Forecasting the abnormal events at well drilling with machine learning

We present a data-driven and physics-informed algorithm for drilling accident forecasting. The core machine-learning algorithm uses the data from the drilling telemetry representing the time-series. We have developed a Bag-of-features representation of the time series that enables the algorithm to predict the probabilities of six types of drilling accidents in real-time. The machine-learning model is trained on the 125 past drilling accidents from 100 different Russian oil and gas wells. Validation shows that the model can forecast 70% of drilling accidents with a false positive rate equals to 40%. The model addresses partial prevention of the drilling accidents at the well construction.

Automated summary

We present a data-driven and physics-informed algorithm for real-time drilling accident forecasting, which can predict the probabilities of six types of accidents. The model, trained on past drilling accidents, can forecast 70% of the accidents with a false positive rate of 40%, addressing partial prevention of accidents during well construction.