OceanAI: A Conversational Platform for Accurate, Transparent, Near-Real-Time Oceanographic Insights

2025-11-02

AI Summary

Scientific dialogue AI systems in oceanography frequently exhibit hallucination and lack verifiability, undermining scientific rigor. Method: This study develops a conversational oceanographic analysis platform built upon open-source large language models (LLMs), uniquely integrating them with NOAA’s real-time parametric ocean data streams via RESTful APIs to enable natural-language querying and dynamic visualization. Contribution/Results: The platform ensures full traceability and reproducibility: every response is accompanied by direct links to the original NOAA data sources and precise timestamps. In blind evaluation, it is the only system consistently delivering authoritative, data-grounded answers; in contrast, leading proprietary AI models either refuse queries or generate fabricated content. The approach significantly enhances trustworthiness, transparency, and scalability of scientific dialogue systems—setting a new standard for domain-specific, evidence-based AI in ocean science.

Technology Category

• Natural Language Processing: Conversational AI/Dialog Systems
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Assisted, interactive, and conversational search
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Artificial intelligence is transforming the sciences, yet general conversational AI systems often generate unverified "hallucinations" undermining scientific rigor. We present OceanAI, a conversational platform that integrates the natural-language fluency of open-source large language models (LLMs) with real-time, parameterized access to authoritative oceanographic data streams hosted by the National Oceanic and Atmospheric Administration (NOAA). Each query such as "What was Boston Harbor's highest water level in 2024?" triggers real-time API calls that identify, parse, and synthesize relevant datasets into reproducible natural-language responses and data visualizations. In a blind comparison with three widely used AI chat-interface products, only OceanAI produced NOAA-sourced values with original data references; others either declined to answer or provided unsupported results. Designed for extensibility, OceanAI connects to multiple NOAA data products and variables, supporting applications in marine hazard forecasting, ecosystem assessment, and water-quality monitoring. By grounding outputs and verifiable observations, OceanAI advances transparency, reproducibility, and trust, offering a scalable framework for AI-enabled decision support within the oceans. A public demonstration is available at https://oceanai.ai4ocean.xyz.

Problem

• Providing verified oceanographic data through conversational AI to prevent hallucinations
• Integrating real-time NOAA data streams with large language models for accuracy
• Enhancing transparency and reproducibility in AI-driven oceanographic decision support

Innovation

• Integrates LLMs with NOAA real-time data streams
• Triggers API calls for verified data synthesis
• Provides reproducible responses with data references