“We achieved in a few weeksand at a small fraction of thecost what would otherwise havetaken a decade and well over amillion dollars using traditionalinspection approaches.”
Esbern Hansen, P.Eng., Shell Canada
Esbern Hansen, P.Eng., Shell Canada
.svg)
.png)
Watercourse hazard has traditionally been assessed through site visits.But it’s only about 4% of sites that represent more than 90% ofwatercourse hazard exposure.Our probabilistic machine learning techniques quantify uncertainty inpredictions and allow screening conservatism to align with organizationalrisk tolerance. The model integrates a wide range of inputs, including:
Cambio Water Crossing PoF applies supervised machine learningmodels trained on over 33,000 field inspections across ~20,000watercourse crossings across North America.
Prioritize crossings for inspection within large inventories
Screen uninspected, remote, or data-limited crossings
Identify high-risk crossings before field deployment
Standardize screening across regions and operating units
Optimize inspection frequency and budget allocation
Adjust screening conservatism based on organizational risk tolerance
Support risk-based integrity planning for water crossings
Track prioritized crossings in Cambio for ongoing monitoring
.png)