MAPCast: A Convection Allowing MPAS Emulator for Ensemble-based Background Error Covariance Estimation Toward Multi-Scale Data Assimilation
Machine learning (ML) emulators offer a cost-efficient alternative to numerical weather prediction models for generating convection-allowing background ensembles in ensemble-based data assimilation (DA). However, few studies have explored ML-based surrogate background ensembles for estimating background-error covariances (BECs). This study develops a convection-allowing emulator, MAPCast, trained on historical convection-allowing simulations from the Model for Prediction Across Scales (MPAS), and evaluates its ability to estimate BECs, paving the way toward multiscale DA. The evaluation uses 10 retrospective convective cases at 15- and 60-min forecast lead times corresponding to subhourly and hourly DA. MAPCast reproduces MPAS forecasts with good fidelity, including realistic storm coverage, temporal evolution, and similar spatial and spectral characteristics of state variables. Discrepancies are primarily confined to small spatial scales near sharp gradients and convective-scale features and variables. For BEC statistics, MAPCast captures ensemble spread magnitude and spatial distribution for most variables, although larger errors occur for storm-related fields that are vertical velocity and reflectivity. Correlation structures are reproduced most faithfully at mesoscale and above, followed by at convective scales, whereas cross-variable correlations are less accurately represented than univariate correlations, indicating that multivariate coupling remains the principal limitation. MAPCast shows weaker replication of full-scale versus decomposed large and small-scale correlations. BEC estimates derived from 15-min forecasts consistently outperform those from 60-min forecasts, suggesting that shorter lead times better preserve flow-dependent error structures.