Mass and Environment in the Quenching of Satellite Galaxies
|-
| 2023/08/30 || Kartick Sarkar (Tel Aviv University) || Supernovae bubbles and winds
|-
| 2023/08/15 || Hugh Jones (University of Hertfordshire) || A blue depression in M dwarfs - a tale of two M5 dwarfs
|-
| 2023/07/19 || 赵倩文 || --
|-
| 2023/07/12 || 张茜 || --
|-
| 2023/07/07 || Judit Donada Oliu (University of Barcelona) || The multiplicity fraction in 202 open clusters from Gaia
|-
| 2023/06/21 || 简明杰 (Stockholm University) || Dispersing star-light in the near-infrared: stellar parameters and abundances
|-
| 2023/07/12 || 秦松梅 || Split Main-sequence of Galactic open clusters
|-
| 2023/06/07 || 陈丙秋 (YNU) || 银河系与麦哲伦云的尘埃和气体分布
|}

文件:Galaxy decomposition 240417组会.pdf

2024-04-17T06:49:39Z

Mi Chen：

2023 autumn

2023-11-27T06:32:04Z

Mi Chen：

===2023-11-13===
* 徐权峰：Gaussian Mixture Models: 任何概率分布都可以视为有限个高斯分布的加权融合 [http://cluster.shao.ac.cn/wiki/index.php?title=File:GMM.pdf GMMPDF] [http://cluster.shao.ac.cn/wiki/index.php?title=File:EM.pdf EMPDF] [http://cluster.shao.ac.cn/wiki/index.php?title=File:MLE.pdf MLEPDF]

===2023-11-14===
* 徐权峰(Workshop)：星系图像中生成模型的应用-报告 [http://cluster.shao.ac.cn/wiki/index.php?title=File:星系图像中生成模型的应用-报告.pdf PDF]

===2023-11-27===
* 叶人豪： Dirichlet distribution [[File:11.27KKC DirichletDistribution.pdf|PDF]]
* 陈宓：方向性统计 [[File:方向性统计_directional_statistics.pdf|PDF]]

2023 autumn

2023-11-27T06:31:16Z

Mi Chen：/* 2023-11-27 */

文件:方向性统计 directional statistics.pdf

2023-11-27T06:28:13Z

Mi Chen：

2023 autumn

2023-11-27T06:26:43Z

Mi Chen：

Students

2022-10-21T12:20:28Z

Mi Chen：

==居梦婷 Mengting Ju==
[[File:Jmt.jpg |150px|right|jumengting]]
Office: 1713

Tel: 5532

Email: mtju@shao.ac.cn

Research interests: galaxy formation

Supervisor：Lei Hao, Jun Yin, Jinliang Hou

Expected graduation:2022

[[ MTJU Wiki Main Page]]

==李璐 Lu Li==
[[File:IMG 5036.jpg|150px|right|lilu]]
Office: 1510

Tel: 5532

Email: lilu@shao.ac.cn

Research interests: Star clusters, Astrostatistics

Supervisor：Zhengyi Shao , Li Chen

Starting time of the Ph.D. program: 2015

==张书会 Shuhui Zhang ==
[[File:Shuhui Zhang.JPG|200px|right|Zhang]]

Office: 1510

Tel: 5322

Email: shzhang@shao.ac.cn

Research interests: Galaxies, Stars and Milk way

Supervisor：Zhengyi Shao, Ruixiang Chang, Jing Zhong

Expected graduation: 2018

==刘蓉蓉 Rongrong Liu==
[[File:Liurongrong.jpg|115px|right|liurongrong]]
Office:

Tel:

Email: lrongr@shao.ac.cn

Research interests: stellar population synthesis, star formation history of galaxies

Supervisor：Zhengyi Shao

Expected graduation: 2022

== 卢家风 Jiafeng Lu ==

[[File:jiafenglu.jpg|100px|right|jflu]]

Office: 1513

Tel:

Email: jflu@shao.ac.cn

Research interests:

Supervisor: Shiyin Shen

Expected graduation:

==钟文心 Wenxin Zhong==

[[File:钟文心.JPG|100px|right|zhongwenxin]]

Office: 1513

Tel:

Email: zhongwenxin@shao.ac.cn

Research interests: galaxy formation and evolution

Supervisor: Jian Fu , Shiyin Shen

Expected graduation:

==胡国真 Guozhen Hu==
[[File:1536673757543.jpeg|150px|right|guozhen]]

Office: 1513

Tel:

Email: hgz@shao.ac.cn

Research interests:

Supervisor：Zhengyi Shao

Expected graduation:

==张茜 Xi Zhang==
[[File:212532358773278788.jpg|100px|right|张茜]]

Office: 1516

Tel:

Email: zx@shao.ac.cn

Research interests: Open Clusters in the Milky Way

Supervisor：Li Chen , Jing Zhong

Expected graduation:

==潘翠云 Cuiyun Pan==

[[File:Ab.jpeg|100px|right|Ab]]

Office: 1713

Tel:

Email: cuiyunpan@shao.ac.cn

Research interests:

Supervisor：Zhengyi Shao

Expected graduation:

== 穆子豪 Zihao Mu ==

Office: 1712

Tel:

Email: muzihao@shao.ac.cn

Research interests:

Supervisor: Shiyin Shen

Expected graduation:
== 李春燕 Chunyan Li ==

Office: 1513

Tel:

Email: lichunyan@shao.ac.cn

Research interests: Blue stragglers in open clusters

Supervisor: Li Chen

Expected graduation:

== 邱佳杰 Jiajie Qiu ==

Office: 1713

Tel:

Email: jiajieqiu2682@shao.ac.cn

Research interests: Major-merging Pairs of Galaxies; Double-Peaked Narrow Emission-Line Galaxies; SFR - M* Relation

Supervisor: Shiyin Shen

Expected graduation:

== 赵倩文 Qianwen Zhao ==

Office: 1513

Tel:

Email: qianwenzhao@shao.ac.cn

Research interests:

Supervisor: Shiyin Shen

Expected graduation:

== 曾琪 Qi Zeng ==

Office: 1713

Tel:

Email: zengqi@shao.ac.cn

Research interests: dust extinction and dust emission

Supervisor: Shiyin Shen

Expected graduation:

== 秦松梅 Songmei Qin ==

Office: 1513

Tel:

Email: qsm@shao.ac.cn

Research interests: Open cluster and stellar rotation

Supervisor: Li Chen & Jing Zhong

== 刘桂梅 Guimei Liu ==

Office: 1513

Tel:

Email: liugm@shao.ac.cn

Research interests: Binary cluster

Supervisor: Li Chen & Jing Zhong

== 蒋悦悦 Yueyue Jiang ==

Office: 1513

Tel:

Email: jyy@shao.ac.cn

Research interests:

Supervisor: Li Chen & Jing Zhong

== 唐通 Tong Tang ==

Office: 1513

Tel:

Email: tangtong@shao.ac.cn

Research interests:

Supervisor: Li Chen & Jing Zhong

== 王左磊 Zuolei Wang ==

Office: 1513

Tel:

Email: wangzuolei@shao.ac.cn

Research interests:

Supervisor: Li Chen & Jing Zhong

== 徐权峰 Quanfeng Xu ==

Office: 1712

Tel:

Email: xuquanfeng@shao.ac.cn

Research interests: Deep Learning classification galaxy morphology

Project:
* [[Deep learning on galaxy morphology profile]]
* [[Auto clustering of galaxies after dimensionality reduction]]

Supervisor: Shiyin Shen

== 叶人豪 Renhao Ye ==

Office: 1515

Tel: 18721248926

Email: astre2019@foxmail.com

Research interests: Galaxy morphological classification, Deep learning

Supervisor: Shiyin Shen

== 陈宓 Mi Chen ==

Office: 1513

Tel: 18105772388

Email: michen@shao.ac.cn

Research interests: Galaxy morphology, Deep learning

Supervisor: Rafael S de Souza, Shiyin Shen

==[[已毕业学生|Graduated students]]==

King Kong Club

2022-10-17T14:43:39Z

Mi Chen：

==2022_autumn==
===2022-10-17===
*JWST CEERS天区中星系形态的分析 [https://arxiv.org/abs/2210.01110v1]
:* Morfometryka的非参数测量，Asymmetry和spirality结合很好的区分形态
:* JSWT的图像和HST图像的差异：更反映星族特征，更规则的形态，Hubble序列高红移仍存在，特别是对小质量星系
*钟文心：eFEDs巡天观测soft X-ray背景观测银河系热CGM [[File:2210.03133.pdf|paper]]
:*在soft X-ray背景的光谱拟合中加入太阳风exchange charge和银冕发射的X-ray辐射成分，更好地约束银河系CGM的金属丰度和温度。
*曾琪：利用远红外观测数据及辐射转移模型计算漩涡星系(NGC 4013, NGC 5907 and NGC 4565)尘埃的发射率 [https://arxiv.org/pdf/astro-ph/0406389.pdf]
*陈宓：利用SVD降维的前2维数据+星系某性质数据形成热图（galaxy manifold），并借此研究星系在Galaxy manifold上的统计与演化规律 [https://arxiv.org/pdf/2210.05862.pdf]

===2022-09-26===
* 沈世银：线性回归模型中基本统计概念的辨析： [https://arxiv.org/abs/2209.09073v1]
* 赵倩文：红蓝星系金属丰度的差异与星系大小有关 arXiv:2208.06939

===2022-09-19===
* 冯帅：基于JWST的星系科学文章列表 [https://ui.adsabs.harvard.edu/public-libraries/-cFx990hTpyIv7SLrUQK7A Link]
* 曾琪：M33辐射转移模型 arXiv:1905.09838
* 徐权峰：基于胶囊网络(Capsules Networks)的星系图像特性提取 [https://doi.org/10.1093/mnras/stac2105 paper] and arXiv:1710.09829v2

===2022-09-05===
*叶人豪：Morpheus应用到JWST分析早期盘星系 arXiv:2208.11456v1
*沈世银：从暗晕的质量函数的角度来估计高红移星系中可能混入的低红移的星系的数目 arXiv:2208.12828
*居梦婷：利用[OII]7322,7332测量高红移星系的金属丰度 arXiv:2207.12430
*陈宓：利用神经网络学习超新星中的尘埃信息 arXiv:2207.10104
*赵倩文：研究JWST红移6.5-8的星系的恒星形成和电离特性 arXiv:2208.14999

===2022-08-29===
*曾琪：星际化学与物理（2022宜昌）REVIEW I [[File:星际物理与化学review.pptx]]
*卢家风：星际化学与物理（2022宜昌）REVIEW II [[File:宜昌.pptx]]
*徐权峰：天文信息学与虚拟天文台（2022丽江）REVIEW [url：[https://nadc.china-vo.org/events/cvo2021summer/info?info_id=21]]

===2022-08-22===
*沈世银
#星系光谱（不包含发射线）中的熵（信息量）的最小的特征就是D4000和Hdelta arXiv:2208.05489
#IFS观测中气相金属丰度的两点相关的测量及模型解释：相关长度，注入半径 arXiv:2206.08072
#星系中星族的恒星金属丰度与引力势（M/R)有一个较为紧密而且红蓝星系相互统一的关系 arXiv:2208.06939

==[[KKC_archive]]==

King Kong Club

2022-09-05T05:13:50Z

Mi Chen：/* 2022-09-05 */

==2022_autumn==

===2022-08-22===
*沈世银
#星系光谱（不包含发射线）中的熵（信息量）的最小的特征就是D4000和Hdelta arXiv:2208.05489
#IFS观测中气相金属丰度的两点相关的测量及模型解释：相关长度，注入半径 arXiv:2206.08072
#星系中星族的恒星金属丰度与引力势（M/R)有一个较为紧密而且红蓝星系相互统一的关系 arXiv:2208.06939

===2022-08-29===
*曾琪：星际化学与物理（2022宜昌）REVIEW I [[File:星际物理与化学review.pptx]]
*卢家风：星际化学与物理（2022宜昌）REVIEW II [[File:宜昌.pptx]]

===2022-09-05===
*叶人豪：Morpheus应用到JWST分析早期盘星系 arXiv:2208.11456v1
*沈世银：从暗晕的质量函数的角度来估计高红移星系中可能混入的低红移的星系的数目 arXiv:2208.12828
*居梦婷：利用[OII]7322,7332测量高红移星系的金属丰度 arXiv:2207.12430
*陈宓：利用神经网络学习超新星中的尘埃信息 arXiv:2207.10104

==[[KKC_archive]]==

Seminar Plan

2021-05-07T07:00:13Z

Mi Chen：/* 1st semester */

腾讯会议ID： 4786244041

==1st semester==

{| class="wikitable"
|-
! Date !! Speaker !! Title
|-
|2021.3.3 || Fu Jian || Simulation and emulation of 21cm HI signals for SKA
|-
|2021.3.24 || Zhengyi Shao || Using the Gaia parallax correctly - The importance and the composition of the parallax uncertainty
[[File:DistancesInTheEraOfGaia.pptx|thumb]]
|-
|2021.3.31 ||Rongrong Li || MaNGA_map [[:File:MaNGA_map.pptx|pptx]]
|-
|2021.4.16 || Lu Li || HDBSCAN [[:File:HDBSCAN.pdf|pdf]]
|-
|2021.4.21 || Shiyin Shen || deep exposure, multiple exposure and stacking [[:File:stacking.pdf|pdf]]
|-
|2021.5.7 || Mi Chen || CNN [[:File:CNN.pdf|pdf]]
|-
|}

----
[[Seminar Plan(2020)]]

[[Seminar Plan(2019)]]

[[Seminar Plan(2018)]]

[[Seminar Plan(2017)]]

[[Seminar Plan(2016)]]

[[Seminar Plan(2014-2015)]]

文件:CNN.pdf

2021-05-07T06:59:29Z

Mi Chen：

Seminar Plan

2021-05-07T06:53:02Z

Mi Chen：

腾讯会议ID： 4786244041

==1st semester==

{| class="wikitable"
|-
! Date !! Speaker !! Title
|-
|2021.3.3 || Fu Jian || Simulation and emulation of 21cm HI signals for SKA
|-
|2021.3.24 || Zhengyi Shao || Using the Gaia parallax correctly - The importance and the composition of the parallax uncertainty
[[File:DistancesInTheEraOfGaia.pptx|thumb]]
|-
|2021.3.31 ||Rongrong Li || MaNGA_map [[:File:MaNGA_map.pptx|pptx]]
|-
|2021.4.16 || Lu Li || HDBSCAN [[:File:HDBSCAN.pdf|pdf]]
|-
|2021.4.21 || Shiyin Shen || deep exposure, multiple exposure and stacking [[:File:stacking.pdf|pdf]]
|-
|2021.5.7 || Mi Chen || CNN [[:File:CNN.pptx|pptx]]
|-
|}

----
[[Seminar Plan(2020)]]

[[Seminar Plan(2019)]]

[[Seminar Plan(2018)]]

[[Seminar Plan(2017)]]

[[Seminar Plan(2016)]]

[[Seminar Plan(2014-2015)]]

Seminar Plan

2021-05-07T06:51:20Z

Mi Chen：

Merger identification

2021-04-22T15:07:16Z

Mi Chen：

== <big>'''Automatic Galaxy Classification '''</big>==
=== ABSTRACT ===
<nowiki>With the rapid growth in astronomical data produced by large sky survey telescopes, traditional manual classiﬁcation processes can no longer fulﬁll the requirements of precision and efﬁciency of spectral classiﬁcation. There is an urgent need to employ machine learning approaches to conduct automated galaxy classiﬁcation tasks. In this work, we are going to find a good enough method to classify the pair galaxies accurately， which may be a foundation for statistical work in the future.</nowiki>
 
=== <big>'''Data'''</big> ===
==== <big>'''Training data'''</big> ====
In this section, we will present how we download the training data and how to handle them.
 
===== <big>'''Where data from '''</big> =====
Galaxy Zoo is a public science project which classifies galaxy pictures at a wide range and high accuracy. Different from GZ1/2(from SDSS), Galaxy Zoo DECaLS are based on the data collected by DECaLS survey, which pictures are deeper. In addition, GZD1/2/5 hasn't released the galaxy catalog but present posted data[https://dx.doi.org/10.5281/zenodo.4196267], and we choose the automated one as which fits the researchers who prefer a large sample(we need to train a model). Learning from them, we download the picture in FITS as a pixel scale of 0.262 and the channels are "g", "r", and "z". The data structure is 3*255*255.'''we haven't done the data augmentation yet''', but we decide to use flip horizontal, random cropping, and scaling.
 
===== <big>'''how to label '''</big> =====
After getting the posted data in GZD1/2/5, we need to label them using the criteria based on Table-1. Label"disk/featured disk/elliptical/stars" and "none/merger/post-merger/minor-merger" are parallel in decision tree.

''"There will be a picture after I learned how to upload the picture :("''
 
<big>'''no-merge galaxy: '''</big>As our target is to classify the pair_galaxy, we first download the no-merge galaxies("none" in the decision tree) and rename it as "ra_dec_0.fits". The "0" means label "none", to compare with "1" as a set of merged galaxies with "merger", "post-merger", and "minor-merger". You can visit it at http://cluster.shao.ac.cn/~michen/nomerge/ (haven't already downloaded it). There are about 310,580 in 313,788(total GZD galaxies).
 
<big>'''merged galaxy: '''</big> As same as the no-merged galaxy, we download and rename the fits as "ra_dec_1_x.fits". The first"1" means they are merged galaxies, and the "x" will be "0" as "merger", "1" as "post-merger", and "2" as "minor-merger".
 
==== <big>''''raw' data'''</big> ====
The 'raw' data is what we want to classify. They are pair galaxies chosen from Feng, we have present the catagory at [http://cluster.shao.ac.cn/~shen/isopair/], we also share how to select the pair galaxies on it either. The whole data should be download in DESI, because DECaLS do not contain the dr8-north. We present the data at [http://cluster.shao.ac.cn/~michen/pair_fits/]
 
=== <big>'''Model'''</big> ===
We use the resnet model with a batch size of 1024 and learning rate at 0.001.
=== <big>'''What to do next'''</big> ===
* combine the "post-merge" and "minor-merge" to "after-merge" to solve the imbalance problem(merger:post:minor are almost 20:1:10)
* use self-supervised(not decided yet) to solve the imbalance problem between merged and no-merged galaxy.
* download the pair fits in mzls and bass
* redownload the merged fits and rename it on webpage.

==reference==
* Using transfer learning to detect galaxy mergers[https://ui.adsabs.harvard.edu/abs/2018MNRAS.479..415A/abstract]
* Deep learning predictions of galaxy merger stage and the importance of observational realism [https://ui.adsabs.harvard.edu/abs/2019MNRAS.490.5390B/abstract]
* Identification of low surface brightness tidal features in galaxies using convolutional neural networks [https://ui.adsabs.harvard.edu/abs/2019MNRAS.483.2968W/abstract]
* Identifying galaxy mergers in observations and simulations with deep learning[https://ui.adsabs.harvard.edu/abs/2019A%26A...626A..49P/abstract]

== say at last ==
CONTINUE UPDATING!!!_2021.4.22

Merger identification

2021-04-22T15:04:34Z

Mi Chen：

== <big>'''Automatic Galaxy Classification '''</big>==
=== ABSTRACT ===
<nowiki>With the rapid growth in astronomical data produced by large sky survey telescopes, traditional manual classiﬁcation processes can no longer fulﬁll the requirements of precision and efﬁciency of spectral classiﬁcation. There is an urgent need to employ machine learning approaches to conduct automated galaxy classiﬁcation tasks. In this work, we are going to find a good enough method to classify the pair galaxies accurately， which may be a foundation for statistical work in the future.</nowiki>
 
=== <big>'''Data'''</big> ===
==== <big>'''Training data'''</big> ====
In this section, we will present how we download the training data and how to handle them.
 
===== <big>'''Where data from '''</big> =====
Galaxy Zoo is a public science project which classifies galaxy pictures at a wide range and high accuracy. Different from GZ1/2(from SDSS), Galaxy Zoo DECaLS are based on the data collected by DECaLS survey, which pictures are deeper. In addition, GZD1/2/5 hasn't released the galaxy catalog but present posted data[https://dx.doi.org/10.5281/zenodo.4196267], and we choose the automated one as which fits the researchers who prefer a large sample(we need to train a model). Learning from them, we download the picture in FITS as a pixel scale of 0.262 and the channels are "g", "r", and "z". The data structure is 3*255*255.'''we haven't done the data augmentation yet''', but we decide to use flip horizontal, random cropping, and scaling.
 
===== <big>'''how to label '''</big> =====
After getting the posted data in GZD1/2/5, we need to label them using the criteria based on Table-1. Label"disk/featured disk/elliptical/stars" and "none/merger/post-merger/minor-merger" are parallel in decision tree.

''"There will be a picture after I learned how to upload the picture :("''
 
<big>'''no-merge galaxy: '''</big>As our target is to classify the pair_galaxy, we first download the no-merge galaxies("none" in the decision tree) and rename it as "ra_dec_0.fits". The "0" means label "none", to compare with "1" as a set of merged galaxies with "merger", "post-merger", and "minor-merger". You can visit it at http://cluster.shao.ac.cn/~michen/nomerge/ (haven't already downloaded it). There are about 310,580 in 313,788(total GZD galaxies).
 
<big>'''merged galaxy: '''</big> As same as the no-merged galaxy, we download and rename the fits as "ra_dec_1_x.fits". The first"1" means they are merged galaxies, and the "x" will be "0" as "merger", "1" as "post-merger", and "2" as "minor-merger".
 
==== <big>''''raw' data'''</big> ====
The 'raw' data is what we want to classify. They are pair galaxies chosen from Feng, we have present the catagory at [http://cluster.shao.ac.cn/~shen/isopair/], we also share how to select the pair galaxies on it either. The whole data should be download in DESI, because DECaLS do not contain the dr8-north. We present the data at [http://cluster.shao.ac.cn/~michen/pair_fits/]
 
=== <big>'''Model'''</big> ===
We use the resnet model with a batch size of 1024 and learning rate at 0.001.
=== <big>'''3. What to do next'''</big> ===
* combine the "post-merge" and "minor-merge" to "after-merge" to solve the imbalance problem(merger:post:minor are almost 20:1:10)
* use self-supervised(not decided yet) to solve the imbalance problem between merged and no-merged galaxy.
* download the pair fits in mzls and bass
* redownload the merged fits and rename it on webpage.

==reference==
* Using transfer learning to detect galaxy mergers[https://ui.adsabs.harvard.edu/abs/2018MNRAS.479..415A/abstract]
* Deep learning predictions of galaxy merger stage and the importance of observational realism [https://ui.adsabs.harvard.edu/abs/2019MNRAS.490.5390B/abstract]
* Identification of low surface brightness tidal features in galaxies using convolutional neural networks [https://ui.adsabs.harvard.edu/abs/2019MNRAS.483.2968W/abstract]
* Identifying galaxy mergers in observations and simulations with deep learning[https://ui.adsabs.harvard.edu/abs/2019A%26A...626A..49P/abstract]

== say at last ==
CONTINUE UPDATING!!!_2021.4.22