Mapping Fiber Optic DAS Data to Particle Motion via Machine Learning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional seismic data acquisition methods, such as surface seismic measurements, are often contaminated by near-surface complexities, while downhole sensors provide limited subsurface illumination due to cost and installation challenges, necessitating an alternative for effective subsurface property estimation in oil & gas and mining industries.
Innovation Solution
The method involves using Distributed Acoustic Sensing (DAS) with fiber-optic cables to collect seismic data and employing machine learning to translate DAS measurements into particle motion data comparable to discrete seismic receiver data, enabling integration into established seismic processing workflows with enhanced spatial resolution and coverage.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If downhole sensors are deployed to avoid near-surface contamination, then measurement reliability is improved, but device complexity and installation difficulty increase
Solution Approach 1:
The patent replaces traditional mechanical downhole sensors (geophones, accelerometers) with fiber optic DAS systems that use optical principles. The fiber optic cable acts as a distributed array of sensors without requiring mechanical coupling to the formation, eliminating complex installation procedures while maintaining measurement reliability by sensing acoustic waves through the fiber itself.
Solution Approach 2:
The fiber optic cable serves multiple functions: it acts as both the communication medium for data transmission and the sensing element for acoustic detection. This multi-functionality eliminates the need for separate sensor installations, reducing device complexity while maintaining reliable subsurface measurements.
2Measurement precision
If discrete seismic receivers are used to obtain particle motion data, then measurement precision is improved, but quantity of substance and cost increase
Solution Approach 1:
The patent segments the fiber optic cable into numerous small sensing elements along its length, creating a distributed array of virtual sensors. This segmentation allows the system to achieve the measurement precision of multiple discrete sensors while using a single continuous fiber optic cable, thereby reducing the quantity of physical substances required.
Solution Approach 2:
The patent merges the functions of multiple discrete seismic receivers into a single fiber optic cable system. The cable integrates hundreds or thousands of sensing points along its length, providing comprehensive particle motion measurement capability that would otherwise require numerous separate sensors, thus reducing material quantity and cost.
3Ease of operation
If DAS data is directly processed using conventional seismic methods, then ease of operation is improved, but measurement precision deteriorates due to differences in data characteristics
Solution Approach 1:
The patent introduces machine learning models as an intermediary layer between DAS data and conventional seismic processing workflows. These models translate DAS measurements into particle motion data that mimics the characteristics of discrete sensor data, allowing conventional processing methods to be applied while maintaining measurement precision by accounting for the fundamental differences in data acquisition mechanisms.
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 and robust wavefield characterization with higher spatial resolution and coverage, overcoming the limitations of conventional methods by effectively interpreting DAS data similar to geophone data, offering a cost-effective and durable solution for subsurface imaging.
Implementation Method 1
obtain, from a fiber optic DAS system in a wellbore, a first set of DAS data associated with a first seismic wave
Data Source
AI summary
A method for mapping fiber optic distributed acoustic sensing (DAS) measurements to particle motion involves obtaining, from a fiber optic DAS system in a wellbore, a first set of DAS data associated with a first seismic wave; obtaining, from a discrete seismic receiver in the wellbore, measured particle motion data associated with the first seismic wave; generating training data from the first set of DAS data and the measured particle motion data; training a machine learning model using the training data; obtaining a second set of DAS data associated with a second seismic wave; and determining a predicted particle motion in response to the second seismic wave using the machine learning model applied to the second set of DAS data.