A new collaboration will see researchers use artificial intelligence (AI) technology developed by IBM to discover climate change insights in Nasa’s Earth science data.
Nasa and IBM have joined forces to promote a new application of artificial intelligence (AI) technology to Nasa Earth observation satellite data.
The two organisations have revealed their plans to develop several applications to extract insights from Earth observations about the impact of climate change.
In one of the projects, scientists will train an IBM geospatial intelligence foundation model on Nasa’s Harmonized Landsat Sentinel-2 dataset, a record of land cover and land use changes captured by Earth-orbiting satellites.
The AI is expected to analyse petabytes of satellite data to identify the impact of natural disasters and rising temperatures on crop yields, and wildlife habitats.
Meanwhile, another project is expected to be a large language model based on Earth science literature. IBM has developed an NLP model trained on nearly 300,000 Earth science journal articles to organise the literature and make it easier to discover new knowledge
“The beauty of foundation models is they can potentially be used for many downstream applications,” said Dr Rahul Ramachandran, one of the leaders of the project. “Building these foundation models cannot be tackled by small teams; you need teams across different organisations to bring their different perspectives, resources, and skill sets.”
Raghu Ganti, principal researcher at IBM, added, “Applying foundation models to geospatial, event-sequence, time-series, and other non-language factors within Earth science data could make enormously valuable insights and information suddenly available to a much wider group of researchers, businesses and citizens.
“Ultimately, it could facilitate a larger number of people working on some of our most pressing climate issues.”
For this effort, IBM will work with Nasa’s Interagency Implementation and Advanced Concepts Team (IMPACT). IMPACT is a component of Nasa’s Earth Science Data Systems Programme, charged with expanding the use of the agency’s Earth-observing data through innovation, partnerships, and technology.
Source: E&T
