用卫星数据+图神经网络，提升城市空气污染预测精度。
Improving Local Air Quality Predictions Using Transfer Learning on Satellite Data and Graph Neural Networks
- 结合卫星与气象数据，通过迁移学习和图神经网络预测污染。
- 在布里斯托尔地区误差降低8.6%，梯度误差减少32.6%。
- 适合关注环境监测、公共健康的城市规划者使用。
空气污染是全球重大健康风险，每年导致数百万早逝。氮氧化物（NO2）是一种有害污染物，主要影响监测网络稀疏的城市区域。本文提出一种新方法，利用卫星与气象数据，结合迁移学习和图神经网络（GraphSAGE），预测未设监测点区域的NO2浓度。模型以伦敦数据预训练，应用于布里斯托尔，相比基线模型，标准化均方根误差（NRMSE）降低8.6%，梯度均方根误差（Gradient RMSE）降低32.6%。该研究展示了虚拟传感器在低成本空气质量监测中的潜力，可为气候与健康干预提供实用洞见。
原文摘要 · Abstract (English)
Air pollution is a significant global health risk, contributing to millions of premature deaths annually. Nitrogen dioxide (NO2), a harmful pollutant, disproportionately affects urban areas where monitoring networks are often sparse. We propose a novel method for predicting NO2 concentrations at unmonitored locations using transfer learning with satellite and meteorological data. Leveraging the GraphSAGE framework, our approach integrates autoregression and transfer learning to enhance predictive accuracy in data-scarce regions like Bristol. Pre-trained on data from London, UK, our model achieves a 8.6% reduction in Normalised Root Mean Squared Error (NRMSE) and a 32.6% reduction in Gradient RMSE compared to a baseline model. This work demonstrates the potential of virtual sensors for cost-effective air quality monitoring, contributing to actionable insights for climate and health interventions.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。