NASA and IBM are collaborating to develop artificial intelligence (AI)-based models that will facilitate the mining of massive data sets to advance Earth science and help the world adapt to a changing environment.
The collaboration will apply AI-based model technology to NASA Earth observation satellite data for the first time, NASA said in a statement.
Basic models are types of AI models that are trained on a broad set of unlabeled data, can be used for a variety of tasks, and can apply information about one situation to another.
“The beauty of basic models is that they can potentially be used for many downstream applications,” said Rahul Ramachandran, senior research scientist at NASA’s Marshall Space Flight Center.
Read | Columbia disaster that sank the space shuttle
“Building these base models cannot be handled by small teams; you need teams in different organizations to bring their different perspectives, resources and skill sets,” Ramachandran said in a statement.
One project will train a fundamental IBM geospatial intelligence model on NASA’s Harmonized Landsat Sentinel-2 (HLS) dataset, a record of land cover and land-use change captured by satellites in Earth orbit, the statement said.
By analyzing satellite data to identify changes in the geographic footprint of phenomena such as natural disasters, crop yield cycles, and wildlife habitats, this modeling technology will help researchers provide critical analysis of our planet’s ecological systems.
Another outcome of this collaboration is expected to be an easily searchable corpus of Earth science literature.
IBM has developed a natural language processing (NLP) model trained on nearly 300,000 Earth science journal articles to organize the literature and facilitate the discovery of new knowledge, the company said.
In addition to providing a resource to researchers, the new Earth Science Language Model can be infused into NASA’s science data management and governance processes.
Add Comment