Gradient boosting to boost the efficiency of hydraulic fracturing

    Research output: Contribution to journalArticlepeer-review

    20 Citations (Scopus)

    Abstract

    In this paper, we present a data-driven model for forecasting the production increase after hydraulic fracturing (HF). We use data from fracturing jobs performed at one of the Siberian oilfields. The data includes features, characterizing the jobs, and geological information. To predict an oil rate after the fracturing, machine learning (ML) technique was applied. We have compared the ML-based prediction to a prediction based on the experience of reservoir and production engineers responsible for the HF-job planning. We discuss the potential for further development of ML techniques for predicting changes in oil rate after HF.

    Original languageEnglish
    Pages (from-to)1919-1925
    Number of pages7
    JournalJournal of Petroleum Exploration and Production Technology
    Volume9
    Issue number3
    DOIs
    Publication statusPublished - 1 Sep 2019

    Keywords

    • Decision trees
    • Gradient boosting
    • Hydraulic fracturing
    • Machine learning

    Fingerprint

    Dive into the research topics of 'Gradient boosting to boost the efficiency of hydraulic fracturing'. Together they form a unique fingerprint.

    Cite this