CHATATC: Large Language Model-Driven Conversational Agents for Supporting Strategic Air Traffic Flow Management

TL;DR

This paper introduces CHATATC, a large language model-based conversational agent designed to assist in strategic air traffic flow management by leveraging extensive historical data and natural language interactions.

Contribution

The work presents the development and evaluation of CHATATC, a novel LLM tailored for air traffic management, including its training, capabilities, and interface design.

Findings

CHATATC accurately provides GDP rates, durations, and reasons.

It demonstrates effective natural language query handling.

Identifies limitations in superlative question responses.

Abstract

Generative artificial intelligence (AI) and large language models (LLMs) have gained rapid popularity through publicly available tools such as ChatGPT. The adoption of LLMs for personal and professional use is fueled by the natural interactions between human users and computer applications such as ChatGPT, along with powerful summarization and text generation capabilities. Given the widespread use of such generative AI tools, in this work we investigate how these tools can be deployed in a non-safety critical, strategic traffic flow management setting. Specifically, we train an LLM, CHATATC, based on a large historical data set of Ground Delay Program (GDP) issuances, spanning 2000-2023 and consisting of over 80,000 GDP implementations, revisions, and cancellations. We test the query and response capabilities of CHATATC, documenting successes (e.g., providing correct GDP rates, durations, and reason) and shortcomings (e.g,. superlative questions). We also detail the design of a graphical user interface for future users to interact and collaborate with the CHATATC conversational agent.