Authors : Anser Pasha C. A.; Mohamed Sahil; Pushpa Ravikumar; Arpitha C. N.

Volume/Issue : Volume 11 - 2026, Issue 6 - June

Google Scholar : https://tinyurl.com/3taabj3u

Scribd : https://tinyurl.com/2hkz88rs

DOI : https://doi.org/10.38124/ijisrt/26jun1941

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Abstract : Air pollution is a serious public and environmental health problem due to its harmful impacts on humans and environment, which include increased rate of respiratory diseases and decreased of visibility and altered weather pattern. The harmful effects of air pollution on human health and environment such as increase in respiratory diseases, reduction in visibility and changes in weather patterns has made it a major concern environmental and health concerns. Traditional AQI monitoring systems make use of sophisticated sensor networks and monitoring stations, which is a costly setup and have limitations in accessibility and coverage. The proposed project, SkyVision: Deep Learning Based Air Quality Detection from Sky Images addresses this problem by providing an economical and an intelligent method of detecting the air quality from the images of the sky. A dataset of 12,240 sky images is used and the images undergo preprocessing techniques such as RGB conversion, bilinear image resizing, Gaussian filtering (for denoising), Z-score normalization and data augmentation. The deep learning model employs a pretrained ResNet50 convolutional neural network to automatically extract the relevant visual features like haze density, color intensity, brightness, cloud visibility, atmosphere visibility, etc., from the sky images.

Keywords : Deep Learning, ResNet50, Air Quality Detection, Image Processing, Convolutional Neural Network (CNN).

References :

1. J. J. Mondal, M. F. Islam, R. Islam, N. K. Rhidi, S. Newaz, M. A. Manab, A. B. M. A. Al Islam, and J. Noor, “Uncovering Local Aggregated Air Quality Index with Smartphone Captured Images Leveraging Efficient Deep Convolutional Neural Network,” Scientific Reports, vol. 14, Art. no. 1627, 2024.
2. A. Feldman, S. Kendler, P. Agrawal, and B. Fishbain, “Urban Air-Quality Estimation Using Visual Cues and a Deep Convolutional Neural Network in Bengaluru (Bangalore), India,” Environmental Science & Technology, vol. 58, no. 1, pp. 480–487, 2024.
3. P. Sarkar, D. D. V. Saha, and M. Saha, “Real-Time Air Quality Index Detection through Regression-Based Convolutional Neural Network Model on Captured Images,” Environmental Quality Management, 2024.
4. Z. Zhang et al., “A Systematic Survey of Air Quality Prediction Based on Deep Learning,” Atmosphere, vol. 15, 2024.
5. X. Wang, M. Wang, X. Liu, Y. Mao, Y. Chen, and S. Dai, “Surveillance-Image-Based Outdoor Air Quality Monitoring,” Environmental Science and Ecotechnology, vol. 18, p. 100319, 2024.
6. A. T. Nguyen, D. H. Pham, B. L. Oo, Y. Ahn, and B. T. H. Lim, “Predicting Air Quality Index Using Attention Hybrid Deep Learning and Quantum-Inspired Particle Swarm Optimization,” Journal of Big Data, vol. 11, Art. no. 71, 2024.
7. F. D. Javan, M. Shafiee, and M. A. Pourghasemi, “Air Pollution Observation—Bridging Spaceborne to Unmanned Airborne Remote Sensing: A Systematic Review and Meta-Analysis,” Remote Sensing, vol. 17, 2025.
8. M. S. Vahdatpour, M. Eyvazi, and Y. Zhang, “Forecasting and Visualizing Air Quality from Sky Images with Vision-Language Models,” arXiv preprint arXiv:2509.15076, 2025.
9. Y. Han, “PM25Vision: A Large-Scale Benchmark Dataset for Visual Estimation of Air Quality,” arXiv preprint arXiv:2509.16519, 2025.
10. K. A. Kushal and A. Al Mamun, “AQFusionNet: Multimodal Deep Learning for Air Quality Index Prediction with Imagery and Sensor Data,” arXiv preprint arXiv:2509.00353, 2025