Sensorium Arc: AI Agent System for Oceanic Data Exploration and Interactive Eco-Art

2025-11-19

AI Summary

This study addresses the challenge of low public engagement with complex, abstract marine environmental data. We propose an ecological narrative–driven AI interaction paradigm implemented via a modular multi-agent system that integrates retrieval-augmented large language models, keyword detection, and cross-modal generation. Real-time oceanic data are anthropomorphized into poetic narrators, enabling natural-language dialogue and dynamically triggering spatiotemporal visualizations, ambient soundscapes, and generative imagery. The system introduces a novel dialogue-guided multimodal response mechanism, transforming scientific data into lifelike, emotionally resonant expressions. Empirical evaluation demonstrates significant improvements in users’ affective engagement and aesthetic comprehension of marine change and climate issues. Results validate the cognitive mediation efficacy of AI agents in environmental science communication and establish a scalable prototype bridging ecological art, human–AI coexistence, and participatory environmental literacy.

Technology Category

• Multiagent Systems: Agent Communication
• Humans and AI: Interaction Techniques and Devices
• Natural Language Processing: Language Grounding & Multi-modal NLP

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Assisted, interactive, and conversational search
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems

Abstract

Sensorium Arc (AI reflects on climate) is a real-time multimodal interactive AI agent system that personifies the ocean as a poetic speaker and guides users through immersive explorations of complex marine data. Built on a modular multi-agent system and retrieval-augmented large language model (LLM) framework, Sensorium enables natural spoken conversations with AI agents that embodies the ocean's perspective, generating responses that blend scientific insight with ecological poetics. Through keyword detection and semantic parsing, the system dynamically triggers data visualizations and audiovisual playback based on time, location, and thematic cues drawn from the dialogue. Developed in collaboration with the Center for the Study of the Force Majeure and inspired by the eco-aesthetic philosophy of Newton Harrison, Sensorium Arc reimagines ocean data not as an abstract dataset but as a living narrative. The project demonstrates the potential of conversational AI agents to mediate affective, intuitive access to high-dimensional environmental data and proposes a new paradigm for human-machine-ecosystem.

Problem

• Creating interactive AI agents for ocean data exploration through natural conversations
• Transforming marine datasets into immersive ecological narratives and visualizations
• Developing multimodal systems that blend scientific data with artistic environmental expression

Innovation

• Multimodal AI agent system for ocean data exploration
• Modular multi-agent framework with retrieval-augmented LLMs
• Dynamic data visualization triggered by semantic dialogue parsing