Hybrid ensemble forecasting combining physics-based and machine-learning predictions through spectral nudging

TL;DR

This paper introduces a novel hybrid ensemble forecasting method that integrates physics-based models with machine learning predictions via spectral nudging, significantly enhancing large-scale forecast accuracy and tropical cyclone track predictions.

Contribution

It is the first to apply spectral nudging in a probabilistic ensemble framework, effectively combining physics-based and machine-learned forecasts for improved weather prediction.

Findings

Large-scale forecast skill improved up to two days in the tropics

Tropical cyclone track forecasts significantly enhanced

Near-surface parameters also benefited from the hybrid approach

Abstract

We present the first application of spectral nudging in a probabilistic ensemble forecasting framework, combining the physics-based ECMWF Integrated Forecasting System ensemble (IFS-ENS) with forecasts from the probabilistic machine-learned AIFS-ENS ensemble. Large scales of virtual temperature and vorticity are relaxed toward the machine-learned forecasts, while mesoscale structures remain governed by the physics-based model. This hybrid ensemble shows substantial improvements in large-scale forecast skill, with gains in predictive skill extended by up to two days in the tropics and by approximately half a day in the extra-tropics relative to IFS-ENS. Despite nudging being applied only to upper-air fields, improvements are also found in several near-surface parameters. Tropical cyclone track forecasts improve significantly, consistent with improved representation of the large-scale steering flow, without degrading storm intensity or ensemble spread. These results demonstrate that spectral nudging can be successfully extended to ensemble prediction and provide an attractive pathway for combining machine-learned and physics-based weather prediction systems.