Citation

Wang, Guangcheng and Yang, Jifan and Jiang, Kui and Gu, Ke and Wong, Lai Kuan and Lin, Weisi and Zhai, Guangtao (2026) A Prototype Feature Representation-Guided Multitask Learning Framework for Image-Based PM2.5 Concentration Monitoring. IEEE Transactions on Geoscience and Remote Sensing, 64. p. 4109315. ISSN 0196-2892

Text 7.pdf - Published Version Restricted to Repository staff only Download (4MB)

Abstract

With rapid industrialization, air pollution has emerged as a critical societal problem. Particulate matter (PM2.5) poses severe threats to public health and ecosystems, making it paramount to establish accurate and scalable monitoring solutions to safeguard the health of humans and animals as well as the ecological environment. While conventional instruments provide precise measurements, their widespread deployment is hindered by high costs and limited coverage. The image-based methods that utilize widely distributed traffic cameras or drones to capture PM2.5-related visual features (e.g., contrast and saturation) offer a promising alternative. However, existing approaches, including both traditional hand-crafted feature-based methods and deep learning-based methods, face challenges in complex environments and suffer from performance limitations due to the long-tailed distribution of pollution data. To this aim, we propose a prototype feature representation-guided multitask learning (PFRML) framework, which integrates classification and regression for PM2.5 concentration estimation. The framework comprises two main components. First, a convolutional neural network (CNN)-Transformer ensemble backbone combines CNN’s strength in local spatial feature extraction with Transformer’s capability in modeling global contextual relationships, enabling robust feature representation under complex conditions. Second, a classification-regression multitask paradigm employs prototype learning (effective in few-shot scenarios) to explicitly construct a PM2.5 pollution level representation space (i.e., prototype features), thereby enhancing sparse sample recognition through clustering constraints. Meanwhile, the regression branch implicitly learns continuous concentrations via a multilayer perception while leveraging the prototype features from the classification branch for auxiliary optimization. Experiments conducted on multiple public benchmarks demonstrate that our method achieves superior prediction accuracy and robustness compared to state-of-the-art (SOTA) PM2.5 estimation methods.

Item Type:	Article
Uncontrolled Keywords:	Long-tailed distribution, multitask learning, particulate matter (PM2.5) monitoring
Subjects:	Q Science > QA Mathematics > QA71-90 Instruments and machines
Divisions:	Faculty of Computing and Informatics (FCI)
Depositing User:	Ms Suzilawati Abu Samah
Date Deposited:	31 Jul 2026 06:05
Last Modified:	31 Jul 2026 06:05
URII:	http://shdl.mmu.edu.my/id/eprint/16407

Downloads

Edit (login required)