Luo Yi, Deng Qiong-Fei, Yang Kun, Yang Yang, Shang Chun-Xue, Yu Zhen-Yu
School of Information Science and Technology, Yunnan Normal University, Kunming 650500, China.
Engineering Research Center of GIS Technology in Western China of Ministry of Education, Kunming 650500, China.
Huan Jing Ke Xue. 2018 Jul 8;39(7):3003-3013. doi: 10.13227/j.hjkx.201709174.
Two decades of PM pollution has seriously hindered China's sustainable development. However, relevant research of PM has been hindered because of the lack of long-term historical monitoring data. Therefore, ground observations of PM concentration from 2013 to 2016 in four typical regions of China and the MODIS aerosol optical thickness data, boundary layer height, temperature, and other meteorological data from 2000 to 2016 were used as the basic data. A combined simulation model was constructed by combining the two algorithms of backward artificial neural network and support vector regression and obtains the PM concentration history for the past 20 years using geospatial analysis technology. The results demonstrate that the combination model is better than the single model, with lower error and higher generalization ability. The spatial-temporal analysis results show that the concentration of PM continued to increase in the Beijing-Tianjin-Hebei region and in the three northeastern provinces of China, the PM concentration decreased slowly in the Pearl River Delta, the pollution range of PM in three of the research areas showed an expanding trend, and the PM concentration and pollution range remained stable in the Yangtze River Delta. In 2012, the concentration of PM in the four study areas decreased and the pollution range narrowed, but the PM concentration rose slightly after that decline and the high pollution range narrowed during 2013-2016, which with the country to take PM regional defense and other governance measures.
二十年的颗粒物污染严重阻碍了中国的可持续发展。然而，由于缺乏长期历史监测数据，有关颗粒物的相关研究受到了阻碍。因此，将中国四个典型地区2013年至2016年的颗粒物浓度地面观测数据以及2000年至2016年的中分辨率成像光谱仪（MODIS）气溶胶光学厚度数据、边界层高度、温度等气象数据作为基础数据。通过结合反向人工神经网络和支持向量回归这两种算法构建了一个组合模拟模型，并利用地理空间分析技术获得了过去20年的颗粒物浓度历史数据。结果表明，组合模型优于单一模型，具有更低的误差和更高的泛化能力。时空分析结果表明，京津冀地区和中国东北三省的颗粒物浓度持续上升，珠江三角洲地区的颗粒物浓度缓慢下降，三个研究区域的颗粒物污染范围呈扩大趋势，长江三角洲地区的颗粒物浓度和污染范围保持稳定。2012年，四个研究区域的颗粒物浓度下降且污染范围缩小，但在那次下降之后颗粒物浓度略有上升，2013 - 2016年期间高污染范围缩小，这与国家采取的颗粒物区域联防等治理措施有关。
