Deep Learning Surrogates for Real-Time Gas Emission Inversion

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Newman, Thomas, Nemeth, Christopher, Jones, Matthew, Jonathan, Philip
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866916796967157760
author Newman, Thomas
Nemeth, Christopher
Jones, Matthew
Jonathan, Philip
author_facet Newman, Thomas
Nemeth, Christopher
Jones, Matthew
Jonathan, Philip
contents Real-time identification and quantification of greenhouse-gas emissions under transient atmospheric conditions is a critical challenge in environmental monitoring. We introduce a spatio-temporal inversion framework that embeds a deep-learning surrogate of computational fluid dynamics (CFD) within a sequential Monte Carlo algorithm to perform Bayesian inference of both emission rate and source location in dynamic flow fields. By substituting costly numerical solvers with a multilayer perceptron trained on high-fidelity CFD outputs, our surrogate captures spatial heterogeneity and temporal evolution of gas dispersion, while delivering near-real-time predictions. Validation on the Chilbolton methane release dataset demonstrates comparable accuracy to full CFD solvers and Gaussian plume models, yet achieves orders-of-magnitude faster runtimes. Further experiments under simulated obstructed-flow scenarios confirm robustness in complex environments. This work reconciles physical fidelity with computational feasibility, offering a scalable solution for industrial emissions monitoring and other time-sensitive spatio-temporal inversion tasks in environmental and scientific modeling.
format Preprint
id arxiv_https___arxiv_org_abs_2506_14597
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Deep Learning Surrogates for Real-Time Gas Emission Inversion
Newman, Thomas
Nemeth, Christopher
Jones, Matthew
Jonathan, Philip
Machine Learning
Applications
Real-time identification and quantification of greenhouse-gas emissions under transient atmospheric conditions is a critical challenge in environmental monitoring. We introduce a spatio-temporal inversion framework that embeds a deep-learning surrogate of computational fluid dynamics (CFD) within a sequential Monte Carlo algorithm to perform Bayesian inference of both emission rate and source location in dynamic flow fields. By substituting costly numerical solvers with a multilayer perceptron trained on high-fidelity CFD outputs, our surrogate captures spatial heterogeneity and temporal evolution of gas dispersion, while delivering near-real-time predictions. Validation on the Chilbolton methane release dataset demonstrates comparable accuracy to full CFD solvers and Gaussian plume models, yet achieves orders-of-magnitude faster runtimes. Further experiments under simulated obstructed-flow scenarios confirm robustness in complex environments. This work reconciles physical fidelity with computational feasibility, offering a scalable solution for industrial emissions monitoring and other time-sensitive spatio-temporal inversion tasks in environmental and scientific modeling.
title Deep Learning Surrogates for Real-Time Gas Emission Inversion
topic Machine Learning
Applications
url https://arxiv.org/abs/2506.14597