Trap Prevention in Machine Learning in Prediction of Petrophysical Parameters: A Case Study in The Field X

Abstract

Petrophysical parameters such as porosity and water saturation are vital in the petroleum industry for reservoir characterization. These aspects are typically assessed through laboratorium measurements of core samples or intricate petrophysical calculations. Machine Learning (ML) offers a cost-effective and efficient approach as an alternative to conventional methods of predicting those parameters. However, developing ML models can be prone to the invisible traps such as overfitting, underfitting, feature selection, and feature importance. This study is intended to share how to identify the traps and its mitigation by establishing a synergistic workflow between ML and petrophysical theory. A model was developed based on data from several wells in X field, where they are randomized and split into test and train data. Well-log normalization preceded data splitting, and input features were normalized with outlier removal. A feature selection function was then employed to choose a specific amount of log data. Finally, the model selection function identified the highest-scoring model. Without a proper workflow, overfitting, irrelevant feature selection, and imprecise ranking issues emerged. However, with the proper workflow, these invisible traps were mitigated, even with a relatively small dataset. The final model could accurately predict porosity and water saturation