Born as a branch of I2AM project, the DI4G system provides a data integration feature. The values obtained from image analysis can be aligned and merged with other data logs from the same well (such as density, porosity, sonic, API gamma ray, etc.), and the system builds a complete “feature table” collecting data from all the available logs.
The following step is a clustering task, in which the system builds a group of items with similar features, grouping the samples that are sharing some characteristics.
The clustering application is a semi-automatic task, in which the interpreter can decide, based on his geological background and on the geological characteristics of the logged section, to keep the clusters/classes proposed by the system, or to modify the number of clusters/classes. In this step, by using a graphical representation of the hierarchical clustering structure (a tree, called dendrogram) the interpreter can interactively merge or split the detected rock classes, adding details and precision to the proposed clustering.
The clustering process and the propagation of the classes along the logged sections are very fast (30 seconds) allowing an interactive approach, producing several scenarios with different numbers of classes and/or allowing a quick update of the image log interpretation once more data/knowledge is acquired. DI4G can work on several log types, and also without image logs, it can merge data with different resolution, and provide an easy import wizard. DI4G is a prototype still under development. DI4G is developed in collaboration with ENDIF (Engineering Departement in Ferrara) and with intelliWARE, a new software development company.
For more information about DI4Gplease contact us.