Automated Domain Conversion for Seismic Well Ties
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The oil and gas industry faces challenges in accurately determining the depth of subsurface features due to the high uncertainty in surface seismic datasets recorded in the two-way seismic travel-time domain and the limited spatial information from well logs recorded in the depth domain.
Innovation Solution
A method is developed to transform well logs from the depth domain to the seismic two-way travel-time domain using a trained network, combining sonic well logs and borehole seismic datasets to produce a calibrated surface seismic dataset, which correlates reflected signals from surface seismic datasets with features detected by well logs, thereby reducing uncertainty in depth determination.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Area of stationary object
If surface seismic datasets are used to determine subsurface feature depth, then large spatial area coverage is achieved, but measurement precision deteriorates due to significant uncertainty in depth estimation
Solution Approach 1:
The patent combines surface seismic datasets with well logs by transforming well logs from depth domain to two-way travel-time domain using a trained neural network. This merging allows the strengths of both data sources to be utilized: surface seismic provides large spatial coverage while well logs provide precise depth measurements at well locations, resulting in a calibrated seismic dataset with reduced uncertainty across the entire spatial area.
2Measurement precision
If well logs are used to determine subsurface feature depth, then measurement precision is improved with low uncertainty at well locations, but area coverage deteriorates as information is limited to only wells where logs are recorded
Solution Approach 1:
The patent uses a trained neural network as an intermediary to transform well log data from depth domain to two-way travel-time domain. This transformation enables the well log information to be integrated with surface seismic data, allowing the high-precision depth measurements from well logs to be extrapolated across the entire spatial coverage of the seismic survey through the calibrated seismic dataset.
3Adaptability or versatility
If manual transformation methods are used to convert well logs from depth domain to seismic time domain, then adaptability is maintained, but productivity deteriorates due to time-consuming manual processes
Solution Approach 1:
The patent replaces manual mechanical transformation processes with an automated neural network system. The trained network automatically performs the complex domain transformation from depth to two-way travel-time, eliminating time-consuming manual operations while maintaining high adaptability to different well log and seismic data types through the network's learning capability.
Data Source
AI summary
A method is claimed for automatically transforming sonic well logs from a depth domain to a seismic two-way travel-time domain. The method includes obtaining a training well with a measured sonic well log in the depth domain and a borehole seismic dataset in the depth domain and obtaining an application well with only a measured sonic well log in the depth domain. The method further includes training a network to predict a transformed sonic well log for the training well based, at least in part, on the measured sonic well log and the borehole seismic dataset in the training well, and predicting with the network, the transformed sonic well log in the application well.