Jason Leigh

Aaron McLean, Makena Coffman, Andy Yu et al.

Climate hazards in Hawai'i are increasing in both frequency and severity, with varying impacts over vulnerable communities. This paper presents the Community Census and Spatial Visualization Index (CCSVI), a web-based geospatial visualization platform that integrates climate hazard data with socioeconomic and infrastructural datasets. This system enables users to explore the correlation between environmental risks and social vulnerability through interactive mapping and layered data visualizations. Social vulnerability and climate hazard data are commonly collected individually, this causes the data to be disjointed making it difficult to combine and analyze directly. With data being unrelated when collected, finding direct comparisons and combining the data is difficult resulting in many non-expert users to not understand the data. Additionally, many existing tools focus on only one of these types of data, limiting their interactivity and failing to make any improvements. CCSVI aims to handle the lack of accessible, unified, and interactive systems analyzing the relationship between climate hazards and social vulnerabilities across the state of Hawai'i. This support favors assisting decision-makers, researchers, and community members in identifying at-risk populations, improving disaster preparedness, and creating informed climate adaptation strategies.

Christopher J. Lee, Giorgio Tran, Roderick Tabalba et al.

This paper explores the intersection of data visualization and Large Language Models (LLMs). Driven by the need to make a broader range of data visualization types accessible for novice users, we present a guided LLM-based pipeline designed to transform data, guided by high-level user questions (referred to as macro-queries), into a diverse set of useful visualizations. This approach leverages various prompting techniques, fine-tuning inspired by Abela's Chart Taxonomy, and integrated SQL tool usage.

Yoshiki Takagi, Roderick Tabalba, Nurit Kirshenbaum et al.

Explainable AI (XAI) has demonstrated the potential to help reinforcement learning (RL) practitioners to understand how RL models work. However, XAI for users who do not have RL expertise (non-RL experts), has not been studied sufficiently. This results in a difficulty for the non-RL experts to participate in the fundamental discussion of how RL models should be designed for an incoming society where humans and AI coexist. Solving such a problem would enable RL experts to communicate with the non-RL experts in producing machine learning solutions that better fit our society. We argue that abstracted trajectories, that depicts transitions between the major states of the RL model, will be useful for non-RL experts to build a mental model of the agents. Our early results suggest that by leveraging a visualization of the abstracted trajectories, users without RL expertise are able to infer the behavior patterns of RL.