← Back to VOLUME 13, ISSUE 10, OCTOBER 2026
This work is licensed under a Creative Commons Attribution 4.0 International License.
AI-Driven Air Quality Forecasting and Smart Decision Support Dashboard
Madhuri P. Borawake, Shruti Santosh Thorat, Pranita Pradip Lohokare, Nandini Nathuram Mahadik
👁 5 views📥 2 downloads
Abstract: Urban air pollution threatens public health, yet most monitoring services only report what the air is like right now. This paper presents the design of a web-based platform that goes one step further by estimating the Air Quality Index (AQI) for the coming 72 hours and turning those estimates into practical guidance. The platform merges pollutant readings obtained from OpenAQ and the Central Pollution Control Board (CPCB) with weather variables such as temperature, humidity, wind speed and rainfall. After cleaning and feature construction, an XGBoost regression model learns the link between these inputs and future AQI values. Training, tuning and testing follow a strictly time-ordered split so that no future information leaks into the learning stage. Forecasts are mapped to Indian AQI categories and paired with health advisories, rule-based recommendations and a question-answering chatbot, all delivered through an interactive dashboard built with FastAPI, React.js and PostgreSQL. The system is still being implemented, so no accuracy figures are claimed here; the paper instead documents the architecture, data plan and an evaluation protocol based on MAE, RMSE and R².
Keywords: Air Quality Index; AQI Forecasting; XGBoost Regression; OpenAQ; CPCB; Decision Support; Health Advisory; Chatbot; Environmental Monitoring
Keywords: Air Quality Index; AQI Forecasting; XGBoost Regression; OpenAQ; CPCB; Decision Support; Health Advisory; Chatbot; Environmental Monitoring
How to Cite:
[1] Madhuri P. Borawake, Shruti Santosh Thorat, Pranita Pradip Lohokare, Nandini Nathuram Mahadik, “AI-Driven Air Quality Forecasting and Smart Decision Support Dashboard,” International Advanced Research Journal in Science, Engineering and Technology (IARJSET), DOI: 10.17148/IARJSET.2026.131057
