Surrogate Model Inversion for High-Resolution Gas Emission Mapping
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for estimating gas emission distribution, such as bottom-up and top-down approaches, face challenges including high computational cost, data collection complexities, limited spatial coverage, and inaccuracies due to model uncertainties and errors, especially in remote areas.
Innovation Solution
A dual optimization scheme using a surrogate model that trains on numerical transport models and corrects prior emissions by minimizing the difference between predicted and satellite concentration data, allowing for high-resolution emission distribution estimation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Area of stationary object
If top-down methods using data assimilation algorithms (EnKF, 4D-Var) are used to estimate emission distribution, then spatial coverage and ability to capture all emission sources are improved, but computational cost and complexity increase significantly
Solution Approach 1:
The patent creates a simplified copy (surrogate model) of the complex atmospheric transport model. This surrogate model replicates the essential functionality of predicting gas concentrations from emission distributions but with dramatically reduced computational requirements, enabling high-resolution emission estimation without the prohibitive computational cost of full data assimilation algorithms
Solution Approach 2:
The surrogate model acts as an intermediary between satellite concentration observations and emission distribution estimates. Instead of directly implementing complex data assimilation algorithms, the system uses the surrogate model as a mediator that translates concentration data into emission estimates through a computationally efficient interface
2Manufacturing precision
If high-resolution emission distribution estimation is performed using traditional methods, then manufacturing precision of emission estimates is improved, but loss of time and computational resources increases
Solution Approach 1:
The surrogate model is pre-trained offline using comprehensive atmospheric transport model simulations. This preliminary action captures the complex relationships between emissions, meteorology, and concentrations in advance, allowing the model to produce high-resolution emission estimates rapidly when applied to new satellite data without repeating the computationally intensive training process
3Manufacturing precision
If bottom-up methods are used to gather detailed source data, then manufacturing precision of emission estimates is improved, but device complexity and data collection requirements increase
Solution Approach 1:
Instead of using bottom-up methods that aggregate emissions from individual sources, the patent employs a top-down inversion approach. Satellite concentration measurements are inverted through the surrogate model to directly estimate emission distributions, eliminating the need for extensive ground-based data collection infrastructure while providing comparable or superior precision
4Reliability
If atmospheric transport models with detailed physics are used, then reliability of concentration predictions is improved, but computational cost increases
Solution Approach 1:
The surrogate model creates a simplified copy of the physics-rich atmospheric transport model. It captures the essential physical relationships governing gas transport and transformation while using parameterized representations instead of full numerical simulations, maintaining prediction reliability with fraction of the computational energy
Data Source
Figure 1
Figure 2
Figure 3~4
AI summary
Obtaining accurate estimates of emission distribution of gases is a technically challenging as well as environmentally relevant problem. Existing techniques have high computational cost, need deep mathematical and computational expertise, and are prone to errors. Hence, embodiments of present disclosure provide a method and system for determining emission distribution using a surrogate model. The method takes prior emission distributions of gas and updates them using its future concentrations in the atmosphere by using a trained surrogate of a numerical transport model by maintaining consistency between the emissions, atmospheric transport, and future concentrations. The surrogate model is trained in a data-driven way to improve transport models, which is less complicated and time-consuming than correcting the parameterizations and constants used in numerically modeling various processes in transport.