IBM and NASA built an Earth science GPT. Here’s what it can do
The open-source AI will serve as a beginning for future crop, forest, and climate change monitoring systems.
PHOTOGRAPH: SI Imaging Services,Imazins?GETTY Images
NASA recently estimated that its Earth science missions would create approximately a quarter of a million terabytes of information in 2024 alone. Managing and referencing a large amount of data can be quite challenging. To address this issue, a collaboration between IBM, HuggingFace, and NASA has resulted in an open-source geospatial foundation model. This model is aimed at aiding researchers and other individuals in sifting through the vast amounts of information available. The model will serve as the basis for a new generation of climate and Earth science AIs that can track deforestation, predict crop yields, and rack greenhouse gas emissions.
At its core, this collaboration will create an AI prototype inspired by GPT that is dedicated to decoding the enigmas of our planet. The model will leverage the power of IBM’s Watsonx.ai and a year’s worth of NASA’s Harmonized Landsat Sentinel-2 satellite data (HLS). The two Sentinel-2 satellites have been acquiring high-resolution optical imagery over land and coastal regions in 13 spectral bands.
HuggingFace will host the model on its open-source AI platform. According to IBM, by fine-tuning the model on “labeled data for flood and burn scar mapping,” the team was able to improve the model’s performance by 15 percent over the current state of the art using half as much data.
“The essential role of open-source technologies to accelerate critical areas of discovery such as climate change has never been clearer,” Sriram Raghavan, VP of IBM Research AI, said in a press release. “By combining IBM’s foundation model efforts aimed at creating flexible, reusable AI systems with NASA’s repository of Earth-satellite data, and making it available on the leading open-source AI platform, Hugging Face, we can leverage the power of collaboration to implement faster and more impactful solutions that will improve our planet.”
This incredible resource just might pave the way for a greater understanding of the world in which we live, and therefore new tools with which to address the challenges we face.
