Scholarlink

<p>Accurate assessment of atmospheric nitrogen dioxide (NO<sub>2</sub>) and sulfur dioxide (SO<sub>2</sub>) is essential for understanding climate-air quality interactions, supporting environmental policy, and protecting public health. Traditional monitoring approaches face limitations: satellite observations provide broad spatial coverage but suffer from data gaps, while ground-based sensors offer high temporal resolution but limited spatial extent. To address these challenges, we propose PollutionNet, a Vision Transformer-based framework that integrates Sentinel-5P TROPOMI vertical column density (VCD) data with ground-level observations. By leveraging self-attention mechanisms, PollutionNet captures complex spatiotemporal dependencies that are often missed by conventional CNN and RNN models. Applied to Ireland (2020–2021), our case study demonstrates that PollutionNet achieves state-of-the-art performance (RMSE: 6.89&#xa0;µg/m<sup>3</sup> for NO<sub>2</sub>, 4.49&#xa0;µg/m<sup>3</sup> for SO<sub>2</sub>), reducing prediction errors by up to 14% compared to baseline models. Beyond accuracy gains, PollutionNet provides a scalable and data-efficient tool for applied climatology, enabling robust pollution estimation in regions with sparse monitoring networks. These results highlight the potential of advanced machine learning approaches to enhance climate-related air quality research, inform environmental management, and support sustainable policy decisions. The code and data used in this study are publicly available at: <a href="https://github.com/Prasanjit-Dey/PollutionNet">https://github.com/Prasanjit-Dey/PollutionNet</a>.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

PollutionNet: a vision transformer framework for climatological assessment of NO2 and SO2 using satellite-ground data fusion

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年7月20日

查看全文
  • Prasanjit Dey,
  • Soumyabrata Dev,
  • Bianca Schoen-Phelan

摘要

Accurate assessment of atmospheric nitrogen dioxide (NO2) and sulfur dioxide (SO2) is essential for understanding climate-air quality interactions, supporting environmental policy, and protecting public health. Traditional monitoring approaches face limitations: satellite observations provide broad spatial coverage but suffer from data gaps, while ground-based sensors offer high temporal resolution but limited spatial extent. To address these challenges, we propose PollutionNet, a Vision Transformer-based framework that integrates Sentinel-5P TROPOMI vertical column density (VCD) data with ground-level observations. By leveraging self-attention mechanisms, PollutionNet captures complex spatiotemporal dependencies that are often missed by conventional CNN and RNN models. Applied to Ireland (2020–2021), our case study demonstrates that PollutionNet achieves state-of-the-art performance (RMSE: 6.89 µg/m3 for NO2, 4.49 µg/m3 for SO2), reducing prediction errors by up to 14% compared to baseline models. Beyond accuracy gains, PollutionNet provides a scalable and data-efficient tool for applied climatology, enabling robust pollution estimation in regions with sparse monitoring networks. These results highlight the potential of advanced machine learning approaches to enhance climate-related air quality research, inform environmental management, and support sustainable policy decisions. The code and data used in this study are publicly available at: https://github.com/Prasanjit-Dey/PollutionNet.