Pengzhan Jin

Pengzhan Jin

Auto-generated profile, based on publicly available information

Pengzhan Jin

National Engineering Laboratory for Big Data Analysis and Applications, Peking University, Beijing, 100871, China

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

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

Representative Publications

View All Publications
18 March 2021 in Nature Machine Intelligence
Verified
Journal Article
Closed access
PDF file
LLLu Lu
Lu Lu
PJPengzhan Jin
Pengzhan Jin
GPGuofei Pang
Guofei Pang
ZZZhongqiang Zhang
Zhongqiang Zhang
George KarniadakisGeorge Karniadakis
George Karniadakis

18 February 2022 in IEEE Transactions on Neural Networks and Learning Systems
Verified
Journal Article
Closed access
PJPengzhan Jin
Pengzhan Jin
ZZZhen Zhang
Zhen Zhang
IKIoannis G. Kevrekidis
Ioannis G. Kevrekidis
George KarniadakisGeorge Karniadakis
George Karniadakis
We propose the Poisson neural networks (PNNs) to learn Poisson systems and trajectories of autonomous systems from data. Based on the Darboux–Lie theorem, the phase flow of a Poisson system can be written as the composition of: 1) a coordinate transformation; 2) an extended symplectic map; and 3) the inverse of the transformation. In this work, we extend this result to the unknotted trajectories of autonomous systems. We employ structured neural networks with physical priors to approximate the three aforementioned maps. We demonstrate through several simulations that PNNs are capable of handling very accurately several challenging tasks, including the motion of a particle in the electromagnetic potential, the nonlinear Schrödinger equation, and pixel observations of the two-body problem.

9 June 2022 in Linear Algebra and its Applications
Verified
Journal Article
Closed access
PJPengzhan Jin
Pengzhan Jin
ZLZhangli Lin
Zhangli Lin
BXBo Xiao
Bo Xiao

8 January 2026 in Neural Networks
Verified
Journal Article
Closed access
PJPengzhan Jin
Pengzhan Jin

30 April 2026 in SIAM Journal on Numerical Analysis
Verified
Journal Article
Closed access
SXShanshan Xiao
Shanshan Xiao
PJPengzhan Jin
Pengzhan Jin
YTYifa Tang
Yifa Tang
In this work, we establish a deformation-based framework for learning solution mappings of PDEs defined on varying domains. The union of functions defined on varying domains can be identified as a metric space according to the deformation; then the solution mapping is regarded as a continuous metric-to-metric mapping, and subsequently can be represented by another continuous metric-to-Banach mapping using two different strategies, referred to as the D2D subframework and the D2E subframework, respectively. We point out that such a metric-to-Banach mapping can be learned by neural networks, and hence the solution mapping is accordingly learned. With this framework, a rigorous convergence analysis is built for the problem of learning solution mappings of PDEs on varying domains. As the theoretical framework holds based on several pivotal assumptions which need to be verified for a given specific problem, we study the star domains as a typical example, and other situations could be similarly verified. There are four important features of this framework: (1) The domains under consideration are not required to be diffeomorphic, and therefore a wide range of regions can be covered by one model, provided they are homeomorphic. (2) The deformation mapping is unnecessary to be continuous, and thus it can be flexibly established via combining a primary identity mapping and a local deformation mapping. This capability facilitates the resolution of large systems where only local parts of the geometry undergo change. (3) In fact, the recent methods (Geo-FNO, DIMON, etc.) belong to the D2D subframework. We point out that the D2D subframework introduces regularity issues, whereas the proposed D2E subframework remains free from such problems. From a comprehensive perspective, the D2E subframework is better. (4) If a linearity-preserving neural operator such as MIONet is adopted, this framework still preserves the linearity of the surrogate solution mapping on its source term for linear PDEs, and thus it can be applied to the hybrid iterative method. We finally present several numerical experiments to validate our theoretical results.