IBM and NASA Collaborate to Democratize Access to ai Technology for Climate Science with New Geospatial Foundation Model
To make advanced artificial intelligence (ai) technology more accessible for climate science, IBM and Hugging Face have announced the release of a new geospatial foundation model. This is the largest geospatial model on Hugging Face and marks the first-ever open-source ai foundation model developed in collaboration with NASA.
Promoting Collaboration and Driving Progress in Climate Science
Jeff Boudier, Head of Product and Growth at Hugging Face, emphasized the importance of information sharing and collaboration in driving progress in ai. He stated that open-source ai and the release of models and datasets are crucial to ensuring ai benefits as many people as possible.
Addressing Data Analysis Challenges in Climate Science
Climate science faces constant challenges due to rapidly changing environmental conditions, necessitating access to up-to-date data. Despite the abundance of available data, scientists and researchers often struggle to analyze vast datasets effectively. NASA estimates that by 2024, there will be 250,000 terabytes of data from new missions.
IBM and NASA Collaboration: Building an ai Foundation Model for Geospatial Data
To tackle this issue, IBM started collaborating with NASA earlier this year to build an ai foundation model for geospatial data. By making the geospatial foundation model openly available on Hugging Face, both companies aim to promote collaboration and accelerate progress in climate and Earth science.
Promising Results from the Geospatial Model
Sriram Raghavan, VP at IBM Research ai, reported that the geospatial model, jointly trained by IBM and NASA on satellite data (HLS) over one year across the continental United States, demonstrated a 15 percent improvement over state-of-the-art techniques using only half the labeled data.
Further Applications of the Geospatial Model
With further fine-tuning, the model can be adapted for various tasks such as deforestation tracking, crop yield prediction, and greenhouse gas detection.
NASA’s Initiative for Open Science and IBM’s Broader ai Modeling Efforts
IBM’s collaboration with NASA aligns with NASA’s decade-long initiative to promote a more accessible and inclusive scientific community. NASA, along with other federal agencies, has designated 2023 as the Year of Open Science, celebrating the benefits of sharing data, information, and knowledge openly.
Kevin Murphy, Chief Science Data Officer at NASA, stated that the geospatial model leverages IBM’s foundation model technology and is part of IBM’s broader initiative to create and train ai models with transferable capabilities across different tasks.
Scaling the Impact of Advanced ai with Trusted Data
In June, IBM introduced Pasa, an ai and data platform designed to scale and accelerate the impact of advanced ai with trusted data. A commercial version of the geospatial model integrated into IBM Watsonx will be available through the IBM Enterprise License Agreement (ELA) later this year.
Addressing Climate Challenges with Open-Source Technologies
By leveraging the power of open-source technologies, this latest collaboration aims to effectively address climate challenges and contribute to a more sustainable future for our planet.
Explore other upcoming enterprise technology events and webinars powered by TechForge
