Sunairio logo
High-tech energy control room

November 12, 2026

How the SHED and Sunairio ONE Solve the Power Sector’s Biggest Analytical Blind Spot

Energy traders, power producers, and grid planners rely heavily on time-series weather data to model the simultaneous, correlated variability between load spikes, renewable generation variability, and generator outage events. As recent weather-driven grid emergencies have starkly demonstrated — from Winter Storm Uri in Texas to extreme heatwaves in California — anticipating the impact of severe weather on wind, solar, and load is no longer optional — it is the defining challenge of modern energy management. 

However, a critical analytical blind spot has persisted: the industry has lacked a single, comprehensive weather dataset capable of accurately representing both long-run variability, historical extremes, and future climate realities.

That is changing. A recently published independent technical evaluation by the Electric Power Research Institute (EPRI) — conducted in partnership with energy supplier Constellation through the EPRI Incubatenergy Labs (IEL) program — validates that Sunairio’s historical and forward-looking datasets successfully address this functional gap, broadly matching or outperforming established industry benchmarks.

Here is a closer look at the industry data problem, how Sunairio solves it, and what the EPRI evaluation uncovered.

The Five Non-Negotiable Criteria for Weather Data in the Power Sector

To accurately capture correlated variability between energy load, wind generation, solar output, and market prices, grid planners and energy traders require data that satisfies five strict criteria:

  1. High Spatial Resolution: Data must be highly localized (3 km or less) to capture the unique microclimates of individual wind farms, solar arrays, and population centers.
  2. High Temporal Resolution: Hourly or sub-hourly data is required to model sudden ramps in solar and wind production or steep drops in temperature.
  3. Long Historical Duration: A minimum 20-year timespan is necessary to capture natural, multi-decadal weather variability and rare tail events.
  4. Physical Consistency: Variables like temperature, wind speed, irradiance, and humidity must be physically consistent with one another at any given time to accurately model complex joint extremes (e.g., high heat combined with low wind).
  5. Forward-Looking Climate Trends: Because the climate is non-stationary, historical data alone is no longer sufficient; models must capture projected shifts in extreme weather frequencies and baseline distributional changes.

For years, traditional industry-standard weather datasets have forced market participants to compromise. Analysts routinely have to stitch together multiple unrelated datasets for specific weather variables, sacrificing either temporal depth, spatial resolution, or the inclusion of forward-looking climate projections.

Consider a common real-world example: Most grid planning studies in the U.S. have traditionally relied on the National Renewable Energy Laboratory’s (NREL) WIND Toolkit. While excellent in resolution, it is only a seven-year dataset spanning 2007 to 2013. Relying on a seven-year slice of history provides a severely limited view of wind generation resource risk, completely missing cyclical weather patterns and recent extreme events.

Sunairio’s Data: Unifying the Past and the Future

Sunairio bridges this persistent analytical gap by unifying two proprietary datasets to provide a comprehensive, continuously updated, high-spatiotemporal resolution solution.

  • The SHED (Sunairio High-resolution Earth Data): Sunairio’s high-resolution historical weather dataset. It offers deep temporal history (dating back to 1950 for wind and temperature, and 1998 for irradiance) coupled with high 2-km spatial resolution and hourly intervals.
  • Sunairio ONE: Trained on the SHED, Sunairio ONE is a calibrated, high-resolution, long-range weather forecast ensemble. It blends short, medium, and seasonal forecast insights with a 1,000-member ML-statistical ensemble that explicitly models non-stationary climate trends out to 2050.

Together, these tools act as the foundational intelligence for Sunairio’s next-generation grid forecasting platform. By utilizing SHED and Sunairio ONE, utilities, independent power producers, battery energy storage system (BESS) operators, and virtual power plant (VPP) operators can quantify a full spectrum of weather risk over long time horizons. Instead of relying on static slices of history that ignore climate trends, asset managers can stress-test their portfolios against realistic, climate-adjusted future extremes.

Inside the EPRI Evaluation Scope

To quantify exactly how effective the Sunairio data is, EPRI conducted an independent, multi-location evaluation of accuracy and physical realism. EPRI measured Sunairio's temperature, wind speed, and irradiance performance directly against public gold-standard datasets across more than 50 locations in the contiguous United States.

The public datasets used as benchmarks included:

  • ECMWF’s ERA5 (Reanalysis)
  • NREL’s WIND Toolkit (WTK)
  • NREL’s National Solar Radiation Database (NSRDB)

The analysis evaluated performance across 37 major load centers, 12 tall tower sites (for hub-height wind speeds), and 15 SURFRAD/SOLRAD observation sites.

Key Results: Superior Historical Accuracy (SHED)

Because historical data can be compared directly to actual observations, EPRI evaluated the SHED based on its objective accuracy, looking at metrics like Mean Absolute Error (MAE), root mean square error (RMSE), correlation, and bias.

Across these evaluated metrics, Sunairio’s historical data demonstrated performance that was comparable to, or explicitly improved over the public benchmarks:

  • Temperature (vs. ERA5): The SHED produced a lower MAE than ERA5 across 24 of the 37 evaluated load centers. Furthermore, SHED demonstrated significant improvements, yielding a higher hourly temperature correlation than ERA5 across nearly all tested sites.
  • Hub-Height Wind (vs. WTK and ERA5): Evaluating wind at the hub-height of modern turbines is notoriously difficult. Sunairio’s SHED performed as well as or better than both ERA5 and the WTK in eight out of nine analyzed metrics—including MAE, distribution realism, and correlation—during critical operating conditions for wind turbines.
  • Solar Irradiance (vs. NSRDB): The SHED produced a lower mean bias and a more realistic overall distribution of Global Horizontal Irradiance (GHI) than the leading public alternative, the NSRDB. Furthermore, SHED provides a continuously updated dataset, whereas NSRDB is typically only updated on an annual basis, ensuring traders and operators always have access to the latest data.

Key Results: Advanced Physical Realism (Sunairio ONE)

Because forward-looking ensembles simulate the future, they cannot be validated against observed reality. Instead, EPRI evaluated Sunairio ONE based on its "physical realism" — its ability to accurately represent the relative frequency and magnitude of hazards, the temporal characteristics of volatility, and its alignment with expected long-term climate trends.

  • Temperature Volatility and Hazards: Sunairio ONE matched or outperformed ERA5 on 92% of temperature physical realism metrics. Crucially, the volatility ratio—which is essential for accurately capturing temperature ramp rates that drive sudden load spikes—aligned more closely with observations in Sunairio ONE than in ERA5.
  • Climate Trends: Sunairio ONE successfully captured non-stationary climate warming. Forward projections showed extreme heat events increasing in frequency and cold events generally decreasing, aligning in direction and magnitude closely with current peer-reviewed climate science.
  • Wind and Solar Dynamics: Sunairio ONE outperformed ERA5 and WTK in representing diurnal and monthly cycles, as well as short-term daily ramp rates. For solar, it achieved the lowest overall mean bias for GHI among all evaluated datasets.

As with any rigorous scientific evaluation, the study also noted specific areas for continued refinement. For example, EPRI noted that while Sunairio ONE excels at daily wind variance, ERA5 remains slightly better at capturing synoptic-scale (multi-day) wind variance. Additionally, refining low-wind tail event representations remains a focus for future iterations, ensuring that the highest-impact resource adequacy risks are flawlessly modeled.

Beyond Grid Planning: Training the Next Generation of AI Weather Models

While resource adequacy and investment planning are critical applications for Sunairio’s datasets, the implications of SHED extend much further—specifically into the rapidly evolving field of artificial intelligence. Today, almost all of the world's leading AI weather models are trained on ERA5 data. While ERA5 is a powerful global reanalysis tool, its spatial resolution is fundamentally limited to approximately 30 kilometers. This bottleneck forces AI models to learn from smoothed, generalized historical data, restricting their ability to forecast highly localized weather phenomena, coastal dynamics, or complex terrain effects with precision.

SHED offers a groundbreaking alternative for AI development by providing a unified training dataset at 100 times the spatial resolution of ERA5. By training on SHED’s 2-kilometer, hourly historical data, meteorologists and data scientists can teach neural networks to recognize complex, highly localized atmospheric patterns that 30-kilometer grids completely miss. This massive upgrade in training data fidelity paves the way for a new class of ultra-high-resolution AI weather forecasts, capable of delivering the hyper-local accuracy required for tomorrow's energy grids and financial markets.

Stop Guessing. Start Planning with Confidence.

The EPRI evaluation provides independent validation of what our partners already know: you no longer have to compromise on your weather and climate data.

  • Read the Data: The complete technical report, Evaluation of Sunairio High-Resolution Earth Data (SHED) and Sunairio ONE Climate Forecast Ensemble, is available to download for free on the EPRI website.
  • See It in Action: To learn more about how Sunairio’s climate-informed datasets can integrate directly into your organization's resource adequacy or commercial trading models, schedule a demonstration today or contact our team directly at info@sunairio.com.