A 1.9 GB collection includes the thermodynamic input file for HeFESTo, machine learning training data for a thermodynamic surrogate, and performance comparison code. The dataset, authored by Qian Yuan and last updated in April 2026, contains files for KNN, neural network, and decision tree methods.
Use Cases
- Training surrogate thermodynamic models based on the provided KNN, neural network, and decision tree data.
- Comparing the performance of different machine learning methods for thermodynamic prediction.
- Reproducing or extending the analysis and figures from the associated research or project.
Strengths
- Dataset size is 1.9 GB, indicating substantial content.
- Includes both raw input data and processed training data for multiple ML methods.
- Released under the permissive CC-BY-4.0 license.
Limitations
- Column-level documentation is absent; field semantics must be inferred after download.
- Row count is unknown, which may limit suitability assessment.
- Description metadata is limited; actual data quality requires manual inspection after download.
Provenance
- Source
- figshare
- Collection Method
- Likely generated as part of research or development work on the HeFESTo thermodynamic model.
- Time Range
- null
- Freshness
- Last updated 2026-04-21 19:01:03; freshness should be verified.
- Geography
- null