Seismic Bumps: Coal Mine Seismic Hazard Data for Predictive Modeling

A tabular dataset curated for evaluating predictive machine learning models on independent and identically distributed data. The intended task is binary classification, likely predicting seismic hazard events in coal mines. The data originates from a 2010 academic study analyzing seismic hazard monitoring systems.

Use Cases

• Benchmarking binary classification algorithms based on the described predictive task.
• Developing models for seismic hazard prediction in mining based on the dataset's focus.
• Studying feature engineering for geophysical monitoring data based on the domain.
• Comparing model performance on curated, IID tabular data based on the curation purpose.

Strengths

• Dataset has a clear, peer-reviewed original source with a citation provided.
• Curation included preprocessing steps such as dropping constant columns and renaming the target feature.
• Released under a permissive CC BY 4.0 license.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count, sample data, and file formats are unknown, which limits suitability assessment.
• Last update date is unknown; freshness unverified.

Provenance

Source

Sikora, Marek, and Łukasz Wrobel. 'Application of rule induction algorithms for analysis of data collected by seismic hazard monitoring systems in coal mines.' Archives of Mining Sciences 55.1 (2010): 91-114.

Collection Method

Data collected by seismic hazard monitoring systems in coal mines, as per the reference.

Time Range

Dataset Year is 2013; temporal coverage of original data is not specified.

Freshness

Dataset Year is 2013; last updated date is unknown.

Geography

Likely related to coal mines, but specific geographic coverage is not stated.