EnsAI: An Emulator for Atmospheric Chemical Ensembles

TL;DR

Ensemble-based methods for data assimilation and emission inversions are a popular way to encode flow-dependency within the model error covariance, but the need to repeatedly run a geophysical model to generate the ensemble can be a significant computational burden.

Abstract

Ensemble-based methods for data assimilation and emission inversions are a popular way to encode flow-dependency within the model error covariance. While most ensemble methods do not require the use of an adjoint model, the need to repeatedly run a geophysical model to generate the ensemble can be a significant computational burden. In this paper, we introduce EnsAI, a new AI-based ensemble generation system for atmospheric chemical constituents. When trained on an existing ensemble for ammonia generated by the GEM-MACH air quality model, it was shown that the ensembles produced by EnsAI can accurately reproduce the meteorology-dependent features of the original ensemble, while generating the ensemble 3,300 times faster than the original GEM-MACH ensemble. While EnsAI requires an upfront cost for generating an ensemble used for training, as well as the training itself, the long term computational savings can greatly exceed these initial computational costs. When used in an emissions inversion system, EnsAI produced similar inversion results to those in which the original GEM-MACH ensemble was used while using significantly less computational resources.

Figures (30)

• Figure 1: Annual mean ammonia emissions for the (unperturbed) inventory. Emissions are only displayed within the domain of the EnsAI model. Particular locations examined in this work are also displayed, which are located in (in order of descending emissions) (a) North Carolina, (b) Iowa, (c) Ohio, (d) Pennsylvania, and (e) Georgia.
• Figure 2: Monthly-mean ammonia emissions perturbations for May (top row) and the resulting ammonia surface concentration perturbations at three different time in May (bottom row) for one member of the GEM-MACH ensemble.
• Figure 3: U-Net architecture used for EnsAI. Each box represents an image or feature map, where the $x, y$ dimensions are displayed on the left and the number of channels are displayed above each box. White boxes denote feature maps that have been copied during the encoding sequence and concatenated with feature maps produced in the decoding sequence. The blue, orange, green, and purple arrows represent residual blocks, max pooling, upscaling blocks, and two-dimensional convolution, respectively. This figure is adapted from the depiction of the original U-Net architecture shown in Fig. 1 of ronneberger2015.
• Figure 4: Examples of correlations and their corresponding $L[1]$ and $L[2]$ values, which are displayed in the upper left corner of each panel. The correlation length modes are taken with respect to the origin. The values for $L[0]$ are the same for all panels and units are selected so that $L[0]=1$.
• Figure 5: Time series of components of the error covariances for the location in North Carolina (exact location shown in Fig. \ref{['fig:mean_emissions']}) for the GEM-MACH ensemble (blue), the EnsAI ensemble (orange), and the static covariance (green) for June 2015. The top plot shows the time series of the standard deviation of surface ammonia $\sigma_c$. Lower plots show time series for the horizontal correlation length modes $L_{ec}[m\le 2]$ for the emissions/surface concentration cross-correlation.