# Discovering conservation laws from trajectories via machine learning

Source: [Discovering conservation laws from trajectories via machine learning](<https://www.sota2.com/research/paper/68fa3f4e1e209131ce8ec428>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T02:19:28.778Z

Authors: Seungwoong Ha, Hawoong Jeong

Published: 2021-02-08T05:51:21.000Z

## Abstract

Invariants and conservation laws convey critical information about the underlying dynamics of a system, yet it is generally infeasible to find them from large-scale data without any prior knowledge or human insight. We propose ConservNet to achieve this goal, a neural network that spontaneously discovers a conserved quantity from grouped data where the members of each group share invariants, similar to a general experimental setting where trajectories from different trials are observed. As a neural network trained with a novel and intuitive loss function called noise-variance loss, ConservNet learns the hidden invariants in each group of multi-dimensional observables in a data-driven, end-to-end manner. Our model successfully discovers underlying invariants from the simulated systems having invariants as well as a real-world double pendulum trajectory. Since the model is robust to various noises and data conditions compared to baseline, our approach is directly applicable to experimental data for discovering hidden conservation laws and further, general relationships between variables.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Conservation-law discovery on lorenz (test)](<https://www.sota2.com/research/sota/conservation-law-discovery-on-lorenz-test.md>): Conservation-law discovery; lorenz (test); F1 Score: 0.

- [Conservation-law discovery on burgers (test)](<https://www.sota2.com/research/sota/conservation-law-discovery-on-burgers-test.md>): Conservation-law discovery; Burgers' (test); F1: 0.

- [Conservation-law discovery on ks (test)](<https://www.sota2.com/research/sota/conservation-law-discovery-on-ks-test.md>): Conservation-law discovery; KS (test); F1 Score: 0.

- [Conservation-law discovery on double\_pendulum (test)](<https://www.sota2.com/research/sota/conservation-law-discovery-on-double_pendulum-test.md>): Conservation-law discovery; double\_pendulum (test); F1 Score: 0.

- [Conservation-law discovery on three\_body (test)](<https://www.sota2.com/research/sota/conservation-law-discovery-on-three_body-test.md>): Conservation-law discovery; three\_body (test); F1 Score: 0.

- [Conservation-law discovery on lotka\_volterra (test)](<https://www.sota2.com/research/sota/conservation-law-discovery-on-lotka_volterra-test.md>): Conservation-law discovery; lotka\_volterra (test); F1 Score: 0.

- [Conservation-law discovery on mass\_spring (test)](<https://www.sota2.com/research/sota/conservation-law-discovery-on-mass_spring-test.md>): Conservation-law discovery; mass\_spring (test); F1 Score: 100.

- [Conservation-law discovery on henon\_heiles (test)](<https://www.sota2.com/research/sota/conservation-law-discovery-on-henon_heiles-test.md>): Conservation-law discovery; henon\_heiles (test); F1 Score: 0.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2102.04008>)

[PDF](<https://arxiv.org/pdf/2102.04008.pdf>)
