常年招收博士/硕士研究生、实习生（包含本科生）、助理研究员、博士后研究员

要求：1. 对科研工作富有热情、感兴趣，2. 勤奋务实、 态度积极，3. 有扎实的数学、力学功底

多尺度计算力学，物理启发人工智能
机器学习知识嵌入与知识发现

2011-09--2014-02   哥伦比亚大学   哲学硕士
2011-09--2015-08   哥伦比亚大学   哲学博士
2010-09--2011-08   哥伦比亚大学   理学硕士
2006-09--2010-06   河海大学   工学学士

2022-03~现在，中国科学院大学，副教授、博导
2018-01~2022-01，东北大学（美国）， 终身序列助理教授、博导
2015-11~2017-08，麻省理工学院，博士后研究员

   

（1） 国家自然科学基金委优秀青年基金（海外）, 国家级, 2022
（2） NSF Travel Award for Junior Faculty, 其他, 2018
（3） Best Poster Award, 其他, 2015

   

[1] Sun, Fangzheng, Liu, Yang, Wang, JianXun, Sun, Hao. Symbolic Physics Learner: Discovering governing equations via Monte Carlo tree search. The Eleventh International Conference on Learning Representations (ICLR-2023)null. 2023, [2] Sun, Fangzheng, Liu, Yang, Wang, Qi, Sun, Hao. PiSL: Physics-informed Spline Learning for data-driven identification of nonlinear dynamical systems. MECHANICAL SYSTEMS AND SIGNAL PROCESSING[J]. 2023, 191:110165: http://dx.doi.org/10.1016/j.ymssp.2023.110165.
[3] Peijie Zhang, Pu Ren, Yang Liu, Hao Sun. Autoregressive matrix factorization for imputation and forecasting of spatiotemporal structural monitoring time series. MECHANICAL SYSTEMS AND SIGNAL PROCESSING[J]. 2022, 169: 108718:1-108718:14, [4] Rao, Chengping, Ren, Pu, Liu, Yang, Sun, Hao. Discovering Nonlinear PDEs from Scarce Data with Physics-encoded Learning. THE TENTH INTERNATIONAL CONFERENCE ON LEARNING REPRESENTATIONS (ICLR-22)null. 2022, https://openreview.net/forum?id=Vog_3GXsgmb.
[5] Zhao Chen, Yang Liu, Hao Sun. Forecasting of nonlinear dynamics based on symbolic invariance. Computer Physics Communications[J]. 2022, 277: 108382:1-108382:16, https://www.sciencedirect.com/science/article/pii/S0010465522001011.
[6] Pu Ren, Chengping Rao, Yang Liu, JianXun Wang, Hao Sun. PhyCRNet: Physics-informed convolutional-recurrent network for solving spatiotemporal PDEs. COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING[J]. 2022, 389: 114399:1-114399:21, https://www.sciencedirect.com/science/article/pii/S0045782521006514.
[7] Zhao Chen, Yang Liu, Hao Sun. Symbolic deep learning for structural system identification. Journal of Structural Engineering-ASCE[J]. 2022, [8] Lele Luan, Yang Liu, Hao Sun. Distilling governing laws and source input for dynamical systems from videos. The 31st International Joint Conference on Artificial Intelligence (IJCAI-2022)null. 2022, [9] Rao, Chengping, Sun, Hao, Liu, Yang. Physics informed deep learning for computational elastodynamics without labeled data. JOURNAL OF ENGINEERING MECHANICS-ASCE[J]. 2021, 147(8): 04021043:1-04021043:19, http://arxiv.org/abs/2006.08472.
[10] Rao, Chengping, Sun, Hao, Liu, Yang. Hard Encoding of Physics for Learning Spatiotemporal Dynamics. International Conference on Learning Representations (ICLR) Workshop on Deep Learning for Simulationnull. 2021, http://arxiv.org/abs/2105.00557.
[11] Chen, Zhao, Liu, Yang, Sun, Hao. Physics-informed learning of governing equations from scarce data. NATURE COMMUNICATIONS[J]. 2021, 12(1): 6316:1-6316:13, https://www.nature.com/articles/s41467-021-26434-1.
[12] Fangzheng Sun, Yang Liu, Hao Sun. Physics-informed Spline Learning for Nonlinear Dynamics Discovery. The 30th International Joint Conference on Artificial Intelligence (IJCAI-21)null. 2021, https://www.ijcai.org/proceedings/2021/283.
[13] Zhang, Ruiyang, Liu, Yang, Sun, Hao. Physics-guided convolutional neural network (PhyCNN) for data-driven seismic response modeling. ENGINEERING STRUCTURES[J]. 2020, 215: 110704:1-110704:13, http://dx.doi.org/10.1016/j.engstruct.2020.110704.
[14] Zhang, Ruiyang, Liu, Yang, Sun, Hao. Physics-informed multi-LSTM networks for metamodeling of nonlinear structures. COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING[J]. 2020, 369: 113226:1-113226:16, http://dx.doi.org/10.1016/j.cma.2020.113226.
[15] Rao, Chengping, Sun, Hao, Liu, Yang. Physics-informed deep learning for incompressible laminar flows. THEORETICAL AND APPLIED MECHANICS LETTERS[J]. 2020, 10(3): 207-212, http://lib.cqvip.com/Qikan/Article/Detail?id=7101994175.
[16] Rao, Chengping, Liu, Yang. Three-dimensional convolutional neural network (3D-CNN) for heterogeneous material homogenization. COMPUTATIONAL MATERIALS SCIENCE[J]. 2020, 184: 109850:1-109850:12, http://dx.doi.org/10.1016/j.commatsci.2020.109850.
[17] Meng, QingXiang, Lv, Dandan, Liu, Yang. Mesoscale computational modeling of concrete-like particle-reinforced composites with non-convex aggregates. COMPUTERS & STRUCTURES[J]. 2020, 240: http://dx.doi.org/10.1016/j.compstruc.2020.106349.
[18] Jiang, Yanhui, Liu, Yang. Effect of Dielectric Imperfections on the Electroactive Deformations of Polar Dielectric Elastomers. JOURNAL OF APPLIED MECHANICS-TRANSACTIONS OF THE ASME[J]. 2019, 86(8): 081007:1-081007:7, 

   

（ 1 ） 中央高校基本科研业务费专项资金资助项目：物理嵌入深度学习理论与方法, 负责人, 中国科学院计划, 2022-05--2023-12