Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

VayuBuddy: an LLM-Powered Chatbot to Democratize Air Quality Insights

Zeel B Patel, Yash Bachwana, Nitish Sharma, Sarath Guttikunda, Nipun Batra

TL;DR

This work presents VayuBuddy, a Large Language Model (LLM)-powered chatbot system to reduce the barrier between the stakeholders and air quality sensor data, and benchmarks the capabilities of 7 LLMs on 45 diverse question-answer pairs.

Abstract

Nearly 6.7 million lives are lost due to air pollution every year. While policymakers are working on the mitigation strategies, public awareness can help reduce the exposure to air pollution. Air pollution data from government-installed sensors is often publicly available in raw format, but there is a non-trivial barrier for various stakeholders in deriving meaningful insights from that data. In this work, we present VayuBuddy, a Large Language Model (LLM)-powered chatbot system to reduce the barrier between the stakeholders and air quality sensor data. VayuBuddy receives the questions in natural language, analyses the structured sensory data with a LLM-generated Python code and provides answers in natural language. We use the data from Indian government air quality sensors. We benchmark the capabilities of 7 LLMs on 45 diverse question-answer pairs prepared by us. Additionally, VayuBuddy can also generate visual analysis such as line-plots, map plot, bar charts and many others from the sensory data as we demonstrate in this work.

VayuBuddy: an LLM-Powered Chatbot to Democratize Air Quality Insights

TL;DR

This work presents VayuBuddy, a Large Language Model (LLM)-powered chatbot system to reduce the barrier between the stakeholders and air quality sensor data, and benchmarks the capabilities of 7 LLMs on 45 diverse question-answer pairs.

Abstract

Nearly 6.7 million lives are lost due to air pollution every year. While policymakers are working on the mitigation strategies, public awareness can help reduce the exposure to air pollution. Air pollution data from government-installed sensors is often publicly available in raw format, but there is a non-trivial barrier for various stakeholders in deriving meaningful insights from that data. In this work, we present VayuBuddy, a Large Language Model (LLM)-powered chatbot system to reduce the barrier between the stakeholders and air quality sensor data. VayuBuddy receives the questions in natural language, analyses the structured sensory data with a LLM-generated Python code and provides answers in natural language. We use the data from Indian government air quality sensors. We benchmark the capabilities of 7 LLMs on 45 diverse question-answer pairs prepared by us. Additionally, VayuBuddy can also generate visual analysis such as line-plots, map plot, bar charts and many others from the sensory data as we demonstrate in this work.

Paper Structure

This paper contains 16 sections, 4 figures, 4 tables.

Table of Contents

  1. Related Work
  2. Chatbots
  3. Codegen LLMs
  4. LLMs for tabular data
  5. Air Quality Toolkits
  6. Dataset
  7. Air Quality Dataset
  8. Natural Language Prompts Dataset
  9. Large Language Models
  10. Prompt Engineering
  11. Evaluation
  12. Experimental Setup
  13. Results
  14. Analysis
  15. Limitations and Future Work
  16. ...and 1 more sections

Figures (4)

  • Figure 1: Flow Diagram of our VayuBuddy System.
  • Figure 2: Location of Sensors: This image was generated by VayuBuddy with the following prompt: "Plot the locations of the stations on the India Map. Do not Annotate."
  • Figure 3: This image was generated by VayuBuddy with the following prompt: "Create a calendar map showing average PM2.5."
  • Figure 4: This image was generated by VayuBuddy with the following prompt: "Plot the choropleth map showing PM10 levels across India, with different colours representing different AQI categories (e.g., Good, Moderate, Unhealthy, etc.)"