Clasificación Automatizada de Facies
Labels rock type from well logs across hundreds of wells consistently, which a team of interpreters working separately cannot do.
Measures porosity, grain size and fracture density from core photographs and CT scans instead of from a description written twenty years ago.
Core is the most expensive data an operator owns and the least used. Boxes are photographed once, described qualitatively, and then stored; the quantitative information in the images is never extracted.
Segmentation models run over core photographs, CT slices and thin-section images to quantify pore geometry, grain-size distribution and fracture intensity. Results are depth-registered against the log suite so they can be used as calibration points rather than sitting in a separate report.
Image-derived porosity is a two-dimensional estimate and systematically disagrees with helium porosity by a few porosity units; we report the offset rather than hiding it. Legacy core photographs without a colour reference or a consistent scale bar cannot be calibrated at all, and in most archives that is the majority of the older boxes.
Cada página de capacidad declara una limitación real. Si un proveedor no puede decirle dónde termina su producto, no le están diciendo la verdad sobre dónde empieza.
Labels rock type from well logs across hundreds of wells consistently, which a team of interpreters working separately cannot do.
Works out what each document is and which well, field and date it belongs to, so the archive becomes navigable rather than a folder tree.
Decides which wells will produce sand and sizes the gravel and screen for the ones that will.
Understands log images, maps and cross-sections alongside text, so you can ask a question about a figure rather than only about a paragraph.
Produces P10, P50 and P90 production forecasts whose spread is calculated, not chosen to look reasonable.