At the forefront of this advancement is Aurora, an innovative AI-driven forecasting system meticulously developed to operate at an unprecedented spatial resolution of approximately 0.1° in mid-latitudes. This resolution is comparable to the high-resolution configuration of the Integrated Forecasting System (IFS) known as HRES, which currently represents the gold standard in numerical weather prediction with its Gaussian grid (TCo1279) framework. By matching this granularity, Aurora confronts the limitations that have historically relegated AI weather models to coarser scales, predominantly 0.25°, dictated by data availability and computational feasibility.

The significance of operating at a finer resolution cannot be overstated. Weather phenomena such as convective storms, boundary layer processes, and other mesoscale dynamics unfold at spatial scales that are poorly resolved at coarser grids. Capturing these features with fidelity is crucial for accurately forecasting high-impact weather events, including severe storms and rapid atmospheric changes. Aurora’s capacity to work directly with 0.1° resolution data, which has only become accessible since 2016, illustrates a leap forward beyond previous AI systems tethered to more abundant but less detailed datasets.

Achieving this feat required employing a novel pretraining–fine-tuning protocol. Initially, Aurora was pretrained on extensive datasets at coarser resolutions to learn generalized atmospheric representations robustly. It was then fine-tuned on the relatively newer high-resolution IFS HRES analysis data spanning from 2016 to 2022. This approach harnesses the strengths of both data regimes, enabling Aurora to efficiently adapt to finer scales without necessitating prohibitively large volumes of high-resolution data for training from scratch. The result is a model that surpasses the forecasting skill of the operational IFS HRES when evaluated under established protocols.

Evaluation of Aurora’s performance reveals compelling advantages. When measured against the root mean squared error (RMSE) across a comprehensive set of meteorological target variables, pressure levels, and forecast lead times, Aurora outperforms IFS HRES in over 92% of comparisons. This superiority becomes especially pronounced beyond the 12-hour lead time mark, with RMSE reductions reaching up to 24%. Such improvements signal enhanced reliability in medium- to long-range forecasts, a critical window for disaster preparedness and mitigation efforts.

Interestingly, at the shortest lead times, classical numerical methods represented by IFS HRES maintain an edge, a pattern consistent with other contemporary AI forecasting models. This disparity underscores the complementary nature of traditional and AI-based predictive approaches, with AI models delivering significant enhancements as forecast horizons extend. The interplay between model types may pave the way for hybrid systems that exploit the strengths of each methodology.

To further validate Aurora’s real-world applicability, researchers conducted extensive evaluations using the WeatherReal-ISD dataset, a rich compilation of in situ measurements from over 13,000 weather observation stations worldwide. These assessments focused on key surface variables—10-meter wind speed and 2-meter air temperature—across forecast lead times extending up to 10 days. Aurora consistently outperformed IFS HRES in reducing forecast error across this entire range, indicating robust skill in capturing surface atmospheric phenomena crucial for everyday weather impacts.

The case for pretraining is further reinforced by quantitative analyses demonstrating that models trained with a pretraining stage hold a 25% performance advantage over those trained from scratch using only high-resolution data. This finding emphasizes the value of leveraging historical, abundant datasets to bootstrap learning before specializing in new, high-resolution regimes with sparser data availability.

The practical strengths of Aurora are vividly illustrated in a detailed case study of Storm Ciarán, a powerful mid-latitude storm that swept across Northwest Europe in late 2023. The storm generated record-breaking low pressure readings in England during November, raising significant forecasting challenges. When initialized at 31 October 00 UTC, comparisons among several AI models highlighted Aurora as uniquely capable of capturing the abrupt surge in maximum 10-meter wind speeds, closely aligning with the ground truth provided by the IFS analysis. Other AI models, including FourCastNet, GraphCast, and Pangu-Weather, notably failed to reproduce this rapid intensification.

This breakthrough not only demonstrates Aurora’s superior predictive skill but also underscores the crucial role of spatial resolution and methodological innovations in capturing extreme weather dynamics. The accurate representation of such rapid and localized phenomena is vital for issuing warnings and protecting communities from the devastating impacts of severe storms and other high-impact weather events.

Methodologically, it is worth noting that for the Storm Ciarán predictions, Aurora was run without Low-Rank Adaptation (LoRA), a model compression technique often employed to reduce computational costs. This decision was aimed at maximizing the model’s sensitivity to extreme event dynamics, highlighting the flexibility embedded in Aurora’s design to balance efficiency and precision based on situational requirements.

The success of Aurora, a foundation AI model for the Earth system, signals a new era in atmospheric science where machine learning models are not merely complementary but can supersede traditional forecasting systems in accuracy and temporal reach. By bridging the data and resolution gap that has long hindered AI weather prediction, this approach unlocks latent capacity for more reliable, higher fidelity forecasts.

Looking ahead, the integration of such foundation models promises transformative impacts across sectors reliant on weather information—from disaster risk management and agriculture to renewable energy and transportation. As data acquisition systems continue to improve and resolutions increase, the potential for AI systems like Aurora to leverage ever more granular observations will only grow, leading to smarter, faster, and more actionable weather forecasts worldwide.

In conclusion, Aurora’s demonstrated capabilities exemplify a pivotal step towards realizing the vision of foundation models that encapsulate the complex, multiscale intricacies of the Earth system. Through innovative training protocols and leveraging advances in data availability, Aurora establishes a new benchmark for operational weather prediction, fostering optimism for future developments at the nexus of atmospheric science and artificial intelligence.

Subject of Research:
Development and evaluation of a high-resolution AI-based weather forecasting model (Aurora) designed to surpass state-of-the-art numerical weather prediction systems.

Article Title:
A foundation model for the Earth system

Article References:
Bodnar, C., Bruinsma, W.P., Lucic, A. et al. A foundation model for the Earth system. Nature (2025). https://doi.org/10.1038/s41586-025-09005-y

Image Credits:
AI Generated

Heatwaves, characterized by prolonged spells of extreme temperatures, impose severe stresses on human health, energy infrastructure, agriculture, and ecosystems. Despite their increasing frequency and severity under climate change, the spatial and temporal development of heatwaves remains incompletely understood. Traditional approaches often emphasize local meteorological conditions or climate anomalies, but this new research pivots toward the large-scale atmospheric circulation patterns that govern the behavior of weather extremes across vast regions and timescales.

At the heart of the study lies the Rossby wave—a vast undulating atmospheric wave pattern caused by Earth’s rotation and the temperature gradients between polar and equatorial regions. These waves modulate jet streams and pressure systems, controlling weather progression across the globe. While Rossby waves have long been implicated in extreme weather, the novel finding here establishes that they also generate “preferred corridors” along which heatwaves propagate more consistently, influencing not only their genesis but also their geographic reach and persistence.

Using an innovative combination of observational data spanning multiple decades and cutting-edge atmospheric modeling, the authors identify recurrent heatwave pathways tightly correlated with Rossby wave patterns. They demonstrate that these pathways are far from random, instead reflecting intrinsic dynamical constraints in the Earth’s atmospheric circulation. This insight marks a paradigm shift, allowing meteorologists to anticipate not just localized heat events but larger-scale, connected heatwave episodes that traverse continents.

The researchers employed comprehensive reanalysis datasets of atmospheric variables including temperature, pressure, and wind fields. They applied sophisticated statistical techniques to isolate heatwave occurrences and examine their spatial-temporal coherence with Rossby wave activity. A series of sensitivity tests and model simulations further confirmed that the Rossby wave structures act as steering mechanisms, channeling heatwave development along specific routes over land masses such as North America and Eurasia.

One of the most striking outcomes is the identification of key “Rossby wave corridors” where heatwaves initiate and propagate with significantly elevated probability. These corridors tend to coincide with regions of persistent atmospheric blocking—quasi-stationary pressure systems that stall weather patterns. Such blocking events amplify heatwave intensity and duration by promoting stagnant conditions that trap hot air masses. The interaction between Rossby wave train patterns and these blocks creates a feedback loop that reinforces heat extremes systematically.

Moreover, the study elucidates how these pathways fluctuate with seasonal and interannual climate variability. For instance, shifts in the jet stream and Rossby wave amplitudes linked to phenomena like the Arctic Oscillation or El Niño/Southern Oscillation can modulate the likelihood and trajectories of heatwaves. This coupling suggests new avenues for sub-seasonal to seasonal forecasting of heatwaves by monitoring Rossby wave evolution and associated atmospheric states, potentially enhancing early warning systems.

Importantly, the mechanistic connection uncovered challenges prior assumptions that heatwave propagation was primarily due to localized warming and stationary atmospheric features. Instead, the work highlights that the dynamic large-scale wave teleconnections serve as the organizing principle, imprinting a coherent spatial fingerprint on heatwave events. This insight holds implications for climate modeling, which must adequately capture Rossby wave dynamics to realistically simulate future heatwave risks.

The physical explanation for Rossby-wave-guided heatwave pathways resides in the thermal wind balance and upper-level jet dynamics. Rossby waves manifest as meanders in the jet stream, whose position and amplitude control the advection of warm or cold air masses. When the wave troughs and ridges align to produce prolonged ridges—high-pressure zones—surface heating intensifies and becomes entrenched, fostering conditions favorable for heatwave onset and sustainment. Thus, the wave pattern dictates where hot air is funneled and trapped over land.

This research exemplifies interdisciplinary collaboration by integrating dynamical meteorology, climatology, and atmospheric physics to solve a longstanding puzzle related to extreme weather propagation. The findings carry profound societal relevance, as heatwaves constitute one of the deadliest natural hazards worldwide. By enhancing our capacity to decipher and predict their pathways, emergency response and public health preparedness can be better optimized, ultimately saving lives and mitigating economic losses.

In the broader context of a warming planet, the role of Rossby waves may intensify further. Climate change alters temperature gradients and jet stream behavior, potentially modifying the occurrence and intensity of Rossby wave patterns. This raises critical questions about future heatwave pathways and their evolving spatial patterns, necessitating continuous monitoring and improved dynamic climate modeling frameworks that incorporate these interactions at a granular level.

Furthermore, this study opens new possibilities for exploring teleconnected extremes beyond heatwaves. Given that Rossby waves also influence floods, droughts, and storms, the principle of preferred propagation pathways could extend to a wider range of atmospheric phenomena. Understanding these wave-guided connections may therefore be pivotal in unraveling the complex web of compound climate extremes, offering a more integrated perspective on global climate risks.

In summary, the landmark work by Wang and colleagues advances climate science by revealing that Rossby wave dynamics act as the invisible highways guiding terrestrial heatwaves. Their research offers not only novel theoretical insights but also practical implications for improved forecasting and adaptation strategies under a rapidly changing climate. As the global community confronts the escalating challenge of extreme heat, such scientific breakthroughs provide crucial tools to predict and manage the impacts of these destructive natural events more effectively.

The implications of this research extend into numerous domains including urban planning, agriculture, energy management, and public health, where anticipating heatwave timing and pathways enables targeted interventions and resource optimization. By harnessing the predictability embedded in atmospheric Rossby wave patterns, weather services can deliver more actionable heatwave warnings, mitigating adverse effects on vulnerable populations.

Looking forward, the integration of this newfound knowledge into operational forecasting models represents a promising frontier. Incorporating Rossby wave activity and its coupling with terrestrial heatwaves could refine ensemble forecasting skill, increasing confidence in the timing and spatial extent of extreme heat episodes days to weeks in advance. This improved lead time is essential for proactive disaster risk management amid intensifying climate extremes.

In essence, this pioneering study illuminates a hidden order in chaotic heatwave behavior, transforming our conceptual framework regarding how heatwaves emerge and evolve across continents. By linking the macroscopic atmospheric circulation features embodied in Rossby waves to localized heat extremes, it bridges scales in the climate system, fostering a deeper mechanistic understanding with tangible societal benefit.

Subject of Research: Rossby wave dynamics and their influence on terrestrial heatwave propagation pathways

Article Title: Evidence for preferred propagating terrestrial heatwave pathways due to Rossby wave activity

Article References:
Wang, M., Huang, Y., Franzke, C.L.E. et al. Evidence for preferred propagating terrestrial heatwave pathways due to Rossby wave activity. Nat Commun 16, 4742 (2025). https://doi.org/10.1038/s41467-025-60104-w

Image Credits: AI Generated