NOAA Deploys New AI Driven Global Weather Models
NOAA has deployed a new set of operational AI driven global weather prediction models making a major advancement in forecast speed, efficiency, and accuracy while using fewer computing resources.
Key highlights include the Artificial Intelligence Global Forecast System (AIGFS), the Artificial Intelligence Global Ensemble Forecast System (AIGEFS), and the Hybrid Global Ensemble Forecast System (HGEFS). Together, these models support faster forecast delivery, improved tropical cyclone track guidance, and better representation of forecast uncertainty by combining AI and physics-based approaches.
These efforts stem from Project EAGLE (Experimental AI Global and Limited-area Ensemble), a multi-year collaboration across OAR, NWS, academia, and industry to advance NOAA’s operational weather prediction capabilities. EPIC is a key member of this collaboration through the provision of software infrastructure and community engagement support. Full details on model performance and technical background are available in the official NOAA announcement.
Successful Deployment of UFS Weather Modeling Capabilities to NOAA’s New High-Performance Supercomputing System, Ursa
The EPIC Code Management team has successfully developed and integrated a new automated Jenkins pipeline for unit testing code changes in the NOAA Physical Sciences Laboratory (PSL) Stochastic Physics repository. This pipeline streamlines the software development lifecycle by enabling Continuous Integration (CI), Continuous Delivery (CD), and Continuous Deployment (CD) through an efficient, automated process. By simply adding a GitHub label to a pull request, EPIC Code Managers can now trigger unit tests and seamlessly progress through the CI/CD pipeline.
Advancing Weather Prediction with AI: EPIC Short Course at AMS 2026
Artificial intelligence is rapidly becoming one of the most transformative tools in weather prediction, offering new ways to improve accuracy, efficiency, and scientific discovery. To help the research community explore these advances, NOAA’s Earth Prediction Innovation Center (EPIC) will host a dedicated short course at AMS 2026, focused on hands-on training with community-developed AI modeling tools. This workshop is designed not only to teach participants how to use cutting-edge AI models, but also to equip them with tools and techniques needed to continue innovating long after the session concludes.
Short Range Weather App Tutorial: Simulating the August 10 2020 Derecho
A new tutorial developed by Lapenta Intern, Rowin Smith, guides users through simulating the August 10, 2020 derecho using the SRW App. This step-by-step guide covers app installation, configuring multiple test cases, and using real-world weather data to generate forecasts.
AI innovations: Q&A with PSL’s Sergey Frolov on NOAA’s Project EAGLE
A team of experts in NOAA Research, the National Weather Service (NWS), and the Earth Prediction Innovation Center (EPIC) have recently unveiled Project EAGLE, a new experimental environment engineered to rapidly test and demonstrate Artificial Intelligence (AI) weather models in near-real time.
EPIC Advances NOAA’s Weather Modeling with Containerized Global Workflow
The EPIC Code Management team has successfully developed and integrated a new automated Jenkins pipeline for unit testing code changes in the NOAA Physical Sciences Laboratory (PSL) Stochastic Physics repository. This pipeline streamlines the software development lifecycle by enabling Continuous Integration (CI), Continuous Delivery (CD), and Continuous Deployment (CD) through an efficient, automated process. By simply adding a GitHub label to a pull request, EPIC Code Managers can now trigger unit tests and seamlessly progress through the CI/CD pipeline.
NWS Launches Warn-on-Forecast System Demonstration Project
Doing new and interesting science with the Unified Forecast System (UFS), or any numerical model, requires completing a similar series of basic steps. These steps are easy to define but can be challenging to execute, especially for platforms and environments that are very different from where the model was developed. Working in collaboration with our partners at NOAA Earth Prediction Innovation Center (EPIC) and Environmental Modeling Center (EMC), researchers at George Mason University have succeeded in implementing both the UFS and the EMC global-workflow on multiple community platforms. Our team is now in full production, making runs and analyzing data in support of the Seasonal Forecast System development effort.
DTC Announces Release of CCPP Single-Column Model v7.0.1 with Enhanced Capabilities and Documentation
Modeling is an essential component of NOAA’s services and capabilities value chain. The NOAA Modeling Strategy (2024) provides a 10-year framework to advance cutting-edge research, development, and operational implementation activities for all modeling that is foundational to NOAA’s science and service missions. This strategy positions NOAA to be the global leader in Earth System Modeling as set forth under the principles of the Earth Prediction Innovation Center (EPIC) and the Unified Forecast System (UFS) to implement open-source and community modeling approaches to increase collaboration with the broader community where possible.
New Idealized, Regional Tropical Cyclone Test Case Added to UFS Weather Model
Modeling is an essential component of NOAA’s services and capabilities value chain. The NOAA Modeling Strategy (2024) provides a 10-year framework to advance cutting-edge research, development, and operational implementation activities for all modeling that is foundational to NOAA’s science and service missions. This strategy positions NOAA to be the global leader in Earth System Modeling as set forth under the principles of the Earth Prediction Innovation Center (EPIC) and the Unified Forecast System (UFS) to implement open-source and community modeling approaches to increase collaboration with the broader community where possible.
Community Modeling on Community Platforms – One member’s perspective on the Unified Forecast System
Doing new and interesting science with the Unified Forecast System (UFS), or any numerical model, requires completing a similar series of basic steps. These steps are easy to define but can be challenging to execute, especially for platforms and environments that are very different from where the model was developed. Working in collaboration with our partners at NOAA Earth Prediction Innovation Center (EPIC) and Environmental Modeling Center (EMC), researchers at George Mason University have succeeded in implementing both the UFS and the EMC global-workflow on multiple community platforms. Our team is now in full production, making runs and analyzing data in support of the Seasonal Forecast System development effort.
