检索规则说明:AND代表“并且”;OR代表“或者”;NOT代表“不包含”;(注意必须大写,运算符两边需空一格)
检 索 范 例 :范例一: (K=图书馆学 OR K=情报学) AND A=范并思 范例二:J=计算机应用与软件 AND (U=C++ OR U=Basic) NOT M=Visual
机构地区:[1]贵州大学矿业学院,贵州 贵阳
出 处:《理论数学》2024年第6期447-459,共13页Pure Mathematics
摘 要:气溶胶光学厚度被广泛应用于PM2.5浓度估算中,受极端气候影响以及卫星传感器影响,AOD数据存在大量缺失,本文提出Prophet-LSTM + P-Bshade时空补值模型对MAIAC AOD数据进行补值并使用Catbooost模型结合AOD数据以及ERA5气象数据对中国2020年陆地区域的PM2.5浓度进行估算。结果表明:① Prophet-LSTM + P-Bshade时空补值模型精度明显优于传统补值方法,R、MASE和MAE分别为0.891、0.275和0.183。② Catboost模型在PM2.5浓度估算中比常用的其他机器学习等模型显示更高的估算精度,R、MASE和MAE分别为0.93、15.89 μg∙m−3和10.54 μg∙m−3。③ 中国陆地区域2020年的PM2.5浓度在季节尺度分布上明显,整体呈现冬季 > 春季 > 秋季 > 夏季的季节分布特点。在空间分布上,PM2.5浓度整体呈现东部地区较高,塔里木盆地区域局部较高的特点。Aerosol optical thickness is widely used in PM2.5 concentration estimation, due to the influence of extreme climate and satellite sensors, there are a large number of missing AOD data, this paper proposes the Prophet-LSTM + P-Bshade spatiotemporal compensation model to supplement the MAIAC AOD data, and uses the Catbooost model combined with AOD data and ERA5 meteorological data to estimate the PM2.5 concentration in the land area of China in 2020. The results show that: (1) The accuracy of the Prophet-LSTM + P-Bshade spatiotemporal compensation model is significantly better than that of the traditional compensation method, with R, MASE and MAE of 0.891, 0.275 and 0.183, respectively. (2) The Catboost model showed higher estimation accuracy than other commonly used machine learning models in PM2.5 concentration estimation, with R, MASE and MAE of 0.93, 15.89 μg∙m−3 and 10.54 μg∙m−3, respectively. (3) PM2.5 concentrations in China’s land areas in 2020 were significantly distributed on a seasonal scale, showing the seasonal distribution characteristics of winter > spring > autumn > summer. In terms of spatial distribution, PM2.5 concentrations were higher in the eastern region and higher in the Tarim Basin.
关 键 词:MAIAC AOD Prophet-LSTM + P-Bshade 时空补值 PM2.5 Catbooost
分 类 号:X51[环境科学与工程—环境工程]
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在链接到云南高校图书馆文献保障联盟下载...
云南高校图书馆联盟文献共享服务平台 版权所有©
您的IP:216.73.216.38