A Review of Convolution Neural Network Architectures for Air Quality Prediction
SPU - Journal of Science, Technology and Management Research · 05.01.2026 · 2 (II) · 9-19
DOI: 10.63766/spujstmr.25.000045 ↗Kurz gefasst
Fachartikel in der Zeitschrift SPU - Journal of Science, Technology and Management Research, online erschienen am 05.01.2026. Verfasst von Krishna Veni und 1 weiteren Autor:innen.
Abstract (Originalsprache)
Steep increase in urbanization and industrialization has always contributed to air pollution around, delay in monitoring the air pollutant can risk ecological balance including human health. Therefore, accurate and timely prediction of air quality enables public health and supports effective policy interventions. Though many models are developed, here only Convolutional Neural Networks (CNNs) are focussed to make niche reviews, with their ability to draw spatiotemporal features from historical environmental data, have recently gained significant attention for air quality prediction. This review synthesizes findings from peer-reviewed studies published between 2020 - 2025, focusing on the application of CNNs in air quality modelling. The review explicitly examines and compares data sources, CNN architectures, and validation techniques used. However, challenges remain in model interpretability, and real-time deployment. This paper contributes a structured taxonomy of CNN-based approach, finds strengths and limitations, and highlights open research gaps.
Zitieren
APA
Veni, K., & Mohanty, B. (2026). A Review of Convolution Neural Network Architectures for Air Quality Prediction. SPU - Journal of Science, Technology and Management Research, 2(II), 9-19. https://doi.org/10.63766/spujstmr.25.000045
Vancouver
Veni K, Mohanty B. A Review of Convolution Neural Network Architectures for Air Quality Prediction. SPU - Journal of Science, Technology and Management Research. 2026;2(II):9-19. doi:10.63766/spujstmr.25.000045
BibTeX
@article{Veni2026,
author = {Veni, Krishna and Mohanty, Bibhabasu},
title = {A Review of Convolution Neural Network Architectures for Air Quality Prediction},
journal = {SPU - Journal of Science, Technology and Management Research},
year = {2026},
volume = {2},
number = {II},
pages = {9--19},
doi = {10.63766/spujstmr.25.000045}
}
EUVIMED