基于深度学习方法的PM2.5精细化时空估算模型

提出一种基于深度学习方法的地面PM_2.5浓度时空估算模型（PM_2.5-DNN），该模型基于葵花-8卫星反演的AOD数据，结合PM_2.5监测站和气象站点观测数据对北京市地面PM_2.5浓度进行了逐时的高精度模拟，同时将PM_2.5-DNN模型的模拟性能与当前的主流方法进行了对比研究.结果表明，使用PM_2.5-DNN模型估算的北京地区1km分辨率每小时地面PM_2.5浓度与地表监测站观测数据对比的一致性较好，模型估算精度可达到R²=0.88，性能优于当前的主流方法.本文所提出的方法适用于区域尺度PM_2.5浓度时空分布细粒度建模与估算，采用端到端的训练方式构建模型，为精细的PM_2.5浓度估算提供了一个简便而有效的方法模型.

Refined spatiotemporal estimation model of PM2.5 based on deep learning method

The concentration distribution of fine particulate matter (PM_2.5) on the surface of the atmosphere has a strong temporal and spatial heterogeneity. Due to the limited spatial coverage of traditional PM_2.5 monitoring sites, it is difficult to reflect the complexity of PM_2.5 concentration in time and space. This paper proposed a temporal and spatial prediction model of ground PM_2.5 concentration based on deep learning methods(PM_2.5-DNN). Based on the AOD data from Kuihua-8satellite and the observation data from PM_2.5 monitoring and meteorological station, hourly high-precision simulations of the surface PM_2.5 concentration in Beijing had been carried out. The results show that the 1km resolution hourly ground PM_2.5 concentration in Beijing area estimated by the PM_2.5-DNN model had good consistency with the observation data from the surface monitoring station. The model estimation accuracy could reach R²=0.88, which was better than the performance of current mainstream method. The method proposed in this paper was suitable for fine-grained modelling and estimation of the temporal and spatial distribution of PM_2.5 concentration at a regional scale. The end-to-end training method is used to construct the model, which provides a simple and effective method model for fine PM_2.5 concentration estimation.