Rocket City has always been at the forefront of the world’s efforts of leaving the earth for outer space, and soon it will soon be at the forefront of saving the earth from impacts of climate change as well.

On Wednesday, IBM Research and NASA’s Marshall Space Flight Center announced they are starting development on AI foundation models for NASA’s earth science satellite data. This AI foundation model will allow for NASA’s Earth-observing satellite to analyze geospatial satellite data more quickly and more efficiently in an effort to combat climate change.

Simply put, foundation models are specific AI models used to train on large sets of unlabeled data and apply one situation to another. Currently, half of all scientific findings come from archived data and this makes it challenging for researchers to study ever-evolving threats such as climate change.

Rahul Ramachandran, senior research scientist at NASA’s Marshall Space Flight Center in Huntsville, Alabama, highlighted this challenge during a press briefing on Tuesday as he explained that NASA’s collection of Earth observation data contains 70 petabytes of data and is expected to grow to more than 250 petabytes within a few years.

“Clearly, given the scale of the data that we have, we have a big data problem,” Ramachandran said. “Our goal is to make our data discoverable, accessible and usable for broad scientific use in applications worldwide.”

Ramachandran added the development of new foundation models will make it easier to analyze and draw benefits from the data that NASA has collected. In the examples he used, foundation models using satellite image data could potentially automatically map out flooding data or damage in a hurricane zone instead of researchers having to pour through that same data for the same information.

IBM’s foundation model technology, will aim to vastly speed up the categorization and analysis of incoming data. The goal of this joint project is to advance the scientific understanding of and response to Earth and climate-related issues like natural disasters and warming temperatures.

There are two new models being developed that will aid in this effort:

The first model will be trained on over 300,000 earth science publications to thematically organize the literature and make it easier to search and discover new knowledge.
The second model will be trained on USGS and NASA’s popular Harmonized Landset-Sentinel2 (HLS2) satellite dataset; applications include everything from detecting natural hazards to tracking changes in vegetation and wildlife habitats.

One model will train an IBM geospatial intelligence foundation model on NASA’s Harmonized Landset-Sentinel-2 (HLS) dataset, a record of land cover and land use changes captured by Earth-orbiting satellites.

By analyzing petabytes of satellite data to identify changes in the geographic footprint of phenomena such as natural disasters, cyclical crop yields, and wildlife habitats, this foundation model technology will help researchers provide critical analysis of our planet’s environmental systems.

The other model will develop an easily searchable databank of Earth science literature.

IBM has is using an NLP model trained on nearly 300,000 Earth science journal articles to organize the literature and make it easier to discover new knowledge.

Containing one of the largest AI workloads trained on Red Hat’s OpenShift software to date, the fully trained model uses PrimeQA, IBM’s open-source multilingual question-answering system.

Beyond providing a resource to researchers, the new language model for Earth science could be infused into NASA’s scientific data management and stewardship processes.

The combination of these two models will potentially change humanity and, as pointed out by Ramachandran, workers from both NASA and IBM will be instrumental to the project in Huntsville along with other parts of the world.

“The beauty of foundation models is they can potentially be used for many downstream applications,” said Ramachandran. “Building these foundation models cannot be tackled by small teams,” he added. “You need teams across different organizations to bring their different perspectives, resources, and skill sets.”