Apparatus and methods for improved subsurface data processing systems
A method and apparatus for subsurface data processing includes determining a set of clusters based at least in part on measurement vectors associated with different depths or times in subsurface data, defining clusters in a subsurface data by classes associated with a state mode, reducing a quantity of the subsurface data based at least in part on the classes, and storing the reduced quantity of the subsurface data and classes with the state model in a training database for a machine learning process.
1. A method, comprising:
providing training data and input data, the training data including reduced training data and classes with at least one state model;
assigning training data classes with a state model to the input data;
reconstructing input data based at least in part on the training data;
determining a reconstruction error based at least in part on the reconstructed input data;
sorting the input data based at least in part on the reconstruction error; and
providing the sorted input data as an output.
2. The method of claim 1 , wherein the determining the reconstruction error includes determining a root mean square error between actual and reconstructed measurements class by class.
3. The method of claim 1 , further comprising displaying the sorted input data in a visualization.
4. The method of claim 1 , further comprising determining a class assignment probability for the sorted input data.
5. A subsurface data processing apparatus, comprising:
a memory configured to store subsurface data and a knowledgebase for a machine learning process; and
a processor configured to perform the method of claim 1 .