Dynamics-Informed Machine Learning for Recovering Extensive Missing Systems Dynamics

7.0 MB of data from four distinct domains—climate, neuroscience, finance, and transportation—accompanies code for dynamics-informed machine learning. The dataset includes wind speed, sea surface temperature, EEG signals, exchange rates, and road occupancy rates. Authored by Tao Wu and last updated in May 2026, it is shared under a CC-BY-4.0 license.

Use Cases

• Impute missing values in climate time series based on wind speed and sea surface temperature data
• Recover missing segments in neurological signals based on EEG data
• Forecast financial trends based on historical exchange rate data
• Model traffic patterns based on road occupancy rate data

Strengths

• Data spans four distinct scientific and industrial domains, enabling cross-domain methodological testing
• Includes the main code from the associated research work, facilitating reproducibility
• Shared under a permissive CC-BY-4.0 license

Limitations

• Row count is unknown, which may limit suitability assessment
• Column-level documentation is absent; field semantics must be inferred after download

Provenance

Source

Tao Wu via figshare

Freshness

Last updated 2026-05-14 01:40:55