🛢️ US Well Pad Dataset

Manually digitized oil and gas well pad polygons across the United States, traced from high-resolution satellite imagery using QGIS.

---

About

This dataset contains manually digitized well pad polygons across major oil and gas producing regions in the United States. Each polygon represents the outer boundary of a cleared, graveled well pad surface as visible in satellite imagery. It only covers well pads that are involved with hydraulic fracturing based on FracFocus registry.

The dataset is intended to support:

• AI/ML object detection and segmentation model training
• Land use changes detection
• EGS geothermal research

---

Sample Annotation

Example of manually digitized well pad polygons over Google Satellite imagery — Near Canton Basin, OH

---

Coverage

State	Basin	Status
Texas	Permian Basin	NA
Texas	Eagle Ford	NA
North Dakota	Bakken	NA
Pennsylvania	Marcellus Shale	NA
West Virginia	Marcellus / Utica	NA

Coverage expands with each release. See CHANGELOG.md for version history.

---

Dataset Structure

well-pad-dataset/
├── data/
├── images/
│   └── example_image.png
├── scripts/
├── README.md
├── LICENSE
└── CITATION.cff

---

Attribute Fields

Field	Type	Description
id	Integer	Unique polygon identifier
well_api_numbers	Text	Well API numbers seperated by comma
basin	Text	Oil/gas basin name (e.g., Permian, Bakken)
area_m2	Real	Well pad area in square meters
well_tanks	Integer	Number of tanks in the well pad

---

Dataset Statistics

• coming soon

Statistics updated with each version release.

---

Download

git clone https://github.com/sidrcs/well-pad-dataset.git

Or download directly:

• us_well_pads_epsg5070.gpkg — GPKG (recommended)

---

Methodology

• Tool: QGIS with QuickMapServices plugin
• Basemaps: Google Satellite, ESRI World Imagery, Bing Aerial
• Digitizing: Manual polygon tracing at 1:2,000–1:5,000 scale
• Reference data: FracFocus, state oil & gas commission well databases, SkyTruth
• CRS: EPSG:5070 (Albers Equal Area)
• Tracing convention: Outer boundary of the cleared/graveled pad surface

---

License

This dataset is released under the Creative Commons Attribution 4.0 International (CC BY 4.0) license.

You are free to use, share, and adapt this dataset for any purpose, including commercial use, as long as you give appropriate credit.

See LICENSE for full terms.

---

Citation

If you use this dataset in your research or project, please cite:

@dataset{ramavajjala2026wellpad,
  author    = {Ramavajjala, Chinna Subbaraya Siddharth},
  title     = {US Well Pad Dataset: Manually Digitized Oil and Gas Well Pad Polygons},
  year      = {2026},
  publisher = {GitHub},
  url       = {https://github.com/sidrcs/well-pad-dataset},
  license   = {CC BY 4.0}
}

---

Author

Chinna Subbaraya Siddharth Ramavajjala

• GitHub: @sidrcs

---

Contributing

Contributions welcome! If you'd like to:

• Add polygons for a new region
• Fix a mislabeled polygon
• Improve the scripts

Please open an issue or submit a pull request.

---

Known Limitations

• Imagery dates vary by region — some pads may have been constructed or reclaimed since annotation
• Visual ambiguity between well pads and similar cleared surfaces (gravel pits, staging areas) may result in occasional false positives
• Coverage is not exhaustive — this is a growing dataset