University of Hawai'i (UH) at Mānoa researchers have developed a unique AI tool which can analyze complex geoscience data, enabling more efficient exploration from sea levels on earth, to atmospheric analysis on Mars.
Dubbed the Intelligent Data Exploring Assistant (IDEA), the AI tool combines the power of LLMs which large scientific data sets to allow everyday language exploration and analysis. IDEA can be used to retrieve data and complete analysis, generate plots, and even review its own results.
Described in the Journal of Geophysical Research: Machine Learning and Computation, IDEA serves as a framework on which more specialized models can be built. As a proof of concept, the team built the Station Explorer Assistant (SEA) on the IDEA framework, which can be used to simplify global sea level observations.
"With the Station Explorer Assistant, users don't need to write a single line of code to analyze tide gauge data, track sea level rise, or assess flooding occurrence," said Matthew Widlansky, associate director of the UH Sea Level Center.
"An exciting part of this work is how easily the IDEA framework can be adapted to explore new datasets," added Nemanja Komar, co-author of the study. "We even shifted from sea level records to dust storms on Mars—just by changing the instructions and data source."
Flexibility is central to the design of IDEA, allowing customization and optimization for different research problems. The researchers encourage developers to experiment with the IDEA framework which can be found on Github.