An AI-Enabled Edge-IoT Framework for Real-Time Air Quality Forecasting and Microclimate Zoning in Urban Smart Environments

DOI

10.2991/978-94-6239-674-6_7How to use a DOI?

Keywords

Air Quality Forecasting; LSTM-CNN; IoT; Microclimate Zoning; PM2.5; PM10; Rajasthan; Smart Cities; Environmental Monitoring

Abstract

The fast-rising urbanization and industrialization rates associated with urban agglomeration studies during recent decades have resulted in a considerable reduction in air quality in urban zones, specifically in cities such as Rajasthan, with profound impacts on public health, environment, and urban liveability. Taking into account all the aforesaid concerns and associated complexities, this research study presents an innovative AI-powered Edge IoT system with real-time air quality forecast models and microclimate zones for effective smart urban infrastructure embedding. The proposed system includes a hybrid Long Short-Term Memory-Convolutional Neural Network architecture for efficient and precise forecast models concerning critical air quality components such as PM2.5 & PM10. The system is developed with comprehensive historical datasets ranging from 2019 to 2024 pertaining to air quality and corresponding meteorological factors compiled from Central Pollution Control Board and Open NASA API. Performance analysis with prevalent parameters illustrates its potent predictive aptitude with R² value 0.88, low values for both RMSE & MAE, with a target MAPE value of 9.8% with high efficacy and reliability. The forecasted values for air quality constituents are applied for simulating real-time response actions with virtual IoT sensing systems developed with Autodesk Tinkercad. Additionally, the framework is capable of micro-climate zoning by employing unsupervised machine learning algorithms such as k-means clustering algorithms to identify pollutant and meteorological patterns. This is done to enable the creation of hyper-local zones for pollutant emissions as well as environmental predictions.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Apoorva Verma
AU  - Leena Bhatia
PY  - 2026
DA  - 2026/05/28
TI  - An AI-Enabled Edge-IoT Framework for Real-Time Air Quality Forecasting and Microclimate Zoning in Urban Smart Environments
BT  - Proceedings of the International Conference on Sustainable Computing and Artificial Intelligence (ICSCAI 2025)
PB  - Atlantis Press
SP  - 67
EP  - 79
SN  - 2352-5401
UR  - https://doi.org/10.2991/978-94-6239-674-6_7
DO  - 10.2991/978-94-6239-674-6_7
ID  - Verma2026
ER  -