搜索

x

留言板

尊敬的读者、作者、审稿人, 关于本刊的投稿、审稿、编辑和出版的任何问题, 您可以本页添加留言。我们将尽快给您答复。谢谢您的支持!

姓名
邮箱
手机号码
标题
留言内容
验证码

基于机器学习J1-J2反铁磁海森伯自旋链相变点的识别方法

王伟 揭泉林

引用本文:
Citation:

基于机器学习J1-J2反铁磁海森伯自旋链相变点的识别方法

王伟, 揭泉林

Identifying phase transition point of J1-J2 antiferromagnetic Heisenberg spin chain by machine learning

Wang Wei, Jie Quan-Lin
PDF
HTML
导出引用
  • 通过序参量来研究量子相变是比较传统的做法, 而从机器学习的角度研究相变是一块全新的领域. 本文提出了先采用无监督学习算法中的高斯混合模型对J1-J2反铁磁海森伯自旋链系统的态矢量进行分类, 再使用监督学习算法中的卷积神经网络鉴别无监督学习算法给出的分类点是否是相变点的方法, 并使用交叉验证的方法对学习效果进行验证. 结果表明, 上述机器学习方法可以从基态精确找到J1J2反铁磁海森伯自旋链系统的一阶相变点、无法找到无穷阶相变点, 从第一激发态不仅能找到一阶相变点, 还能找到无穷阶相变点.
    Studying quantum phase transitions through order parameters is a traditional method, but studying phase transitions by machine learning is a brand new field. The ability of machine learning to classify, identify, or interpret massive data sets may provide physicists with similar analyses of the exponentially large data sets embodied in the Hilbert space of quantum many-body system. In this work, we propose a method of using unsupervised learning algorithm of the Gaussian mixture model to classify the state vectors of the J1-J2 antiferromagnetic Heisenberg spin chain system, then the supervised learning algorithm of the convolutional neural network is used to identify the classification point given by the unsupervised learning algorithm, and the cross-validation method is adopted to verify the learning effect. Using this method, we study the J1-J2 Heisenberg spin chain system with chain length N = 8, 10, 12, 16 and obtain the same conclusion. The first order phase transition point of J1-J2 antiferromagnetic Heisenberg spin chain system can be accurately found from the ground state vector, but the infinite order phase transition point cannot be found from the ground state vector. The first order and the infinite order phase transition point can be found from the first excited state vector, which indirectly shows that the first excited state may contain more information than the ground state of J1-J2 antiferromagnetic Heisenberg spin chain system. The visualization of the state vector shows the reliability of the machine learning algorithm, which can extract the feature information from the state vector. The result reveals that the machine learning techniques can directly find some possible phase transition points from a large set of state vectorwithout prior knowledge of the energy or locality conditions of the Hamiltonian, which may assists us in studying unknown systems. Supervised learning can verify the phase transition points given by unsupervised learning, thereby indicating that we can discover some useful information about unknown systems only through machine learning techniques. Machine learning techniques can be a basic research tool in strong quantum-correlated systems, and it can be adapted to more complex systems, which can help us dig up hidden information.
      通信作者: 揭泉林, qljie@whu.edu.cn
    • 基金项目: 国家自然科学基金(批准号: 1217050658)资助的课题
      Corresponding author: Jie Quan-Lin, qljie@whu.edu.cn
    • Funds: Project supported by the National Natural Science Foundation of China (Grant No. 1217050658)
    [1]

    Lei W 2016 Phys. Rev. B. 94 195105Google Scholar

    [2]

    Wetzel S J 2017 Phys. Rev. E 96 022140Google Scholar

    [3]

    Huang L, Wang L 2017 Phys. Rev. B 95 035105Google Scholar

    [4]

    Phiala E S, Daniel T, William D 2018 Phys. Rev. D 97 094506Google Scholar

    [5]

    LakovlevI A, SotnikovO M, MazurenkoV V 2018 Phys. Rev. B 98 174411Google Scholar

    [6]

    Dong X Y, Pollmann F, Zhang X F 2019 Phys. Rev. B 99 121104Google Scholar

    [7]

    Tan D R, Jiang F J 2020 Phys. Rev. B 102 224434Google Scholar

    [8]

    Tan D R, Li C D, Zhu W P, Jiang F J 2020 New J. Phys. 22 063016Google Scholar

    [9]

    Maskara N, Buchhold M, Endres M 2021 arXiv: 2103.15855 [quant-ph]

    [10]

    Tanja D 2021 arXiv: 2103.07236[quant-ph]

    [11]

    Sondhi S L, Girvin S M, Carini J P, Shahar D 1997 Rev. Mod. Phys 69 315Google Scholar

    [12]

    Bulla R, Vojta M 2003 Rep. Prog. Phys. 66 2069Google Scholar

    [13]

    Walker N, Tam K M, Novak B, Jarrell M 2018 Phys. Rev. E. 98 053305Google Scholar

    [14]

    Jadrich R B, Lindquist B A, Pineros W D, Truskeet T M 2018 J. Chem. Phys. 149 194109Google Scholar

    [15]

    Canabarro A, Fanchini F F, Malvezzi A L, Pereira R, Chaves R 2019 Phys. Rev. B 100 045129Google Scholar

    [16]

    Carrasquilla J, Melko R G 2017 Nat. Phys. 13 431Google Scholar

    [17]

    Ahmadreza A, Michel P 2020 arXiv: 2007.09764 [cond-mat. stat-mech]

    [18]

    Chitra R, Pati S, Krishnamurthy H R, Sen D, Ramasesha S 1995 Phys. Rev. B 52 6581Google Scholar

    [19]

    Castilla G, Chakravarty S, Emery V J 1995 Phys. Rev. L 75 1823Google Scholar

    [20]

    Shu C, Li W, Shi J G, Wang Y P 2007 Phys. Rev. E 76 061108Google Scholar

    [21]

    Qian X F, Shi T, Li Y, Song Z, Sun C P 2005 Phys. Rev. A 72 012333Google Scholar

    [22]

    周志华 2016 机器学习 (北京: 清华大学出版社) 第206页

    Zhou Z H 2016 Machine Learning (Beijing: Tsinghua University Press) p206 (in Chinese)

    [23]

    李航 2012 统计机器学习 (北京: 清华大学出版社) 第162页

    Li H 2012The Elements of Statistical Learning (Beijing: Tsinghua University Press) p162 (in Chinese)

    [24]

    徐启伟, 王佩佩, 曾镇佳, 黄泽斌, 周新星, 刘俊敏, 李瑛, 陈书青, 范滇元 2020 物理学报 69 014209Google Scholar

    Xu Q W, Wang P P, Zeng Z J, Huang Z B, Zhou X X, Liu J M, Li Y, Chen S Q, Fan D Y 2020 Acta Phys. Sin. 69 014209Google Scholar

    [25]

    伊恩·古德费洛, 约书亚·本吉奥, 亚伦·库维尔 著 (赵申剑, 黎彧君, 符天凡, 李凯 译) 2017 深度学习 (北京:人民邮电出版社) 第143—317页

    Goodfellow L, Bengio Y, Courville A(translated by Zhang SJ, Li Y J, Fu T F, Li K)2017 Deep Learning (Beijing: The People's Posts and Telecommunications Press) pp143–317 (in Chinese)

  • 图 1  不同链长的 J1-J2海森伯自旋链系统基态与第一激发态能量随J2/J1的变化 (a) N = 8; (b) N = 10; (c) N = 12; (d) N = 16

    Fig. 1.  Ground and first excited energy level diagram in J1-J2 Heisenberg spin chain system with chain length: (a) N = 8; (b) N = 10; (c) N = 12; (d) N = 16.

    图 2  (a) 训练数据为J2/J1$\in $[0, 1)的海森伯J1-J2模型基态矢量生成的GMM对基态矢量的分类结果; (b)采用标记为0的J2/J1$\in $[0.35, 0.45)和为1的J2/J1$\in $[0.55, 0.65); (c)标记为0的J2/J1$\in $[0.3, 0.4)和为1的J2/J1$\in $[0.55, 0.65); (d)标记为0的J2/J1$\in $[0.2, 0.3)和为1的J2/J1$\in $[0.55, 0.65)的基态态矢量作为训练数据, 训练所得的CNN模型对基态态矢量的预测结果

    Fig. 2.  (a) Ground state vector classification results of the GMM generated by the Heisenberg J1-J2 model ground state vector with the training data of J2/J1$\in $ [0, 1); (b) using the ground state vector of J2/J1$\in $[0.35, 0.45) marked as 0 and J2/J1$\in $[0.55, 0.65) marked as 1; (c) J2/J1$\in $[0.3, 0.4) marked as 0 and J2/J1$\in $[0.55, 0.65) marked as 1; (d) J2/J1$\in $[0.2, 0.3) marked as 0 and J2/J1$\in $[0.55, 0.65) marked as 1 as training data, the prediction results of the ground state vector by the trained convolutional neural network model.

    图 3  (a) 训练数据为J2/J1$\in $[0, 0.5)的海森伯J1-J2模型基态态矢量生成的GMM对基态态矢量的分类结果; (b) 分别为采用标记为0的J2/J1$\in $[0.25, 0.3)和为1的J2/J1$\in $[0.35, 0.4); (c)标记为0的J2/J1$\in $[0.2, 0.25)和为1的J2/J1$\in $[0.35, 0.4); (d)标记为0的J2/J1$\in $[0.2, 0.25)和为1的J2/J1$\in $[0.35, 0.4)(标记为1的数据是标记为0的5倍)的基态态矢量作为训练数据, 训练所得的CNN模型对基态态矢量的预测结果

    Fig. 3.  (a) Ground state vector classification results of the GMM generated by the Heisenberg J1-J2 model ground state vector with the training data of J2/J1$\in $ [0, 0.5); (b) respectively usingthe ground state vector of J2/J1$\in $[0.25, 0.3) marked as 0 and J2/J1$\in $[0.35, 0.4) marked as 1; (c) J2/J1$\in $[0.2, 0.25) marked as 0 and J2/J1$\in $[0.35, 0.4) marked as 1; (d) J2/J1$\in $[0.2, 0.25) marked as 0 and J2/J1$\in $[0.35, 0.4) marked as 1 (the data marked as 1 is 5 times as much as the data marked as 0)as training data, the prediction results of the ground state vector by the trained convolutional neural network model.

    图 4  (a) 训练数据为J2/J1$\in $[0, 1)的海森伯J1-J2模型第一激发态态矢量生成的GMM对第一激发态态矢量的分类结果; (b)分别为采用标记为0的J2/J1$\in $[0.35, 0.45)和为1的J2/J1$\in $[0.55, 0.65); (c)标记为0的J2/J1$\in $[0.3, 0.4)和为1的J2/J1$\in $[0.55, 0.65); (d)标记为0的J2/J1$\in $[0.35, 0.45)和为1的J2/J1$\in $[0.55, 0.65) (标记为1的数据是标记为0的5倍)的第一激发态态矢量作为训练数据, 训练所得的CNN模型对第一激发态态矢量的预测结果

    Fig. 4.  (a) The first excited state vector classification results of the GMM generated by the Heisenberg J1-J2 model first excited state vector with the training data of J2/J1 $\in $ [0, 1); (b) using the first excited state vector of J2/J1$\in $[0.35, 0.45) marked as 0 and J2/J1$\in $[0.55, 0.65) marked as 1; (c) J2/J1$\in $[0.3, 0.4) marked as 0 and J2/J1$\in $[0.55, 0.65) marked as 1; (d) J2/J1$\in $[0.35, 0.45) marked as 0 and J2/J1$\in $[0.55, 0.65) marked as 1 (the data marked as 1 is 5 times as much as the data marked as 0)as training data, the prediction results of the first excited state vector by the trained convolutional neural network model.

    图 5  (a)采用标记为0的J2/J1$\in $[0.1, 0.2), 标记为1的J2/J1$\in $[0.3, 0.4); (b)标记为0的J2/J1$\in $[0, 0.1), 标记为1的J2/J1$\in $[0.3, 0.4)的第一激发态态矢量作为训练数据, 训练所得的CNN模型对第一激发态态矢量的预测结果

    Fig. 5.  (a) Using the first excited state vector of J2/J1$\in $[0.1, 0.2) marked as 0 and J2/J1$\in $[0.3, 0.4) marked as 1; (b)J2/J1$\in $[0, 0.1) marked as 0 and J2/J1$\in $[0.3, 0.4) marked as 1 as training data, the prediction results of the first excited state vector by the trained convolutional neural network model.

    图 6  (a) 训练数据为J2/J1$\in $[0, 0.24)的海森伯J1-J2模型第一激发态态矢量生成的GMM对第一激发态态矢量的分类结果; (b), (c)分别为采用标记为0的J2/J1$\in $[0.05, 0.1)和为1的J2/J1$\in $[0.15, 0.2); 标记为0的J2/J1$\in $[0, 0.05)和为1的J2/J1$\in $[0.15, 0.2)的第一激发态态矢量作为训练数据, 训练所得的CNN模型对第一激发态态矢量的预测结果; (d) 训练数据为J2/J1$\in $[0.25, 0.5)的海森伯J1-J2模型第一激发态态矢量生成的GMM对第一激发态态矢量的分类结果

    Fig. 6.  (a) The first excited state vector classification results of the GMM generated by the Heisenberg J1-J2 model first excited state vector with the training data of J2/J1 $\in $ [0, 0.24); (b) (c) respectively using the first excited state vector of J2/J1$\in $[0.05, 0.1) marked as 0 and J2/J1$\in $[0.15, 0.2) marked as 1; J2/J1$\in $[0, 0.05) marked as 0 and J2/J1$\in $[0.15, 0.2) marked as 1 as training data, the prediction results of the first excited state vector by the trained convolutional neural network model; (d) he first excited state vector classification results of the GMM generated by the Heisenberg J1-J2 model first excited state vector with the training data of J2/J1$\in $[0.25, 0.5).

    图 7  海森伯 J1-J2模型基态态矢量变换而来的灰度图 (a) J2/J1 = 0.44; (b) J2/J1 = 0.49; (c) J2/J1 = 0.51; (d) J2/J1 = 0.58

    Fig. 7.  Gray scale images transformed from the ground state vector of the Heisenberg J1-J2 model: (a) J2/J1 = 0.44; (b) J2/J1 = 0.49; (c) J2/J1 = 0.51; (d) J2/J1 = 0.58.

    图 8  海森伯J1-J2模型第一激发态态矢量变换而来的灰度图 (a) J2/J1 = 0.24; (b) J2/J1 = 0.25; (c) J2/J1 = 0.49; (d) J2/J1 = 0.51

    Fig. 8.  Gray scale images transformed from the first excited state vector of the Heisenberg J1-J2 model: (a) J2/J1 = 0.24; (b) J2/J1 = 0.25; (c) J2/J1 = 0.49; (d) J2/J1 = 0.51.

  • [1]

    Lei W 2016 Phys. Rev. B. 94 195105Google Scholar

    [2]

    Wetzel S J 2017 Phys. Rev. E 96 022140Google Scholar

    [3]

    Huang L, Wang L 2017 Phys. Rev. B 95 035105Google Scholar

    [4]

    Phiala E S, Daniel T, William D 2018 Phys. Rev. D 97 094506Google Scholar

    [5]

    LakovlevI A, SotnikovO M, MazurenkoV V 2018 Phys. Rev. B 98 174411Google Scholar

    [6]

    Dong X Y, Pollmann F, Zhang X F 2019 Phys. Rev. B 99 121104Google Scholar

    [7]

    Tan D R, Jiang F J 2020 Phys. Rev. B 102 224434Google Scholar

    [8]

    Tan D R, Li C D, Zhu W P, Jiang F J 2020 New J. Phys. 22 063016Google Scholar

    [9]

    Maskara N, Buchhold M, Endres M 2021 arXiv: 2103.15855 [quant-ph]

    [10]

    Tanja D 2021 arXiv: 2103.07236[quant-ph]

    [11]

    Sondhi S L, Girvin S M, Carini J P, Shahar D 1997 Rev. Mod. Phys 69 315Google Scholar

    [12]

    Bulla R, Vojta M 2003 Rep. Prog. Phys. 66 2069Google Scholar

    [13]

    Walker N, Tam K M, Novak B, Jarrell M 2018 Phys. Rev. E. 98 053305Google Scholar

    [14]

    Jadrich R B, Lindquist B A, Pineros W D, Truskeet T M 2018 J. Chem. Phys. 149 194109Google Scholar

    [15]

    Canabarro A, Fanchini F F, Malvezzi A L, Pereira R, Chaves R 2019 Phys. Rev. B 100 045129Google Scholar

    [16]

    Carrasquilla J, Melko R G 2017 Nat. Phys. 13 431Google Scholar

    [17]

    Ahmadreza A, Michel P 2020 arXiv: 2007.09764 [cond-mat. stat-mech]

    [18]

    Chitra R, Pati S, Krishnamurthy H R, Sen D, Ramasesha S 1995 Phys. Rev. B 52 6581Google Scholar

    [19]

    Castilla G, Chakravarty S, Emery V J 1995 Phys. Rev. L 75 1823Google Scholar

    [20]

    Shu C, Li W, Shi J G, Wang Y P 2007 Phys. Rev. E 76 061108Google Scholar

    [21]

    Qian X F, Shi T, Li Y, Song Z, Sun C P 2005 Phys. Rev. A 72 012333Google Scholar

    [22]

    周志华 2016 机器学习 (北京: 清华大学出版社) 第206页

    Zhou Z H 2016 Machine Learning (Beijing: Tsinghua University Press) p206 (in Chinese)

    [23]

    李航 2012 统计机器学习 (北京: 清华大学出版社) 第162页

    Li H 2012The Elements of Statistical Learning (Beijing: Tsinghua University Press) p162 (in Chinese)

    [24]

    徐启伟, 王佩佩, 曾镇佳, 黄泽斌, 周新星, 刘俊敏, 李瑛, 陈书青, 范滇元 2020 物理学报 69 014209Google Scholar

    Xu Q W, Wang P P, Zeng Z J, Huang Z B, Zhou X X, Liu J M, Li Y, Chen S Q, Fan D Y 2020 Acta Phys. Sin. 69 014209Google Scholar

    [25]

    伊恩·古德费洛, 约书亚·本吉奥, 亚伦·库维尔 著 (赵申剑, 黎彧君, 符天凡, 李凯 译) 2017 深度学习 (北京:人民邮电出版社) 第143—317页

    Goodfellow L, Bengio Y, Courville A(translated by Zhang SJ, Li Y J, Fu T F, Li K)2017 Deep Learning (Beijing: The People's Posts and Telecommunications Press) pp143–317 (in Chinese)

  • [1] 张嘉晖. 蛋白质计算中的机器学习. 物理学报, 2024, 73(6): 069301. doi: 10.7498/aps.73.20231618
    [2] 欧阳鑫健, 张岩星, 王之龙, 张锋, 陈韦嘉, 庄园, 揭晓, 刘来君, 王大威. 面向铁电相变的机器学习: 基于图卷积神经网络的分子动力学模拟. 物理学报, 2024, 73(8): 086301. doi: 10.7498/aps.73.20240156
    [3] 刘烨, 牛赫然, 李兵兵, 马欣华, 崔树旺. 机器学习在宇宙线粒子鉴别中的应用. 物理学报, 2023, 72(14): 140202. doi: 10.7498/aps.72.20230334
    [4] 管星悦, 黄恒焱, 彭华祺, 刘彦航, 李文飞, 王炜. 生物分子模拟中的机器学习方法. 物理学报, 2023, 72(24): 248708. doi: 10.7498/aps.72.20231624
    [5] 罗启睿, 沈一凡, 罗孟波. 高分子塌缩相变和临界吸附相变的计算机模拟和机器学习. 物理学报, 2023, 72(24): 240502. doi: 10.7498/aps.72.20231058
    [6] 张逸凡, 任卫, 王伟丽, 丁书剑, 李楠, 常亮, 周倩. 机器学习结合固溶强化模型预测高熵合金硬度. 物理学报, 2023, 72(18): 180701. doi: 10.7498/aps.72.20230646
    [7] 郭唯琛, 艾保全, 贺亮. 机器学习回归不确定性揭示自驱动活性粒子的群集相变. 物理学报, 2023, 72(20): 200701. doi: 10.7498/aps.72.20230896
    [8] 田城, 蓝剑雄, 王苍龙, 翟鹏飞, 刘杰. BaF 2高压相变行为的第一性原理研究. 物理学报, 2022, 71(1): 017102. doi: 10.7498/aps.71.20211163
    [9] 陈江芷, 杨晨温, 任捷. 基于波动与扩散物理系统的机器学习. 物理学报, 2021, 70(14): 144204. doi: 10.7498/aps.70.20210879
    [10] 田城, 蓝剑雄, 王苍龙, 翟鹏飞, 刘杰. BaF2高压相变行为的第一性原理研究. 物理学报, 2021, (): . doi: 10.7498/aps.70.20211163
    [11] 刘武, 朱成皖, 李昊天, 赵谡玲, 乔泊, 徐征, 宋丹丹. 基于机器学习和器件模拟对Cu(In,Ga)Se2电池中Ga含量梯度的优化分析. 物理学报, 2021, 70(23): 238802. doi: 10.7498/aps.70.20211234
    [12] 张瑶, 张云波, 陈立. 基于深度学习的光学表面杂质检测. 物理学报, 2021, 70(16): 168702. doi: 10.7498/aps.70.20210403
    [13] 孙立望, 李洪, 汪鹏君, 高和蓓, 罗孟波. 利用神经网络识别高分子链在表面的吸附相变. 物理学报, 2019, 68(20): 200701. doi: 10.7498/aps.68.20190643
    [14] 曲艳东, 孔祥清, 李晓杰, 闫鸿浩. 热处理对爆轰合成的纳米TiO2混晶的结构相变的影响. 物理学报, 2014, 63(3): 037301. doi: 10.7498/aps.63.037301
    [15] 刘志强, 常胜江, 王晓雷, 范飞, 李伟. 基于VO2薄膜相变原理的温控太赫兹超材料调制器. 物理学报, 2013, 62(13): 130702. doi: 10.7498/aps.62.130702
    [16] 李炎, 唐刚, 宋丽建, 寻之朋, 夏辉, 郝大鹏. Erds Rnyi随机网络上爆炸渗流模型相变性质的数值模拟研究. 物理学报, 2013, 62(4): 046401. doi: 10.7498/aps.62.046401
    [17] 韩秀琴, 姜虹, 石玉仁, 刘妍秀, 孙建华, 陈建敏, 段文山. 一维 Frenkel-Kontorova(FK)模型原子链的相变研究. 物理学报, 2011, 60(11): 116801. doi: 10.7498/aps.60.116801
    [18] 樊华, 李理, 袁坚, 山秀明. 互联网流量控制的朗之万模型及相变分析. 物理学报, 2009, 58(11): 7507-7513. doi: 10.7498/aps.58.7507
    [19] 袁坚, 任勇, 刘锋, 山秀明. 复杂计算机网络中的相变和整体关联行为. 物理学报, 2001, 50(7): 1221-1225. doi: 10.7498/aps.50.1221
    [20] 神经网络的自适应删剪学习算法及其应用. 物理学报, 2001, 50(4): 674-681. doi: 10.7498/aps.50.674
计量
  • 文章访问数:  3061
  • PDF下载量:  90
  • 被引次数: 0
出版历程
  • 收稿日期:  2021-04-14
  • 修回日期:  2021-06-27
  • 上网日期:  2021-09-09
  • 刊出日期:  2021-12-05

/

返回文章
返回