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

2025-11-02

AI Summary

India suffers approximately 1.6 million premature deaths annually due to air pollution; however, existing environmental data analytics tools are highly technical, non-interactive, and ill-suited for evidence-based policymaking. To address this gap, we present the first conversational air quality management platform tailored to India’s heterogeneous environmental data—including CPCB monitoring records, demographic statistics, and NCAP funding allocations. Leveraging large language models (LLMs), our system enables end-to-end natural language–to–code generation, analytical reasoning, and interactive visualization. Innovatively, the LLM performs semantic parsing, dynamically generates executable SQL and Python code, and renders interpretable visualizations—substantially lowering the barrier to data-driven analysis. The platform is publicly deployed with real-time demonstration capabilities, empowering policymakers, researchers, and the general public to obtain actionable insights on demand. This advances both decision-making accessibility and civic engagement in environmental governance.

Technology Category

• Natural Language Processing: Interpretability, Analysis, and Evaluation of NLP Models
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Planning, Routing, and Scheduling: Planning with Language Models

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

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.

Problem

• Addressing air pollution data accessibility for Indian decision makers
• Overcoming expertise barriers in environmental analytics tools
• Integrating dispersed air quality data through conversational interface

Innovation

• LLM-powered conversational interface for air quality analytics
• Integrates multi-source environmental and policy data
• Generates executable Python code and interactive visualizations