leverages AI to improve business forecast data by nearly 40%

LinkedIn +

Boston-based weather intelligence and climate adaptation platform has achieved significant advancements in its One Forecast (1F) Model by leveraging operational weather models and machine learning.

According to the company, after extensive tests and validation, the 1F Model’s forecast now provides up to 38% better data for supporting predictive business decisions than publicly available forecasts. The model upgrades will be implemented into’s weather intelligence platform during Q2.

The model incorporates a high-resolution, short-term forecasting system leveraging a unique combination of both machine learning and state-of-the-art numerical weather prediction (NWP) technology.’s 1F Model rapidly post-processes NWP weather data, reduces inaccuracies and quantifies the uncertainty in the weather forecast, thereby generating probabilistic predictions.

Luke Peffers, chief weather officer at, said, “Our next-generation 1F Model is a game-changer for businesses to better understand weather forecasts, make more informed decisions, and take actions to protect critical infrastructure or moving assets in advance of impact. We are pushing the boundaries of what can be reliably predicted through a combination of NWP models and machine learning, resulting in more accurate forecasts and probabilistic outputs that provide a significant advantage for our customers and enabling them to protect their assets and resources.”’s 1F Model is a multi-task neural network with a custom loss function that predicts seven key weather variables. In contrast to traditional neural networks that are typically trained to predict one output variable, multi-task neural networks are trained to optimize the performance of multiple output variables at the same time. This is ideal for predicting highly correlated weather variables that are related to the underlying weather phenomena. The model outputs 21 ensemble members, which are used to generate probabilities that can be used to drive better decision making.

Tyler McCandless, director of data science at, added, “We have demonstrated impressive results for the Contiguous United States (CONUS) model with improved forecast skill across key variables both from a deterministic and probabilistic model verification. Our deterministic model results show an improvement over the baseline High-Resolution Rapid Refresh (HRRR) model up to 12.5% in overall forecast lead times across CONUS, as quantified by the root mean square error (RMSE). Beyond the significant improvement in our deterministic model forecast skill, we also demonstrated a tremendous improvement in probabilistic forecasting with up to 38% improvement in our Continuous Ranked Probability Score (CRPS) metric.” @tomorrowio_

Share this story:

About Author

, editor-in-chief

Dan first joined UKi Media & Events in 2014 having spent the early years of his career in the recruitment industry. As editor, he now produces content for Meteorological Technology International, unearthing the latest technological advances and research methods for the publication of each exciting new issue. When he’s not reporting on the latest meteorological news, Dan can be found on the golf course or apprehensively planning his next DIY project.

Comments are closed.