Skip to content
#diffusion models Open access

NeuPlume: generative inversion of atmospheric point-source emissions from sparse observations

Oct 2026 · Atmospheric Chemistry and Physics · Vol 26, pp. 14185-14203 · 0 citations · 42 references
Atmospheric and Environmental Gas Dynamics

TL;DR

NeuPlume is presented, a neural-physical framework that formulates inversion as observation-guided generation and selection of complete three-dimensional concentration fields and provides an extensible methodology for jointly estimating source parameters and concentration fields.

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.

Read PDF

Similar papers

Preprint Oct 2026

Operator-Aware Posterior Sampling for Multivariate Weather Downscaling

This paper learns the forward operator from paired data and normalize the gradient per channel and shows that this normalization corresponds to steepest descent under a block-max norm, allowing a single guidance strength across variables.

Carlo Saccardi, R. Saathof, Geethu Joseph et al. · 0 citations

Generative Atmospheric Super-Resolution from Heterogeneous In Situ Observations through Composable Interfaces

This work forms this reconstruction problem as generative atmospheric super-resolution and introduces composable observation interfaces for conditioning a single pretrained 13-variable atmospheric diffusion model without retraining the underlying model.

Yang Xu, Dibyajyoti Chakraborty, Hai-Wen Guan et al. · 0 citations
Open access Sep 2026

Reconstructing subsurface temperature fields from single-point time series: a metric learning approach in the South China Sea

Subsurface ocean observations remain severely limited in spatial coverage due to the high cost and operational difficulty of in-situ deployment. Although moored buoys and profiling floats enable continuous, minute-level sampling at fixed locations, the temporal evolution information they record is largely underutil...

Lu-,-Hong-Feng-,-Li-Zheng-Bao-,-Guo-Zhong-Wen Hong, Meng-Yao Wang, Qing Xu et al. · 0 citations
#diffusion models Open access Sep 2026

DIRECT 1.0: a diffusion-based generative model for dense sea surface temperature reconstructions from sparse satellite observations

DI, a conditional generative framework for dense SST reconstruction that models the full distribution of plausible solutions rather than a single deterministic estimate, is introduced, enabling reliable SST reconstruction from sparse satellite observations.

Grega Rovšček, M. Ličer, A. Barth et al. · 0 citations

Physics-Guided Flow-Map Matching for Precipitation Nowcasting

Precipitation nowcasting, generating future radar fields from past observations, is critical for flood warning and disaster response. It is also a demanding benchmark for spatiotemporal generative modeling, with chaotic dynamics, heavy-tailed intensities, and rare high-intensity structures that matter most. Determinist...

Shunya Nagashima, Takumi Bannai, Makoto Misaizu et al. · 0 citations

Related blog posts

Microsoft Research Blog Nov 16, 2026

TokenEconomizer: Learning from Experience to Make AI Coding Agents More Efficient

AI coding agents are increasingly help developers fix bugs and build features largely on their own, but every interaction with their models consumes tokens. In each session, an agent sends instructions, tool descriptions, and session history to its model. Most efforts to reduce this cost focus on individual tasks. Yet developers return to the same […] The post TokenEconomizer: Learning from Experience to Make AI Coding Agents More Efficient appeared first on Microsoft Research.

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.