Medium-range weather forecasting underpins operational and planning decisions across the energy industry. Developing competitive weather models was once the domain of national meteorological centers, but recent advances in machine-learned weather prediction (MLWP) have opened the field to industry. We present Aries, a SwinTransformer-based MLWP model developed at InCommodities. Aries is trained on ERA5 reanalysis data at 0.25\textdegree{} resolution, predicting 74 prognostic and 11 diagnostic atmospheric variables. We evaluate the model on 2025 ECMWF Analysis initializations, ensuring a recent and strictly out-of-sample test period for all models compared. On 10-metre wind speed, Aries outperforms both ECMWF HRES and AIFS in terms of RMSE for lead times up to four days, while on 2-metre temperature it achieves RMSE on par with AIFS operational. These results demonstrate that proprietary development of competitive weather models is technically viable, supporting a broader set of forecasts available for operational and planning applications in the energy industry.
Figures & tables
Fig. 1: Latitude-weighted RMSE of 10 m wind speed forecasts over Europe for operational 2025 runs with — Aries, — AIFS, and — HRES against ERA5. Shaded regions denote 25th–75th percentile ranges.
Parameter
Value
Depth
14 layers
Attention heads
16
Embedding dimension
3,584
Total parameters
2.4 B
TABLE I: Aries model configuration.
Fig. 2: Latitude-weighted RMSE (top) and bias (bottom). Left: 10 m wind speed, USA. Middle: 2 m temperature, Europe. Right: 2 m temperature, USA. Shaded regions denote 25th–75th percentile ranges. — Aries, — ECMWF AIFS, — ECMWF HRES.
Fig. 3: Global Aries 2 m temperature forecasts at 24, 72, 96, and 120 h lead time.
Fig. 4: Global Aries 10 m wind speed forecasts at 24, 72, 96, and 120 h lead time.
Fig. 5: 2 m temperature forecasts over Europe at 24, 72, 96, and 120 h lead time (rows) for Aries, AIFS, HRES, and ERA5 (columns). ERA5 is the ground-truth reanalysis.
Fig. 6: 10 m wind speed forecasts over Europe at 24, 72, 96, and 120 h lead time (rows) for Aries, AIFS, HRES, and ERA5 (columns). The 72 and 96 h panels capture Storm Éowyn over the British Isles and the North Sea. ERA5 is the ground-truth reanalysis.
Fig. 7: Time series of 2 m temperature forecasts at the Horns Rev offshore wind farm, Denmark ( 55.5∘ N, 7.8∘ E) over the 0–168 h horizon. Point values are bilinearly interpolated from each model’s native grid to the site; Aries and AIFS are output at 6-hourly steps, HRES and ERA5 at hourly steps, and the curves are interpolated between steps with an Akima spline. — Aries, — AIFS, — HRES, - - ERA5 (ground truth).
Fig. 8: Time series of 10 m wind speed forecasts at the Horns Rev offshore wind farm, Denmark ( 55.5∘ N, 7.8∘ E) over the 0–168 h horizon. The wind maximum around day 3.5 corresponds to the passage of Storm Éowyn. Point values are bilinearly interpolated from each model’s native grid to the site; Aries and AIFS are output at 6-hourly steps, HRES and ERA5 at hourly steps, and the curves are interpolated between steps with an Akima spline. — Aries, — AIFS, — HRES, - - ERA5 (ground truth).
Weather forecasting predicts future atmospheric conditions, from local storms to global patterns, using physical models, observations, and machine learning.
State-of-the-art medium-range AI weather models can outperform traditional Numerical Weather Prediction (NWP) but require massive training budgets. This restricts usage for under-resourced groups and severely limits fast model iteration. Here we develop Otter Weather, a highly efficient spatiotemporal forecasting model designed to democratise high-performance weather prediction with AI. Evaluated on ERA5 reanalysis data at 1.5° resolution using standard WeatherBench protocols, the Otter family significantly advances the skill-compute Pareto frontier. The deterministic version outperforms the best NWP baseline by 9.6% at a 24-hour lead time while requiring fewer than 3.5 A100-days for training. It provides a 2x efficiency gain over lightweight AI models and a 100-fold reduction in compute compared to resource-intensive frontier architectures. We extend these efficiency gains into probabilistic forecasting by training via the Continuous Ranked Probability Score (CRPS). Scaling to a larger architecture, Otter-XL achieves a 9.7% CRPS improvement over the IFS ENS baseline. This yields an almost two-fold increase in predictive skill over comparable lightweight models at similar compute budgets. Otter-XL also outperforms frontier architectures like GenCast by over 2%, while using an order of magnitude less compute. Finally, Otter is applied out-of-the-box to a complex acoustic scattering PDE task where it outperforms a state-of-the-art foundation modelling approach, suggesting that the advances made here might apply across a range of scientific domains.
Cristiana Diaconu, Jonas Scholz, Aliaksandra Shysheya +4
Data-driven models now rival numerical weather prediction in the medium range, but extending them to sub-seasonal lead times raises challenges absent at shorter horizons. Errors accumulate over long autoregressive rollouts, systematic biases grow with lead time, and several years of data must be held out for independent verification, even though machine-learning models otherwise benefit from longer training records. To address these challenges, we adapt ECMWF's AIFS-CRPS medium-range model. AIFS-SUBS adopts a 24h autoregressive time step to reduce error accumulation, adds stratospheric levels and top-of-atmosphere thermal radiation as predictors, and reserves 2007--2011 as an independent verification window. We evaluate two config-durations: AIFS-SUBS, fine-tuned on operational analyses, and AIFS-SUBS-ERA5, trained on ERA5 alone. Across weeks 2--6, AIFS-SUBS matches the operational Integrated Forecasting System (IFS) in probabilistic skill while reducing systematic biases. For the convective (OLR) component of the Madden--Julian Oscillation (MJO), AIFS-SUBS extends skilful forecasts (correlation > 0.5) by eight days relative to the IFS, while matching or exceeding the IFS for the full multivariate RMM index. AIFS-SUBS also reproduces the observed MJO modulation of tropical cyclone activity comparably. Stratospheric skill is particularly strong with AIFS-SUBS reproducing sudden stratospheric warming (SSW) frequency and surface impact. In the AI Weather Quest, AIFS-SUBS-ERA5 attains a variable-averaged ranked probability skill score slightly ahead of the IFS at weeks 3 and 4. At inference, AIFS-SUBS uses about 200 times less energy than the IFS, opening the door to much larger real-time ensembles. AIFS-SUBS is ECMWF's first machine-learning model targeted at sub-seasonal time-scales.
Jakob Schloer, Steffen Tietsche, Christopher D. Roberts +6
1European Centre for Medium-Range Weather Forecasts (ECMWF)
Machine learning weather prediction (MLWP) models have achieved impressive forecasting performance at a small fraction of the computational costs required for traditional physics-based methods. However, they are primarily (1) data-driven and (2) evaluated using pixel-wide error metrics (e.g., RMSE), so there are no guarantees that their forecasts are consistent with known physical laws. We introduce PhysMetrics.Weather, an evaluation framework that assesses the physical realism of MLWP models across three types of metrics: conservation, spectral, and dynamical. By quantifying physical realism, this tool guides the development of physics-informed architectures and helps evaluate whether MLWP models are reliable for operational use. Our framework is available on Github at https://github.com/Emmakast/PhysMetrics.Weather.
Emma Kasteleyn, Timo Maier, Axel Lauer +3
University of Amsterdam, Amsterdam, The Netherlands · Deutsches Zentrum für Luft- und Raumfahrt (DLR), Institut für Physik der Atmosphäre, Oberpfaffenhofen, Germany · University of Bremen, Institute of Environmental Physics (IUP), Bremen, Germany +1