# From Data to Laws: Neural Discovery of Conservation Laws Without False Positives

Source: [From Data to Laws: Neural Discovery of Conservation Laws Without False Positives](<https://www.sota2.com/research/paper/69c21a8f0636e5bf4afc48b6>)

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

Data updated: 2026-03-25T05:00:04.214Z

Authors: Rahul D Ray

Published: 2026-03-20T20:06:34.000Z

## Abstract

Conservation laws are fundamental to understanding dynamical systems, but discovering them from data remains challenging due to parameter variation, non-polynomial invariants, local minima, and false positives on chaotic systems. We introduce NGCG, a neural-symbolic pipeline that decouples dynamics learning from invariant discovery and systematically addresses these challenges. A multi-restart variance minimiser learns a near-constant latent representation; system-specific symbolic extraction (polynomial Lasso, log-basis Lasso, explicit PDE candidates, and PySR) yields closed-form expressions; a strict constancy gate and diversity filter eliminate spurious laws. On a benchmark of nine diverse systems including Hamiltonian and dissipative ODEs, chaos, and PDEs, NGCG achieves consistent discovery (DR=1.0, FDR=0.0, F1=1.0) on all four systems with true conservation laws, with constancy two to three orders of magnitude lower than the best baseline. It is the only method that succeeds on the Lotka--Volterra system, and it correctly outputs no law on all five systems without invariants. Extensive experiments demonstrate robustness to noise ($\\sigma = 0.1$), sample efficiency (50--100 trajectories), insensitivity to hyperparameters, and runtime under one minute per system. A Pareto analysis shows that the method provides a range of candidate expressions, allowing users to trade complexity for constancy. NGCG achieves strong performance relative to prior methods for data-driven conservation-law discovery, combining high accuracy with interpretability.

## 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 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: 1.

- [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: 100.

- [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.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2603.20474>)

[PDF](<https://arxiv.org/pdf/2603.20474.pdf>)
