IBM has unveiled a groundbreaking AI foundation model designed to revolutionize the way we analyze and understand weather and climate data. Developed in partnership with NASA and contributions from Oak Ridge National Laboratory, this open-source model, named ‘Prithvi WxC’, empowers scientists, developers, and businesses with unprecedented insights.
Prithvi WxC transcends the limitations of existing weather AI models by offering a flexible and scalable approach to tackling a wide range of challenges, from short-term weather forecasts to long-term climate projections. Its unique design and training regime allow it to tackle applications far beyond traditional weather forecasting, as detailed in a recent arXiv paper titled “Prithvi WxC: Foundation Model for Weather and Climate.”
Among its potential applications, Prithvi WxC excels in creating targeted forecasts based on local observations, detecting and predicting severe weather patterns, enhancing the spatial resolution of global climate simulations, and improving the representation of physical processes in numerical weather and climate models.
One remarkable experiment showcased in the aforementioned paper demonstrated the model’s ability to accurately reconstruct global surface temperatures using a mere 5% of the original data. This capability hints at broader applications in data assimilation.
Trained on 40 years of Earth observation data from NASA’s MERRA-2 (Modern-Era Retrospective analysis for Research and Applications, Version 2), Prithvi WxC distinguishes itself as a foundation model with a unique architecture. This architecture enables fine-tuning for global, regional, and local scales, making it adaptable for a wide spectrum of weather studies.
The model is readily available for download on Hugging Face, accompanied by two fine-tuned versions tailored to specific scientific and industry-relevant applications.
One fine-tuned version focuses on “Climate and weather data downscaling.” Downscaling, a common meteorological practice, involves inferring high-resolution outputs from low-resolution data. The model can depict both weather and climate data at up to 12x resolution, generating localized forecasts and climate projections. This fine-tuned downscaling model is accessible on the IBM Granite page on Hugging Face.
The second fine-tuned version addresses “Gravity wave parameterization.” Gravity waves, ubiquitous throughout the atmosphere, significantly influence various atmospheric processes related to climate and weather, such as cloud formation and aircraft turbulence. Traditional numerical climate models have struggled to capture these waves accurately, leading to uncertainties in understanding their impact on climate processes. Prithvi WxC empowers scientists with the ability to better estimate gravity wave generation, thereby improving the accuracy of numerical weather and climate models and reducing uncertainties when simulating future weather and climate events. This gravity wave parameterization model is being released as part of the NASA-IBM Prithvi family of models on Hugging Face.
“Advancing NASA’s Earth science for the benefit of humanity means delivering actionable science in ways that are useful to people, organizations, and communities. The rapid changes we’re witnessing on our home planet demand this strategy to meet the urgency of the moment,” said Karen St. Germain, director of the Earth Science Division of NASA’s Science Mission Directorate. “The NASA foundation model will help us produce a tool that people can use: weather, seasonal, and climate projections to help inform decisions on how to prepare, respond, and mitigate.”
“This space has seen the emergence of large AI models that focus on a fixed dataset and single use case — primarily forecasting. We have designed our weather and climate foundation model to go beyond such limitations so that it can be tuned to a variety of inputs and uses,” said Juan Bernabe-Moreno, Director of IBM Research Europe and IBM’s Accelerated Discovery Lead for Climate and Sustainability. “For example, the model can run both on the entire earth as well as in a local context. With such flexibility on the technology side, this model is well-suited to help us understand meteorological phenomena such as hurricanes or atmospheric rivers, reason about future potential climate risks by increasing the resolution of climate models, and finally inform our understanding of imminent severe weather events.”
“As a premier research institution and computing facility, we’re focused on supporting teams to make research breakthroughs across many areas of science,” said Arjun Shankar, director of the National Center for Computational Sciences at Oak Ridge National Laboratory. “Our collaboration with IBM and NASA to support the creation of the Prithvi weather and climate foundation model was a key part of our goal to bring advanced computing and data to problems of national importance, in this case, for weather and climate applications, which need continued computational science and model skill improvements to be impactful.”
IBM has already teamed up with Environment and Climate Change Canada (ECCC) to explore the model’s versatility with additional weather forecasting use cases. ECCC is leveraging the model to investigate very short-term precipitation forecasts using a technique called precipitation nowcasting, which incorporates real-time radar data. The team is also testing the downscaling approach, transforming global model forecasts at 15 km resolution to a more localized km-scale.
This weather and climate model represents a significant milestone in the ongoing collaboration between IBM Research and NASA to harness AI technology for exploring our planet. It joins the Prithvi family of AI foundation models, further expanding its capabilities. In 2023, IBM and NASA introduced the Prithvi geospatial AI foundation model, the largest open-source geospatial AI model available on Hugging Face. This model has been embraced by governments, companies, and public institutions for analyzing changes in disaster patterns, biodiversity, land use, and other geophysical processes.
The foundation model and the gravity wave parameterization model are accessible through the NASA-IBM Hugging Face page, while the downscaling model can be accessed through the IBM Granite Hugging Face page.
IBM stands as a global leader in hybrid cloud and AI, providing consulting expertise to clients in over 175 countries. Their mission is to empower clients to leverage insights from their data, optimize business processes, reduce costs, and gain a competitive edge in their respective industries.
Thousands of governments and corporations in critical infrastructure sectors, including financial services, telecommunications, and healthcare, rely on IBM’s hybrid cloud platform and Red Hat OpenShift to accelerate their digital transformations securely and efficiently. IBM’s dedication to innovation, evident in their breakthroughs in AI, quantum computing, industry-specific cloud solutions, and consulting, delivers open and flexible options to their clients. This commitment is further solidified by IBM’s steadfast dedication to trust, transparency, responsibility, inclusivity, and service.
