ARXIV:2604.04829 · DYNAMICAL SYSTEM IDENTIFICATION · SUBMITTED 07 APR · 20:14 UTC · FRESHNESS UNKNOWN

VerifiedSource: PDF linkedVerifiedPaperPack: citation fields availablePartialProof: unverified proof status

A Robust SINDy Autoencoder for Noisy Dynamical System Identification

Kairui Ding · arXiv

A robust SINDy autoencoder for identifying noisy dynamical systems by incorporating a noise-separation module.

Blocked on Code›Score3.0Evidence unverified

Opportunity summary

Pain A robust SINDy autoencoder for identifying noisy dynamical systems by incorporating a noise-separation module.

Evidence 0 refs | 0 sources | 0% coverage

Blocker Evidence unverified

Open Build Read PDF Signal Canvas Track

PROBLEM

A robust SINDy autoencoder for identifying noisy dynamical systems by incorporating a noise-separation module. It uses sparse regression techniques to identify parsimonious models of unknown systems from a library of candidate functions.

METHOD

Full abstract

Sparse identification of nonlinear dynamics (SINDy) has been widely used to discover the governing equations of a dynamical system from data. It uses sparse regression techniques to identify parsimonious models of unknown systems from a library of candidate functions. Therefore, it relies on the assumption that the dynamics are sparsely represented in the coordinate system used. To address this limitation, one seeks a coordinate transformation that provides reduced coordinates capable of reconstructing the original system. Recently, SINDy autoencoders have extended this idea by combining sparse model discovery with autoencoder architectures to learn simplified latent coordinates together with parsimonious governing equations. A central challenge in this framework is robustness to measurement error. Inspired by noise-separating neural network structures, we incorporate a noise-separation module into the SINDy autoencoder architecture, thereby improving robustness and enabling more reliable identification of noisy dynamical systems. Numerical experiments on the Lorenz system show that the proposed method recovers interpretable latent dynamics and accurately estimates the measurement noise from noisy observations.

RESULT

ScienceToStartup currently rates this 3.0/10 on the public viability pass. Numerical experiments on the Lorenz system show that the proposed method recovers interpretable latent dynamics and accurately estimates the measurement noise from noisy observations.

WHY NOW

Dynamical System Identification moved forward this cycle; last verified April 2026. Public score 3.0/10.

Continue into Read for claims, analysis, references, and neighboring papers.

Opportunity summary

Score3.0

PainA robust SINDy autoencoder for identifying noisy dynamical systems by incorporating a noise-separation module.

Evidence0 refs | 0 sources | 0% coverage

Blockerno shell-level blocker reported

Analysis summary

A robust SINDy autoencoder for identifying noisy dynamical systems by incorporating a noise-separation module.

VerifiedSource: PDF linkedVerifiedPaperPack: citation fields availablePartialProof: unverified proof status

Competitive landscape

A robust SINDy autoencoder for identifying noisy dynamical systems by incorporating a noise-separation module.

Segment

Dynamical System Identification

Adoption evidence

No public code link in the paper record yet

Commercial read

3.0/10 public viability

Direct

not classified

Adjacent

not classified

Substitute

not classified

Unknown

not classified

{ "contract_version": "paper-r2", "paper_id": "4a80fb93-e5ed-44f4-b808-5547f9a43710", "arxiv_id": "2604.04829", "canonical_route": "/paper/a-robust-sindy-autoencoder-for-noisy-dynamical-system-identification", "active_tab": "synced from current hash by the drawer client", "selected_artifact": "a-robust-sindy-autoencoder-for-noisy-dynamical-system-identification", "endpoints": { "paper_pack": "/api/v1/paper/a-robust-sindy-autoencoder-for-noisy-dynamical-system-identification/paper-pack", "build_passport": "/api/v1/paper/a-robust-sindy-autoencoder-for-noisy-dynamical-system-identification/build-passport", "mcp_resource": "sciencetostartup://surfaces/paper-workspace" } }

{ "surface": "paper", "mode": "paper", "query": "A Robust SINDy Autoencoder for Noisy Dynamical System Identification", "normalized_query": "2604.04829", "route": "/paper/a-robust-sindy-autoencoder-for-noisy-dynamical-system-identification", "paper_ref": "a-robust-sindy-autoencoder-for-noisy-dynamical-system-identification", "topic_slug": null, "benchmark_ref": null, "dataset_ref": null }

{ "@context": "https://schema.org", "@graph": [ { "@type": "WebPage", "@id": "https://sciencetostartup.com/paper/a-robust-sindy-autoencoder-for-noisy-dynamical-system-identification#webpage", "url": "https://sciencetostartup.com/paper/a-robust-sindy-autoencoder-for-noisy-dynamical-system-identification", "name": "A Robust SINDy Autoencoder for Noisy Dynamical System Identification", "description": "A robust SINDy autoencoder for identifying noisy dynamical systems by incorporating a noise-separation module.", "isPartOf": { "@id": "https://sciencetostartup.com/#website" } }, { "@type": "ScholarlyArticle", "@id": "https://sciencetostartup.com/paper/a-robust-sindy-autoencoder-for-noisy-dynamical-system-identification#scholarlyArticle", "headline": "A Robust SINDy Autoencoder for Noisy Dynamical System Identification", "description": "A robust SINDy autoencoder for identifying noisy dynamical systems by incorporating a noise-separation module.", "url": "https://sciencetostartup.com/paper/a-robust-sindy-autoencoder-for-noisy-dynamical-system-identification", "sameAs": "https://arxiv.org/abs/2604.04829", "identifier": { "@type": "PropertyValue", "propertyID": "arXiv", "value": "2604.04829" }, "isAccessibleForFree": true, "isPartOf": { "@id": "https://sciencetostartup.com/#website" }, "datePublished": "2026-04-06T16:30:24.000Z", "author": [ { "@type": "Person", "name": "Kairui Ding" } ], "additionalProperty": [ { "@type": "PropertyValue", "propertyID": "viabilityScore", "value": 3 }, { "@type": "PropertyValue", "propertyID": "researchDomain", "value": "Dynamical System Identification" } ] }, { "@type": "BreadcrumbList", "itemListElement": [ { "@type": "ListItem", "position": 1, "name": "Home", "item": "https://sciencetostartup.com" }, { "@type": "ListItem", "position": 2, "name": "Dynamical System Identification", "item": "https://sciencetostartup.com/topics" }, { "@type": "ListItem", "position": 3, "name": "A Robust SINDy Autoencoder for Noisy Dynamical System Identi", "item": "https://sciencetostartup.com/paper/a-robust-sindy-autoencoder-for-noisy-dynamical-system-identification" } ] } ] }

Competitive landscape

A robust SINDy autoencoder for identifying noisy dynamical systems by incorporating a noise-separation module.

Segment

Dynamical System Identification

Adoption evidence

No public code link in the paper record yet

Commercial read

3.0/10 public viability

Direct

not classified

Adjacent

not classified

Substitute

not classified

Unknown

not classified

A Robust SINDy Autoencoder for Noisy Dynamical System Identification

A Robust SINDy Autoencoder for Noisy Dynamical System Identification

Claim map

Constellation map

Competitive landscape

Buzz

PDF

REFERENCES

Related Papers

Subscribe to the weekly brief

Build artifacts

Brief

Experiment plan

Validation checklist

Scientific founder

Translational engineer

Domain operator

GTM lead

Regulatory/clinical advisor

Timeline

Claim map

Constellation map

Competitive landscape

Buzz

PDF

REFERENCES

Related Papers

Subscribe to the weekly brief

Build artifacts

Brief

Experiment plan

Validation checklist

Scientific founder

Translational engineer

Domain operator

GTM lead

Regulatory/clinical advisor

Timeline