Near-Surface Velocity Modeling Using Uphole and Full Waveform Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional seismic exploration on land is hindered by near-surface complexities such as the weathering layer, which introduces distortions in seismic images due to sharp vertical and horizontal variations in physical parameters, leading to inaccurate interpretation of subsurface structures and inability to accurately characterize the shallow near surface.
Innovation Solution
A combination of uphole vertical velocities and full seismic waveform data is used to build continuous three-dimensional velocity models, employing a machine learning model trained with seismic waveform data and uphole data to generate high-resolution near surface velocity models, reducing computational complexity and avoiding distortions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Speed
If conventional seismic acquisition setups are used to target deep structures, then deep geological exploration performance is improved, but the ability to accurately characterize the very shallow weathering layer deteriorates
Solution Approach 1:
The patent divides the velocity model construction into two distinct components: uphole vertical velocities for the shallow near surface and full waveform seismic data for deeper structures. This segmentation allows each data type to be optimized for its appropriate depth range, resolving the contradiction between deep exploration capability and shallow characterization accuracy.
Solution Approach 2:
The patent applies different data sources and processing methods to different depth zones: uphole survey data is specifically used for the shallow weathering layer where high vertical resolution is needed, while full waveform data is used for deeper structures. This local quality approach ensures each zone is characterized by the most appropriate data type.
2Measurement precision
If uphole seismic surveys are used to investigate the shallow near surface, then shallow velocity profile resolution is improved, but the ability to characterize broader subsurface structures deteriorates
Solution Approach 1:
The patent merges uphole vertical velocity data with full waveform seismic data to create a comprehensive velocity model. The uphole data provides high-resolution shallow velocities while the full waveform data provides broader subsurface coverage, and their combination resolves the contradiction between localized precision and areal coverage.
3Measurement precision
If machine learning models are trained with both seismic waveform data and uphole data, then near surface velocity model accuracy is improved, but computational complexity increases
Solution Approach 1:
The patent performs preliminary processing of the seismic data by forming gathers and transforming to the Laplace-Fourier domain before feeding into the machine learning model. This preliminary action reduces the dimensionality and complexity of the input data while preserving the essential information needed for accurate velocity model prediction.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
This approach provides accurate, high-resolution velocity models of the near surface, enabling precise characterization of shallow geological structures and reducing computational resources, while correcting for local shallow conditions and avoiding 'bullseye' effects.
Implementation Method 1
The seismic wave travels into the ground, is reflected by subsurface formations, and returns to the surface where it is recorded by sensors called geophones
Implementation Method 2
The seismic wave travels into the ground, is reflected by subsurface formations, and returns to the surface
Implementation Method 3
A source is lowered within a shallow borehole and the uphole times are recorded by seismic receivers (e.g., geophones) located on the surface in proximity of the borehole. The vertical travel times can be interpreted for the interval velocities
Data Source
AI summary
Systems and methods for building a near surface velocity model for a subsurface formation include obtaining seismic data representing a subsurface formation; forming seismic gathers based on the seismic data; and determining uphole vertical velocities for the subsurface formation based on uphole seismic survey data. A training dataset is formed including input features that include a subset of the seismic gathers and labeled output data that includes the uphole vertical velocities corresponding to the subset of seismic gathers. A machine learning model is trained using the training dataset; and a near surface velocity model is generated for the subsurface formation using the machine learning model that takes as input the seismic gathers.