NeuPlume: generative inversion of atmospheric point-source emissions from sparse observations
- 1State Key Laboratory of Information Engineering in Surveying Mapping and Remote Sensing (Wuhan, China)
Abstract
Inverting point-source emissions from sparse atmospheric observations is difficult because emission rate, release height, wind speed, turbulence, and plume morphology can compensate for one another. We present NeuPlume, a neural-physical framework that formulates inversion as observation-guided generation and selection of complete three-dimensional concentration fields. A Lagrangian stochastic model builds a scenario-specific forward library, a conditional neural field compresses the simulated fields, and a latent diffusion model learns their conditional distribution. During inversion, diffusion posterior sampling generates candidate fields on a coarse-to-fine parameter grid, and NeuPlume returns the parameters and field that best match the observations. Across 30 synthetic cases, the selected fields achieve a mean spatial correlation of 0.942 and a mean emission-rate error of 13.6 %. Matched stress tests show that both observation geometry and transport-model fidelity govern inversion quality: trajectory-concentrated sampling weakens full-field reconstruction, while unrepresented transport alters parameter identification and, for effective plume rise, also degrades field reconstruction. Applied to four UAV methane transects above a coal-mine ventilation shaft, NeuPlume yields known- U minimum-loss emission estimates of 5.27–15.85 kt yr ⁻¹ and exposes wind-speed and height-boundary sensitivities under model mismatch. NeuPlume thus provides an extensible methodology for jointly estimating source parameters and concentration fields: additional transport regimes can be incorporated through regime-specific simulation ensembles and neural-model retraining.
Versions
Related
- Global Observations and European emissions of the halogenated olefins HFO-1234yf, HFO-1234ze(E), and HCFO-1233zd(E) from the AGAGE (Advanced Global Atmospheric Gases Experiment) network
- Generative Atmospheric Super-Resolution from Heterogeneous In Situ Observations through Composable Interfaces
- Recurrent High-Resolution Satellite Observations Quantify Facility-Resolved Annual Large-Emitter Methane Emissions in the Permian Basin
- Improved determination of atmospheric trace gas emissions through observation-based analysis techniques: The AMIGO global initiative
- Satellite observations of nitrous oxide emissions from adipic acid production
BibTeX
@article{wang2026neuplume,
title = {{NeuPlume: generative inversion of atmospheric point-source emissions from sparse observations}},
author = {Lei Wang and Xin Ma},
journal = {Atmospheric Chemistry and Physics},
year = {2026},
month = oct,
doi = {10.5194/acp-26-14185-2026},
url = {https://acp.copernicus.org/articles/26/14185/2026/},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - NeuPlume: generative inversion of atmospheric point-source emissions from sparse observations
AU - Lei Wang
AU - Xin Ma
PY - 2026
DA - 2026/10/09
JO - Atmospheric Chemistry and Physics
DO - 10.5194/acp-26-14185-2026
UR - https://acp.copernicus.org/articles/26/14185/2026/
AB - Inverting point-source emissions from sparse atmospheric observations is difficult because emission rate, release height, wind speed, turbulence, and plume morphology can compensate for one another. We present NeuPlume, a neural-physical framework that formulates inversion as observation-guided generation and selection of complete three-dimensional concentration fields. A Lagrangian stochastic model builds a scenario-specific forward library, a conditional neural field compresses the simulated fields, and a latent diffusion model learns their conditional distribution. During inversion, diffusion posterior sampling generates candidate fields on a coarse-to-fine parameter grid, and NeuPlume returns the parameters and field that best match the observations. Across 30 synthetic cases, the selected fields achieve a mean spatial correlation of 0.942 and a mean emission-rate error of 13.6 %. Matched stress tests show that both observation geometry and transport-model fidelity govern inversion quality: trajectory-concentrated sampling weakens full-field reconstruction, while unrepresented transport alters parameter identification and, for effective plume rise, also degrades field reconstruction. Applied to four UAV methane transects above a coal-mine ventilation shaft, NeuPlume yields known- U minimum-loss emission estimates of 5.27–15.85 kt yr ⁻¹ and exposes wind-speed and height-boundary sensitivities under model mismatch. NeuPlume thus provides an extensible methodology for jointly estimating source parameters and concentration fields: additional transport regimes can be incorporated through regime-specific simulation ensembles and neural-model retraining.
SN - 1680-7324
ER -