Numerous test data accumulates in the process of gas reservoir exploration and development, so it is necessary to apply the data mining technology to this process. Influenced by the geologic factors such as structure, deposition and diagenesis, tight sandstone gas reservoir formation types are so diversified that traditional cross-plot analysis technique hardly identify the formation types. In this paper, the formation types of tight sandstone gas reservoir in Daniudi area are successfully identified using the decision tree algorithm of data mining based on hierarchical decomposition theory, facilitating the development of the gas reservoir.

Daniudi gas field is a tight sandstone gas field in the northeast of Ordos Basin. How to use the successful experience in developing area to predict favorable gas-rich area in other areas in this gas field is very important to the next exploration and development in this field. This paper proposes a multi-information integrated method to predict favorable gas-rich area. Firstly describe sedimentary microfacies by integrating seismic, logging and geological information; and then summarize and analyze the seismic reflection patterns of medium-high productivity wells; finally determine the favorable gas-rich area with the distribution of storage coefficient based on the previous analysis. The welltest of newly drilled wells shows that the coincidence rate of favorable gas-rich area predicted by this method could be up to 90%,and this method could be extended to use in the other tight sandstone gas reservoirs.