| OpendTect Workflows Documentation version 4.2 |
|---|
| Prev |
|
Next
|
Purpose: Create a Chimney "probability" Cube for fluid migration path interpretation.
Theory: When fluids (oil, gas, brine) move up through strata, rocks are cracked, chemically altered, and connate gas stays behind causing changes in the acoustic properties of the rocks. The actual path often remains visible in post-stack seismic data as subtle vertical noise trails. A Chimney Cube is a new seismic volume that highlights such vertical disturbances so that these can be interpreted as fluid migration paths. This requires studying the spatial relationships between the paths (chimneys) and other elements of the petroleum system: faults, traps, HC anomalies, (paleo) mud-volcanos, pockmarks, etc. The Chimney Cube is created by training a neural network on two sets of attributes extracted at example locations picked by a human interpreter: one set representing the chimney class (vertically disturbed noise trails) and the other representing the non-chimneys class (i.e. normal seismic response).
Software: OpendTect + Dip-Steering + Neural Networks
Workflow:
- Scan your data set for obvious chimneys. For example calculate Similarity attributes at different time-slices, look for circular features in these slices and position seismic lines through these circles. Chimneys are often associated with faults, high-amplitude anomalies, and seepage-related features such as pockmarks and mud-volcanos (look at the seabed reflection for mounds).
- Create two New Picksets: one for Chimneys and one for Non-chimneys (right-mouse click in the tree).
- Pick examples for chimneys and non-chimneys (Select the Pickset in the tree and then left-click in the scene on the element at the position you want to add; Control-click to remove a pick). Try to pick a representative set for both chimneys and non-chimneys. This means: pick different chimneys, pick as many points as possible (several hundred picks for each is typical); for non-chimneys pick both low- and high energy zones, also pick (non-leaking) faults and other noisy zones that are not vertically disturbed.
- Open the attribute set window and open the default set called: NN Chimney Cube. Select seismic and steering cube and Save the attribute set.
- Open the Neural Networks window. Select Pattern recognition (Picksets). Select Supervised, the input attributes, the Picksets (Chimneys and Non-chimneys) and the Percentage to set aside for testing (e.g. 30%).
- Train the neural network. Stop where the test set has reached minimum error (beyond that point overfitting occurs: the network learns to recognize individual examples from the training set but looses general prediction capabillities). Store the trained neural network.
- Apply the trained neural network to the seismic data in batch: Processing - Create seismic output, or on-the-fly: right-click on the element in the tree (e.g. part of an inline). You can chose between 4 outputs: Choose Chimneys to create the Chimney "probability" Cube.
Tips:
- The default attribute set can be tuned to your data set by changing parameters, and adding or removing attributes.
- The colors in the neural network indicate the relative weight attached to each attribute (ranging from white to red). White nodes indicate low weights meaning the attributes are not contributing much and can be removed to speed up processing time.
- Display the Mis-classified points (Pickset tree) to evaluate why these are mis-classified. If you agree with the network you may want to remove some of these points from the input sets and retrain the network. This will improve the classification results but the process is dangerous as you are working towards a solution.
For more info, see this Tutorial video:
Chimney Cube (flash video)