mlsanityData to 7 Oct 2026

Paradigm Shift Through the Integration of Physical Methodology and Data Science

arXiv 2110.01408 ↗First posted 30 Sep 2021physics.data-an cs.LG physics.comp-phcited by 0

Not on the map. Why?

Abstract (arXiv)

Data science methodologies, which have undergone significant developments recently, provide flexible representational performance and fast computational means to address the challenges faced by traditional scientific methodologies while revealing unprecedented challenges such as the interpretability of computations and the demand for extrapolative predictions on the amount of data. Methods that integrate traditional physical and data science methodologies are new methods of mathematical analysis that complement both methodologies and are being studied in various scientific fields. This paper highlights the significance and importance of such integrated methods from the viewpoint of scientific theory. Additionally, a comprehensive survey of specific methods and applications are conducted, and the current state of the art in relevant research fields are summarized.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 22 of its 80 references that are in the map. First posted on arXiv 30 Sep 2021.

Builds on

22 of 80 references.

References · 22

  1. 2018Neural Ordinary Differential Equationscited by 3,733
  2. 2019Hamiltonian Neural Networkscited by 702
  3. 2017AirSim: High-Fidelity Visual and Physical Simulation for Autonomous Vehiclescited by 517
  4. 2018Deep Hidden Physics Models: Deep Learning of Nonlinear Partial Differential Equationscited by 233
  5. 2016Theory-guided Data Science: A New Paradigm for Scientific Discovery from Datacited by 169
  6. 2018Deep learning to represent sub-grid processes in climate modelscited by 156
  7. 2018Learning Equations for Extrapolation and Controlcited by 151
  8. 2014Dynamic mode decomposition with controlcited by 128
  9. 2017Learning Deep Neural Network Representations for Koopman Operators of Nonlinear Dynamical Systemscited by 125
  10. 2019An Energy Approach to the Solution of Partial Differential Equations in Computational Mechanics via Machine Learning: Concepts, Implementation and Applicationscited by 118
  11. 2017DeepSD: Generating High Resolution Climate Change Projections through Single Image Super-Resolutioncited by 80
  12. 2017Data-driven discovery of Koopman eigenfunctions for controlcited by 64
10 more
  1. 2019Small Data Challenges in Big Data Era: A Survey of Recent Progress on Unsupervised and Semi-Supervised Methodscited by 62
  2. 2020Physics-Guided Machine Learning for Scientific Discovery: An Application in Simulating Lake Temperature Profilescited by 59
  3. 2016Towards Bayesian Deep Learning: A Framework and Some Existing Methodscited by 57
  4. 2017Machine Learning for the Geosciences: Challenges and Opportunitiescited by 53
  5. 2018Data-driven discovery of PDEs in complex datasetscited by 42
  6. 2020MeshingNet: A New Mesh Generation Method based on Deep Learningcited by 30
  7. 2019Data-Driven POD-Galerkin Reduced Order Model for Turbulent Flowscited by 21
  8. 2019Deep Variational Koopman Models: Inferring Koopman Observations for Uncertainty-Aware Dynamics Modeling and Controlcited by 18
  9. 2021Machine learning initialization to accelerate Stokes profile inversionscited by 4
  10. 2020Hybrid Scheme of Kinematic Analysis and Lagrangian Koopman Operator Analysis for Short-term Precipitation Forecastingcited by 2

Built on by

Not cited yet.