Well-definedness of Physical Law Learning: The Uniqueness Problem
- URL: http://arxiv.org/abs/2210.08342v2
- Date: Wed, 19 Oct 2022 16:33:21 GMT
- Title: Well-definedness of Physical Law Learning: The Uniqueness Problem
- Authors: Philipp Scholl, Aras Bacho, Holger Boche, Gitta Kutyniok
- Abstract summary: Physical law learning is the ambiguous attempt at automating the derivation of governing equations with the use of machine learning techniques.
This paper shall serve as a first step to build a comprehensive theoretical framework for learning physical laws.
- Score: 63.9246169579248
- License: http://creativecommons.org/licenses/by-sa/4.0/
- Abstract: Physical law learning is the ambiguous attempt at automating the derivation
of governing equations with the use of machine learning techniques. The current
literature focuses however solely on the development of methods to achieve this
goal, and a theoretical foundation is at present missing. This paper shall thus
serve as a first step to build a comprehensive theoretical framework for
learning physical laws, aiming to provide reliability to according algorithms.
One key problem consists in the fact that the governing equations might not be
uniquely determined by the given data. We will study this problem in the common
situation of having a physical law be described by an ordinary or partial
differential equation. For various different classes of differential equations,
we provide both necessary and sufficient conditions for a function from a given
function class to uniquely determine the differential equation which is
governing the phenomenon. We then use our results to devise numerical
algorithms to determine whether a function solves a differential equation
uniquely. Finally, we provide extensive numerical experiments showing that our
algorithms in combination with common approaches for learning physical laws
indeed allow to guarantee that a unique governing differential equation is
learnt, without assuming any knowledge about the function, thereby ensuring
reliability.
Related papers
- Towards true discovery of the differential equations [57.089645396998506]
Differential equation discovery is a machine learning subfield used to develop interpretable models.
This paper explores the prerequisites and tools for independent equation discovery without expert input.
arXiv Detail & Related papers (2023-08-09T12:03:12Z) - Comparison of Single- and Multi- Objective Optimization Quality for
Evolutionary Equation Discovery [77.34726150561087]
Evolutionary differential equation discovery proved to be a tool to obtain equations with less a priori assumptions.
The proposed comparison approach is shown on classical model examples -- Burgers equation, wave equation, and Korteweg - de Vries equation.
arXiv Detail & Related papers (2023-06-29T15:37:19Z) - Solving differential equations using physics informed deep learning: a
hand-on tutorial with benchmark tests [0.0]
We revisit the original approach of using deep learning and neural networks to solve differential equations.
We focus on the possibility to use the least possible amount of data into the training process.
A tutorial on a simple equation model illustrates how to put into practice the method for ordinary differential equations.
arXiv Detail & Related papers (2023-02-23T16:08:39Z) - Discovering ordinary differential equations that govern time-series [65.07437364102931]
We propose a transformer-based sequence-to-sequence model that recovers scalar autonomous ordinary differential equations (ODEs) in symbolic form from time-series data of a single observed solution of the ODE.
Our method is efficiently scalable: after one-time pretraining on a large set of ODEs, we can infer the governing laws of a new observed solution in a few forward passes of the model.
arXiv Detail & Related papers (2022-11-05T07:07:58Z) - Physics Informed RNN-DCT Networks for Time-Dependent Partial
Differential Equations [62.81701992551728]
We present a physics-informed framework for solving time-dependent partial differential equations.
Our model utilizes discrete cosine transforms to encode spatial and recurrent neural networks.
We show experimental results on the Taylor-Green vortex solution to the Navier-Stokes equations.
arXiv Detail & Related papers (2022-02-24T20:46:52Z) - A Probabilistic State Space Model for Joint Inference from Differential
Equations and Data [23.449725313605835]
We show a new class of solvers for ordinary differential equations (ODEs) that phrase the solution process directly in terms of Bayesian filtering.
It then becomes possible to perform approximate Bayesian inference on the latent force as well as the ODE solution in a single, linear complexity pass of an extended Kalman filter.
We demonstrate the expressiveness and performance of the algorithm by training a non-parametric SIRD model on data from the COVID-19 outbreak.
arXiv Detail & Related papers (2021-03-18T10:36:09Z) - Computational characteristics of feedforward neural networks for solving
a stiff differential equation [0.0]
We study the solution of a simple but fundamental stiff ordinary differential equation modelling a damped system.
We show that it is possible to identify preferable choices to be made for parameters and methods.
Overall we extend the current literature in the field by showing what can be done in order to obtain reliable and accurate results by the neural network approach.
arXiv Detail & Related papers (2020-12-03T12:22:24Z) - The data-driven physical-based equations discovery using evolutionary
approach [77.34726150561087]
We describe the algorithm for the mathematical equations discovery from the given observations data.
The algorithm combines genetic programming with the sparse regression.
It could be used for governing analytical equation discovery as well as for partial differential equations (PDE) discovery.
arXiv Detail & Related papers (2020-04-03T17:21:57Z) - Learning To Solve Differential Equations Across Initial Conditions [12.66964917876272]
A number of neural network-based partial differential equation solvers have been formulated which provide performances equivalent, and in some cases even superior, to classical solvers.
In this work, we posit the problem of approximating the solution of a fixed partial differential equation for any arbitrary initial conditions as learning a conditional probability distribution.
arXiv Detail & Related papers (2020-03-26T21:29:22Z) - Physics Informed Deep Learning for Transport in Porous Media. Buckley
Leverett Problem [0.0]
We present a new hybrid physics-based machine-learning approach to reservoir modeling.
The methodology relies on a series of deep adversarial neural network architecture with physics-based regularization.
The proposed methodology is a simple and elegant way to instill physical knowledge to machine-learning algorithms.
arXiv Detail & Related papers (2020-01-15T08:20:11Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.