Hybrid CNN–ILSTM Framework for Air Quality Index Prediction Using Machine Learning and Deep Learning Models
ITM Web of Conferences · 2026 · 86 · 01014
DOI: 10.1051/itmconf/20268601014 ↗Kurz gefasst
Fachartikel in der Zeitschrift ITM Web of Conferences, online erschienen am 05.06.2026. Verfasst von Shankar Prasad Mitra und 1 weiteren Autor:innen. Die Arbeit nennt 25 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Air pollution has emerged as one of the important aspects of the environment which has caused serious concerns among people residing in urban areas. It becomes very important to predict the Air Quality Index (AQI) with high accuracy to mitigate such problems. In this paper, we have developed a hybrid model of deep learning techniques such as Convolutional Neural Network and Improved Long Short-Term Memory (ILSTM). We used the CPCB dataset of India from the years 2015 to 2020 for our experimentation. We compared several baseline models such as Linear Regression, LASSO, Ridge Regression, Support Vector Regression (SVR), LSTM, and GRU. The proposed method effectively considers the interaction between features and time sequence data present in pollutants. The experimental results show that the proposed hybrid deep learning model performs better than all others with MAE = 8.41, RMSE = 10.00, and R 2 = 0.98.
Zitieren
APA
Mitra, S. P., & Das, S. (2026). Hybrid CNN–ILSTM Framework for Air Quality Index Prediction Using Machine Learning and Deep Learning Models. ITM Web of Conferences, 86, 01014. https://doi.org/10.1051/itmconf/20268601014
Vancouver
Mitra SP, Das S. Hybrid CNN–ILSTM Framework for Air Quality Index Prediction Using Machine Learning and Deep Learning Models. ITM Web of Conferences. 2026;86:01014. doi:10.1051/itmconf/20268601014
BibTeX
@article{Mitra2026,
author = {Mitra, Shankar Prasad and Das, Shuvendu},
title = {Hybrid CNN–ILSTM Framework for Air Quality Index Prediction Using Machine Learning and Deep Learning Models},
journal = {ITM Web of Conferences},
year = {2026},
volume = {86},
pages = {01014},
doi = {10.1051/itmconf/20268601014}
}
EUVIMED