Data and code for: From Data Chaos to Physically Interpretable Deterministic Mapping

12.6 MB of synthetic benchmark datasets and code accompany the manuscript 'From Data Chaos to Physically Interpretable Deterministic Mapping'. The repository includes data for Burgers', FitzHugh-Nagumo, Navier-Stokes, and CSTR systems, authored by Dongni Jia and last updated in May 2026. Real-world industrial data for a grinding-classification plant are noted as confidential and not included.

Use Cases

• Benchmarking system identification algorithms based on the described synthetic systems (Burgers', FitzHugh-Nagumo, Navier-Stokes, CSTR)
• Reproducing results from the associated manuscript using the provided example datasets
• Developing physically interpretable models for chaotic dynamical systems based on the described methodology

Strengths

• Includes four distinct synthetic benchmark systems (Burgers', FitzHugh-Nagumo, Navier-Stokes, CSTR) for method validation
• Released under a permissive CC-BY-4.0 license, allowing for reuse and modification

Limitations

• Row count is unknown, which may limit suitability assessment
• Column-level documentation is absent; field semantics must be inferred after download
• The primary real-world industrial dataset is confidential and not publicly available

Provenance

Source

Dongni Jia

Collection Method

Synthetic data generation for benchmark systems; source code archived from GitHub release v1.0.

Freshness

Last updated 2026-05-27 21:02:50; freshness should be verified