Pollution tracker: Finding industrial sources of aerosol emission in satellite imagery
Pollution tracker: Finding industrial sources of aerosol emission in satellite imagery
复制标题
DOI：
10.1017/eds.2023.20
复制
发表时间：
2023-07
期刊：
影响因子：
--
通讯作者：
P. Manshausen;D. Watson‐Parris;L. Wagner;Pirmin Maier;S. J. Muller;G. Ramminger;P. Stier
中科院分区：
文献类型：
--
作者：
P. Manshausen;D. Watson‐Parris;L. Wagner;Pirmin Maier;S. J. Muller;G. Ramminger;P. Stier
摘要人为气溶胶（悬浮在空气中的固体或液体颗粒）的影响是当前气候扰动不确定性的最大贡献者。重工业场所，如燃煤电厂和钢铁制造商，是温室气体的主要来源，也会在小范围内排放大量的气溶胶。这使它们成为研究气溶胶与辐射和云相互作用的理想场所。然而，现有的重工业地点数据集要么不公开，要么存在报告空白。在这里，我们开发了一种有监督的深度学习算法，使用现有的数据集进行训练，以检测高分辨率卫星数据中未报告的行业站点。为了使管道在全球范围内可行，我们采用了两步走的方法。第一步使用10米分辨率的数据，扫描潜在的工业场所，然后使用1.2米分辨率的图像来确认或拒绝检测。在测试数据上，模型表现良好，较低分辨率的模型准确率高达94%。部署到一个大的测试区域，第一阶段模型产生许多假阳性检测。第二阶段，更高分辨率的模型在过滤这些信息方面显示出有希望的结果，同时保留了真正的阳性信息，将整体精度提高到42%，因此人类审查变得可行。在部署区域中，我们发现了五个新的重工业站点，这些站点不在训练数据中。这表明，该方法可以用来补充现有的重工业网站的数据集。
Abstract The effects of anthropogenic aerosol, solid or liquid particles suspended in the air, are the biggest contributor to uncertainty in current climate perturbations. Heavy industry sites, such as coal power plants and steel manufacturers, large sources of greenhouse gases, also emit large amounts of aerosol in a small area. This makes them ideal places to study aerosol interactions with radiation and clouds. However, existing data sets of heavy industry locations are either not public, or suffer from reporting gaps. Here, we develop a supervised deep learning algorithm to detect unreported industry sites in high-resolution satellite data, using the existing data sets for training. For the pipeline to be viable at global scale, we employ a two-step approach. The first step uses 10 m resolution data, which is scanned for potential industry sites, before using 1.2 m resolution images to confirm or reject detections. On held-out test data, the models perform well, with the lower resolution one reaching up to 94% accuracy. Deployed to a large test region, the first stage model yields many false positive detections. The second stage, higher resolution model shows promising results at filtering these out, while keeping the true positives, improving the precision to 42% overall, so that human review becomes feasible. In the deployment area, we find five new heavy industry sites which were not in the training data. This demonstrates that the approach can be used to complement existing data sets of heavy industry sites.