Built and implemented anomaly detection and effective resource allocation for field operations for an oil and gas company.


The client was an upstream gas producer with 500+ wells in remote areas with minimal or no operators present on ground – and had implemented sensors to monitor performance.

  1. Alert Fatigue: The existing reporting system generated thousands of alerts every month, leading to alarm fatigue. Most of the alerts were non-actionable.

  2. Identification Delay: Failures were identified only after the well had shut down leading to significant production loss.


  1. Tested multiple algorithms like SVM, rNN, NN, Time Series ARIMA models, etc and made a choice of final algorithms based on data availability and model quality
  2. Created 150+ features including trend dimensions, rate of change, second order effects and derivatives
  3. Created algorithms which mimic the production engineers process of identifying anomalies based on SCADA data
  4. Integrated with client alarm system through microservices based architecture


  1. Final models built after iterative tests had more than 90% of accuracy, with a median lead time of 90 minutes, with 10% of the cases having lead time in excess of 12 hours 
  2. Classified 63% of events with three major heuristics
  3. Identified anomalies and patterns for optimization, reduced false alarms, improved accuracy of identifying shutdowns and reduced time gap between bad events