IBM and NASA team up on AI climate insights

The joint work will apply AI foundation model technology to NASA’s geospatial science and Earth-observing satellite data for the first time.

Foundation models are types of AI models that are trained on a broad set of unlabelled data, can be used for different tasks, and can apply information about one situation to another. These models have rapidly advanced the field of natural language processing (NLP) technology over the last five years, IBM said, describing itself as ‘pioneering’ applications beyond language.

Earth observations that allow scientists to study and monitor our planet are being gathered at unprecedented rates and volume. Innovative new approaches are required to extract knowledge from these vast datasets. The goal of IBM and NASA’s partnership is to provide an easier way for researchers to gain these insights.

According to IBM, its foundation model technology has potential to speed up the discovery and analysis of these data in order to quickly advance the scientific understanding of Earth and response to climate-related issues.

IBM and NASA plan to develop several new technologies to extract insights from Earth observations. One project will train and IBM geospatial intelligence foundation model on NASA’s Harmonised Landsat Sentinel-2 (HLS) dataset, a record of land cover and land use changes captured by Earth-orbiting satellites.

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

Another output from the collaboration is expected to be an easily searchable corpus of 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.

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 beauty of foundation models is they can potentially be used for many downstream applications,” said Rahul Ramachandran, senior research scientist at NASA's Marshall Space Flight Centre in Huntsville, Alabama.

“Building these foundation models cannot be tackled by small teams,” he added. “You need teams across different organisations to bring their different perspectives, resources, and skill sets.”

Other potential IBM-NASA joint projects in this agreement include constructing a foundation model for weather and climate prediction using MERRA-2, a dataset of atmospheric observations.

“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,” said Raghu Ganti, principal researcher at IBM.

“Ultimately, it could facilitate a larger number of people working on some of our most pressing climate issues.”

This collaboration is part of NASA’s Open-Source Science Initiative, which aims to build an inclusive, transparent and collaborative open science community over the next decade.