Satellite-Based Methane Emissions Quantification Using Learning Machines
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for measuring hydrocarbon site emissions are limited by intermittent ground-level data, which can miss stochastic characteristics of high-emitting sites and restrict spatial resolution, while satellite data provides continuous monitoring but is computationally complex and time-consuming for emissions quantification.
Innovation Solution
A learning machine is trained using satellite data and hydrocarbon-related attributes to generate emissions factors, enabling continuous monitoring and reducing errors in emissions estimation, allowing for real-time adjustments in hydrocarbon site operations to minimize emissions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If ground level measurements are used to measure emissions from hydrocarbon sites, then emissions can be measured at the ground level, but the spatial resolution is restricted and data is intermittent
Solution Approach 1:
The patent transitions from ground-level three-dimensional measurements to satellite-based remote sensing, adding a spatial dimension (aerial/satellite view) to emissions monitoring. This enables coverage of large geographic areas while maintaining measurement capabilities through satellite-based detection of greenhouse gas concentrations.
2Reliability
If satellite data is used to measure emissions from hydrocarbon sites, then continuous monitoring is provided, but computational complexity increases
Solution Approach 1:
The patent pre-processes satellite data and establishes emission factor relationships in advance, creating a framework that allows continuous monitoring without requiring complex real-time computations. By preparing emission factors and calibration data beforehand, the system reduces the computational burden during actual emissions quantification.
3Measurement precision
If atmospheric inverse modeling is used to link satellite data to ground level emissions, then emissions quantification is achieved, but time consumption increases
Solution Approach 1:
The patent employs simplified emission factor models that can be quickly updated and discarded, replacing complex, time-consuming inverse modeling approaches. These lighter computational models provide sufficient accuracy for emissions quantification without requiring extensive processing time, enabling more frequent updates and real-time monitoring.
Data Source
AI summary
A method for determining an emissions associated with hydrocarbon recovery of a hydrocarbon site within a geographic region, the method comprises selecting the hydrocarbon site for which to determine the emissions. The method comprises determining current values of hydrocarbon related attributes that affect emissions at the hydrocarbon site for a current time frame. The method comprises inputting the current values of the hydrocarbon related attributes related to emissions at the hydrocarbon site into a learning machine to generate an emissions factor for each of the hydrocarbon related attributes that affect the emissions at the hydrocarbon site.