Fine particulate matter (PM_2.5) has a considerable impact on the environment, climate change, and human health. Herein, we introduce a deep neural network model for deriving ground-level, hourly PM_2.5 concentrations by Himawari-8 aerosol optical depth, meteorological variables, and land cover information. A total of 151,726 records were collected from 313 ground-level PM_2.5 monitoring stations (spread across the North China Plain) to calibrate and test the proposed model. The sample- and site-based cross-validation yielded satisfactory performance, with correlation coefficients > 0.8 (R = 0.86 and 0.83, respectively). Furthermore, the variation in mean ground-level hourly PM_2.5 concentrations, using 2017 data, showed that the proposed method could be applied for spatiotemporal continuous PM_2.5 monitoring. This study will serve as a reference for the application of geostationary meteorological satellite to perform ground-level PM_2.5 estimation and the utilization in atmospheric monitoring.

细颗粒物（PM _2.5）对环境，气候变化和人类健康具有相当大的影响。在这里，我们介绍了一个深度神经网络模型，该模型可通过Himawari-8气溶胶光学深度，气象变量和土地覆盖信息来推导地面每​​小时的PM _2.5浓度。从313个地面PM _2.5监测站（分布在华北平原）收集了151,726条记录，以校准和测试该模型。基于样本和基于站点的交叉验证产生了令人满意的性能，相关系数> 0.8（ 分别为R = 0.86和0.83）。此外，平均每小时地面PM _2.5的变化使用2017年的数据进行浓度估算，表明该方法可用于时空连续PM _2.5监测。这项研究将为应用地球静止气象卫星进行地面PM _2.5估算和在大气监测中的利用提供参考。