AI model by NASA and IBM can help fight climate change

15% improvement over earlier models

The model in question - IBM's watsonx.ai geospatial foundation - has been built using NASA's large-scale satellite and remote sensing data.

"The essential role of open-source technologies to accelerate critical areas of discovery such as climate change has never been clearer," said Sriram Raghavan, Vice President of IBM Research AI.

"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," added Raghavan.

Released last month, Watsonx.ai is a studio for AI builders that enables them to train, deploy, validate, and tune machine learning and generative AI models.

An LLM to fight climate change

Jointly trained by IBM and NASA on Harmonized Landsat Sentinel-2 satellite data (HLS) over a year, the model has shown a 15 percent improvement over the current models, which use half as much labeled data. 

IBM said that this improvement could speed up geospatial analysis by three to four times and help reduce the amount of data cleaning and labeling required in training a traditional deep learning model, as per a report by the CIO.

"We believe that foundation models have the potential to change the way observational data is analyzed and help us to better understand our planet," said Kevin Murphy, Chief Science Data Officer at NASA. "And by open sourcing such models and making them available to the world, we hope to multiply their impact."