English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Machine learning approaches are widely studied in the production predictionof CBM wells after hydraulic fracturing, but merely used in practice due to thelow generalization ability and the lack of interpretability. A novelmethodology is proposed in this article to discover the latent causality fromobserved data, which is aimed at finding an indirect way to interpret themachine learning results. Based on the theory of causal discovery, a causalgraph is derived with explicit input, output, treatment and confoundingvariables. Then, SHAP is employed to analyze the influence of the factors onthe production capability, which indirectly interprets the machine learningmodels. The proposed method can capture the underlying nonlinear relationshipbetween the factors and the output, which remedies the limitation of thetraditional machine learning routines based on the correlation analysis offactors. The experiment on the data of CBM shows that the detected relationshipbetween the production and the geological/engineering factors by the presentedmethod, is coincident with the actual physical mechanism. Meanwhile, comparedwith traditional methods, the interpretable machine learning models have betterperformance in forecasting production capability, averaging 20% improvement inaccuracy.

Interpretability and causal discovery of the machine learning models to predict the production of CBM wells after hydraulic fracturing