Improving predictive models for rate of penetration in real drilling operations through transfer learning

Abstract

The rate of penetration (ROP) is a key performance indicator in the oil and gas drilling industry as it directly translates to cost savings and emission reductions. A prerequisite for a drilling optimization algorithm is a predictive model that provides expected ROP values in response to surface drilling parameters and formation properties. The high predictive capability of current machine-learning models comes at the cost of excessive data requirements, poor generalization, and extensive computation requirements. These practical issues hinder ROP models for field deployment. Here we address these issues through transfer learning. Simulated and real data from the Volve field were used to pre-train models. Subsequently, these models were fine-tuned with varying retraining data percentages from other Volve wells and Marcellus Shale wells.Four out of the five test cases indicate that retraining the base model would always produce a model with a lower mean absolute error than training an entirely new model or using the base model without retraining. One was on par with the traditional approach. Transfer learning STL allowed for reducing the training data requirement from a typical 70 percent down to just 10 percent. In addition, transfer learning reduced computational costs and training time. Finally, results showed that simulated data could be used without real data or in combination with real data to train a model without trading off the model’s predictive capability.On top of our previous work Pacis et al. (2022) from a single transfer learning, we explored continuous transfer learning (CTL) in Alvheim field wells. Due to the inherent uncertainty and dynamics of drilling data, it was no surprise that continuous retraining further reduced the error than a single transfer learning paradigm. Moreover, we investigated the effect of drilled formations and input combinations on model performance.