Model-Driven Data Mining in the Oil & Gas Exploration and Production

Data mining is not an autonomous data-driven trial-and-error process, but a human-machine-cooperated interactive knowledge discovery process. As a result, the domain-driven data mining is proposed. Additionally, there are lots of models existing in oil and gas exploration and production, such as geological models, logging constrained seismic inversion models and well logging interpretation models, which contain the multifarious domain knowledge. This paper proposes model-driven data mining in the oil and gas exploration and production, with the purpose of mining actionable knowledge benefiting the exploration and production of oil and gas. Main ideas of the model-driven data mining methodology are introduced. Guided by this methodology, we demonstrate some of our work in mining four types of data, including petrophysical data, logging data, seismic data and geological data. Real work of model-driven data mining has shown that our methodology is practical and potential for deeply analyzing data in the exploration and production of oil and gas.