INVESTMENT-GRADE HYPERLOCAL CLIMATE AND GRID SIMULATION
(click to expand)
UNPRECEDENTED ACCURACY
Sunairio’s weather and energy insights are built on a proprietary dataset of historical climate data that is downscaled to any coordinate and any height (from 2m to 300m).
Our data is generated using machine learning downscaling techniques that incorporate a mix of climate reanalysis, numerical weather prediction models, satellite information, and high-resolution topography.
The Sunairio climate dataset is rigorously validated, with measured accuracy that outperforms physics-based downscaling approaches. Contact us for validation documentation.
Our data is generated using machine learning downscaling techniques that incorporate a mix of climate reanalysis, numerical weather prediction models, satellite information, and high-resolution topography.
The Sunairio climate dataset is rigorously validated, with measured accuracy that outperforms physics-based downscaling approaches. Contact us for validation documentation.
COMPREHENSIVE APPROACH
This high-resolution historical weather data powers Sunairio’s forward-looking forecast technology, allowing us to generate high-resolution jointly-correlated ensembles of hourly weather. Our computationally-efficient weather generation technology uses next-generation algorithms to replicate ultra-high-dimensional structure and create large (1,000 path) ensembles of hourly weather patterns at seasonal to climate time scales.
Sunairio’s weather ensembles incorporate localized climate trends informed by a set of CMIP6 global climate models, giving our users state-of-the-art long-range weather modeling at temporal and spatial resolutions necessary for commercial power-market and grid-modeling applications.
In addition, we apply a mix of engineering, ML, and AI techniques to forecast a number of downstream energy resource outputs—including electricity demand, wind generation, solar generation, distributed energy resources, and others. These methods can integrate—but do not require—operational data, allowing customers to simulate pre-construction assets or changes to customer/load resources.
Sunairio’s weather ensembles incorporate localized climate trends informed by a set of CMIP6 global climate models, giving our users state-of-the-art long-range weather modeling at temporal and spatial resolutions necessary for commercial power-market and grid-modeling applications.
In addition, we apply a mix of engineering, ML, and AI techniques to forecast a number of downstream energy resource outputs—including electricity demand, wind generation, solar generation, distributed energy resources, and others. These methods can integrate—but do not require—operational data, allowing customers to simulate pre-construction assets or changes to customer/load resources.