Integrating low-cost sensor monitoring, satellite mapping, and geospatial artificial intelligence for intra-urban air pollution predictions
Integrating low-cost sensor monitoring, satellite mapping, and geospatial artificial intelligence for intra-urban air pollution predictions
复制标题
DOI：
10.1016/j.envpol.2023.121832
复制
发表时间：
2023-05-26
影响因子：
8.9
通讯作者：
South, John
中科院分区：
文献类型：
--
作者：
Liang, Lu;Daniels, Jacob;South, John
越来越需要将地理空间人工智能分析应用于不同的环境数据集，以找到有利于一线社区的解决方案。其中一个迫切需要的解决办法是预测与健康有关的周围地面空气污染浓度。然而，围绕有限的地面参考站的规模和代表性存在许多挑战，用于模型开发，协调多源数据以及深度学习模型的可解释性。这项研究通过利用战略部署的广泛的低成本传感器（LCS）网络来解决这些挑战，该网络通过优化的神经网络进行了严格的校准。检索和处理了一组具有不同数据质量和空间尺度的光栅预测因子，包括间隙填充的卫星气溶胶光学厚度产品和机载激光雷达衍生的3D城市形态。我们开发了一个多尺度的，注意力增强的卷积神经网络模型，以协调LCS测量和多源预测，以估计30米分辨率的每日PM2.5浓度。该模型采用了一种先进的方法，通过使用地质统计克里格法来生成基线污染模式和多尺度残差方法来识别区域模式和局部事件，以保留高频特征。我们进一步使用排列测试来量化特征重要性，这在环境科学中的DL应用中很少做到。最后，我们通过调查街区组尺度上不同城市化水平之间和内部的空气污染不平等问题，展示了该模型的一个应用。总的来说，这项研究展示了地理空间人工智能分析为解决关键环境问题提供可行解决方案的潜力。
There is a growing need to apply geospatial artificial intelligence analysis to disparate environmental datasets to find solutions that benefit frontline communities. One such critically needed solution is the prediction of healthrelevant ambient ground-level air pollution concentrations. However, many challenges exist surrounding the size and representativeness of limited ground reference stations for model development, reconciling multi-source data, and interpretability of deep learning models. This research addresses these challenges by leveraging a strategically deployed, extensive low-cost sensor (LCS) network that was rigorously calibrated through an optimized neural network. A set of raster predictors with varying data quality and spatial scales was retrieved and processed, including gap-filled satellite aerosol optical depth products and airborne LiDAR-derived 3D urban form. We developed a multi-scale, attention-enhanced convolutional neural network model to reconcile the LCS measurements and multi-source predictors for estimating daily PM2.5 concentration at 30-m resolution. This model employs an advanced approach by using the geostatistical kriging method to generate a baseline pollution pattern and a multi-scale residual method to identify both regional patterns and localized events for highfrequency feature retention. We further used permutation tests to quantify the feature importance, which has rarely been done in DL applications in environmental science. Finally, we demonstrated one application of the model by investigating the air pollution inequality issue across and within various urbanization levels at the block group scale. Overall, this research demonstrates the potential of geospatial AI analysis to provide actionable solutions for addressing critical environmental issues.