VayuChat: An LLM-Powered Conversational Interface for Air Quality Data Analytics

TL;DR

VayuChat is a conversational AI system that enables users to perform complex air quality data analysis through natural language, integrating multiple data sources and providing interactive visualizations and executable code to make environmental data accessible.

Contribution

It introduces a novel LLM-powered conversational interface that combines diverse air quality data sources with natural language processing for accessible environmental analytics.

Findings

Enables complex environmental queries via simple conversations

Integrates multiple air quality and policy data sources

Provides interactive visualizations and executable code

Abstract

Air pollution causes about 1.6 million premature deaths each year in India, yet decision makers struggle to turn dispersed data into decisions. Existing tools require expertise and provide static dashboards, leaving key policy questions unresolved. We present VayuChat, a conversational system that answers natural language questions on air quality, meteorology, and policy programs, and responds with both executable Python code and interactive visualizations. VayuChat integrates data from Central Pollution Control Board (CPCB) monitoring stations, state-level demographics, and National Clean Air Programme (NCAP) funding records into a unified interface powered by large language models. Our live demonstration will show how users can perform complex environmental analytics through simple conversations, making data science accessible to policymakers, researchers, and citizens. The platform is publicly deployed at https://huggingface.co/spaces/SustainabilityLabIITGN/ VayuChat. For further information check out video uploaded on https://www.youtube.com/watch?v=d6rklL05cs4.