arXiv subjects

Žiga Zaplotnik

Publications and source records attributed to Žiga Zaplotnik.

4 recordsLinked to original sources

arXiv2025

A Neural-Network Model-Measurement-Based Observation Operator For Weather Radar Reflectivity Assimilation

In three-dimensional variational data assimilation (3DVar) for numerical weather prediction (NWP), the observation operator $\mathcal{H}$ plays a central role by mapping model state variables to an observation equivalent. For weather radar, however, specifying $\mathcal{H}$ is particularly challenging: reflectivity is a nonlinear, microphysics-dependent diagnostic quantity that only indirectly relates to the model's prognostic variables, making traditional parameterised radar operators complex, regime-dependent and difficult to tune. In this study, we propose a neural-network (NN)-based observation operator for radar reflectivity and apply it within a 3DVar framework. Using five years (2019-2023) of radar reflectivity data from the Lisca radar and 4.4 km-resolution short-range forecasts from ALADIN model over Slovenia, we train a convolutional encoder-decoder neural network to map model temperature, humidity, horizontal wind components and surface pressure fields to radar reflectivity. Across independent test cases spanning clear-sky, stratiform, and convective regimes, the NN-based operator accurately reproduces the spatial structure and intensity of observed reflectivity, relying primarily on the model state near the observation point. In the extreme precipitation case, which caused widespread floods in Slovenia on August 4, 2023, assimilating the full radar disc reduces the domain-averaged reflectivity root-mean-square error from 5.99 dBZ to 3.47 dBZ and improves the alignment between the analysed and observed convective bands. Embedded within 3DVar, the Jacobian of the NN observation operator allows radar reflectivity observations to inform model state variables, producing corresponding analysis increments. The proposed NN radar observation operator offers a flexible alternative to traditional parameterised radar operators for improving convective-storm forecasts.

physics.ao-ph↗

arXiv2025

A unified neural background-error covariance model for midlatitude and tropical atmospheric data assimilation

Estimating background-error covariances remains a core challenge in variational data assimilation (DA). Operational systems typically approximate these covariances by transformations that separate geostrophically balanced components from unbalanced inertio-gravity modes - an approach well-suited for the midlatitudes but less applicable in the tropics, where different physical balances prevail. This study estimates background-error covariances in a reduced-dimension latent space learned by a neural-network autoencoder (AE). The AE was trained using 40 years of ERA5 reanalysis data, enabling it to capture flow-dependent atmospheric balances from a diverse set of weather states. We demonstrate that performing DA in the latent space yields analysis increments that preserve multivariate horizontal and vertical physical balances in both tropical and midlatitude atmosphere. Assimilating a single 500 hPa geopotential height observation in the midlatitudes produces increments consistent with geostrophic and thermal wind balance, while assimilating a total column water vapor observation with a positive departure in the nearly-saturated tropical atmosphere generates an increment resembling the tropical response to (latent) heat-induced perturbations. The resulting increments are localized and flow-dependent, and shaped by orography and land-sea contrasts. Forecasts initialized from these analyses exhibit realistic weather evolution, including the excitation of an eastward-propagating Kelvin wave in the tropics. Finally, we explore the transition from using synthetic ensembles and a climatology-based background error covariance matrix to an operational ensemble of data assimilations. Despite significant compression-induced variance loss in some variables, latent-space assimilation produces balanced, flow-dependent increments - highlighting its potential for ensemble-based latent-space 4D-Var.

physics.ao-ph↗

arXiv2025

Radiosonde-constrained reconstructions reveal a weakening Northern Hadley circulation

The Northern Hadley cell (NHC) is a fundamental component of Earth's atmospheric circulation, governing precipitation patterns affecting nearly four billion people. Despite its importance, the sign of recent multidecadal trends in NHC strength remains unresolved. Climate models consistently simulate a weakening, whereas reanalyses have suggested an opposing strengthening. Here, we constrain this discrepancy using the global radiosonde record. To assess the NHC, we reconstruct the three-dimensional meridional wind from sparse radiosonde observations using a masked autoencoder graph neural network and apply an identical reconstruction to five modern reanalyses, sampled at the same locations. This paired reconstruction framework reveals a systematic underestimation of climatological NHC strength across all reanalyses, corroborated in ERA5 by systematic data assimilation increments that persistently strengthen the circulation. Most importantly, our radiosonde-based reconstructions provide vertically resolved observational evidence of a statistically significant weakening of the NHC since 1980, reconciling observations with climate model projections. The weakening is consistently reproduced by all reanalysis-based reconstructions and is robust across training datasets and analysis periods, strengthening confidence in projected changes in the Hadley circulation. More broadly, this study establishes a temporally homogeneous reconstruction framework for evaluating large-scale circulation changes and assessing both reanalysis products and climate model projections.

physics.ao-ph↗

arXiv2023

3D-Var Data Assimilation using a Variational Autoencoder

Data assimilation of atmospheric observations traditionally relies on variational and Kalman filter methods. Here, an alternative neural-network data assimilation (NNDA) with variational autoencoder (VAE) is proposed. The three-dimensional variational (3D-Var) data assimilation cost function is utilised to determine the analysis that optimally fuses simulated observations and the encoded short-range persistence forecast (background), accounting for their errors. The minimisation is performed in the reduced-order latent space, discovered by the VAE. The variational problem is auto-differentiable, simplifying the computation of the cost function gradient necessary for efficient minimisation. We demonstrate that the background-error covariance ($\mathbf{B}$) matrix measured and represented in the latent space is quasi-diagonal. The background-error covariances in the grid-point space are flow-dependent, evolving seasonally and depending on the current state of the atmosphere. Data assimilation experiments with a single temperature observation in the lower troposphere indicate that the $\mathbf{B}$-matrix simultaneously describes both tropical and extratropical background-error covariances.

physics.ao-ph↗