Developing AI-powered Tools for Tracking and Communicating Sea Level Conditions
Advances in natural-language processing and large language models (LLMs), such as those utilized by ChatGPT, are transforming how geoscientists interact with complex datasets, enabling efficient and intuitive scientific analyses. As part of the Tracking and Communicating on Sea Level Pacific RISA project, PI Widlansky and the University of Hawaiʻi Sea Level Center (UHSLC) are developing tools that use LLMs to allow researchers to ask questions in everyday language and receive clear explanations and data analyses in response, minimizing the need for time-consuming tech support for project managers. A key objective of this project is to strengthen the nation’s coastal preparedness by improving access to tidal datum information and water level thresholds relevant for navigation, engineering, and flood response. The team is producing tracking metrics, standardized indicators, and visualizations to support national-scale reporting efforts, such as the Pacific Islands Regional Climate Assessment (PIRCA) report for the Republic of the Marshall Islands (RMI). Users of the new Intelligent Data Exploring Assistant (IDEA) can request digital “report cards” for water level conditions, helping to communicate high-water exceedances and benchmark comparisons in a consistent and interpretable format. Built using open-source software and freely available libraries, IDEA allows users to generate reproducible data analyses and visualizations without needing extensive programming experience. By combining UHSLC’s authoritative sea level data with cutting-edge generative AI interfaces, this project aims to reduce technical barriers to data analysis, improve stakeholder engagement, and enhance decision-making capacity for coastal resilience and hazard planning.
A major advancement this year was the development and implementation of the Station Explorer Assistant (SEA), an AI-powered web application that enables users to analyze tide gauge data using natural language prompts. It even writes and runs its own analysis software, which it shows the user to check that its results are accurate. SEA lowers the technical barriers for exploring sea level datasets by integrating generative AI with authoritative water level observations from the UHSLC. By making sea level science easier to understand and access, SEA can support communities adapting to rising seas and other coastal challenges.
SEA technology is also generalizable across geoscience domains, through a framework called an Intelligent Data Exploring Assistant (IDEA), which can be demonstrated by asking it to analyze atmospheric observations from Mars collected by NASA’s InSight Mission (Try it!). By combining LLM capabilities with robust domain-specific customizations, SEA and the IDEA example generate accurate analyses, visualizations, and insights through natural-language prompts. This study highlights the potential of IDEA frameworks to lower technical barriers, enhance educational opportunities, and transform geoscientific workflows while addressing the limitations and uncertainties of current LLM technology. PI Widlansky’s work also highlights how AI can enhance scientific research and communication, and helps us to envision how the creation of similar tools can support scientists in many fields.
Research Team Matthew Widlansky (University of Hawaiʻi Sea Level Center)
AI-powered Sea Level Rise Tools
Developing AI-powered Tools for Tracking and Communicating Sea Level Conditions
Advances in natural-language processing and large language models (LLMs), such as those utilized by ChatGPT, are transforming how geoscientists interact with complex datasets,
enabling efficient and intuitive scientific analyses. As part of the Tracking and Communicating on Sea Level Pacific RISA project, PI Widlansky and the University of Hawaiʻi Sea Level Center (UHSLC) are developing tools that use LLMs to allow researchers to ask questions in everyday language and receive clear explanations and data analyses in response, minimizing the need for time-consuming tech support for project managers. A key objective of this project is to strengthen the nation’s coastal preparedness by improving access to tidal datum information and water level thresholds relevant for navigation, engineering, and flood response. The team is producing tracking metrics, standardized indicators, and visualizations to support national-scale reporting efforts, such as the Pacific Islands Regional Climate Assessment (PIRCA) report for the Republic of the Marshall Islands (RMI). Users of the new Intelligent Data Exploring Assistant (IDEA) can request digital “report cards” for water level conditions, helping to communicate high-water exceedances and benchmark comparisons in a consistent and interpretable format. Built using open-source software and freely available libraries, IDEA allows users to generate reproducible data analyses and visualizations without needing extensive programming experience. By combining UHSLC’s authoritative sea level data with cutting-edge generative AI interfaces, this project aims to reduce technical barriers to data analysis, improve stakeholder engagement, and enhance decision-making capacity for coastal resilience and hazard planning.
A major advancement this year was the development and implementation of the Station Explorer Assistant (SEA), an AI-powered web application that enables users to analyze tide gauge data using natural language prompts. It even writes and runs its own analysis software, which it shows the user to check that its results are accurate. SEA lowers the technical barriers for exploring sea level datasets by integrating generative AI with authoritative water level observations from the UHSLC. By making sea level science easier to understand and access, SEA can support communities adapting to rising seas and other coastal challenges.
SEA technology is also generalizable across geoscience domains, through a framework called an Intelligent Data Exploring Assistant (IDEA), which can be demonstrated by asking it to analyze atmospheric observations from Mars collected by NASA’s InSight Mission (Try it!). By combining LLM capabilities with robust domain-specific customizations, SEA and the IDEA example generate accurate analyses, visualizations, and insights through natural-language prompts. This study highlights the potential of IDEA frameworks to lower technical barriers, enhance educational opportunities, and transform geoscientific workflows while addressing the limitations and uncertainties of current LLM technology. PI Widlansky’s work also highlights how AI can enhance scientific research and communication, and helps us to envision how the creation of similar tools can support scientists in many fields.
Research Team
Matthew Widlansky (University of Hawaiʻi Sea Level Center)
Resources
SEAinfo page, with several YouTube video demonstrations and presentations by PI Widlansky
https://uhslc.soest.hawaii.edu/research/SEAinfo/
GitHub IDEA page
https://github.com/uhsealevelcenter/IDEA
IDEA manuscript with a plain language summary and abstract
https://uhslc.soest.hawaii.edu/research/SEAinfo/IDEA_manuscript_latest.pdf
Our Vision
Pacific Island communities that are resilient to climate impacts and using climate information to manage risks.
Follow Pacific RISA
Archives