Shaleforce

This dataset provides users with access to comprehensive and granular oil and gas production - along with flaring and geothermal data linked to the well identification number established by the American Petroleum Institute. It empowers rapid exploratory screening and ML model training to rank new drilling locations and or appraise the potential of repurpose existing assets for geothermal and sustainable energy development. The dataset includes: Well level features on over 857,808 wells (and growing by the month) in Texas, New Mexico and Colorado, completion and producing operator names, activity dates, depths.

Database covers both vertical and unconventional wells. Well-level production allocation. Texas oil production history is reported at the lease level, and many leases have multiple wells (anywhere from 2 to over 2,000).

AutoML is deployed to perform lease-based production allocation to individual wells upfront. Cumulative production information and 53 features - including initial 90-day flow rate, first year production, flared volume, flaring intensity, bottomhole temperature, pressure and geothermal gradient (where available) per well identification number. Location information including surface Latitude and Longitude coordinates, wellbore Section and Abstract.

These features facilitate numeric encoding and or categorical feature engineering. Coverage on daily completion and monthly production data of Colorado, New Mexico and Texas, including Eagle Ford and Permian. The free trial sample, a subset of the paid dataset, provides access to wells that were completed in the first half of 2010.