| 利用PCA-kNN方法改进广州市空气质量模式PM2.5预报 |
| |
| 引用本文： | 汤静,王春林,谭浩波,邓雪娇,邓涛.利用PCA-kNN方法改进广州市空气质量模式PM2.5预报[J].热带气象学报,2019,35(1):125-134. |
| |
| 作者姓名： | 汤静 王春林 谭浩波 邓雪娇 邓涛 |
| |
| 作者单位： | 1.广州市气候与农业气象中心 广东 广州 511430 |
| |
| 基金项目： | 国家重点研发计划项目课题2016YFC0203305国家重点研发计划项目课题2016YFC0201901广州市产学研协同创新重大专项201604020028广东省气象局科技创新团队计划项目201704广东省气象局科研项目GRMC2017Q16广州市气象局科研项目201618 |
| |
| 摘 要： | 为了提高广州市PM2.5客观预报能力，采用主成分分析结合机器学习算法k近邻（PCA-kNN）方法，基于空气质量模式（CMAQ）预报产品、中尺度天气模式（GRAPES-MESO）预报产品和2017年上半年广州PM2.5观测实况，试验确定PCA-kNN方法的最佳参数方案，建立广州市空气质量模式PM2.5预报客观订正方法。结果表明:与CMAQ模式的PM2.5预报相比，在第1~3天预报时效上，PCA-kNN订正结果与实况的相关系数分别提高20%、15%、29%，均方根误差分别降低17%、16%、20%，平均偏差更接近0，PM2.5浓度等级TS评分接近或优于CMAQ预报，PCA-kNN订正结果优于CMAQ预报。机器学习算法PCA-kNN方法可有效改进广州市空气质量模式PM2.5预报，本研究对其他地区、其他污染物客观预报研究具有借鉴意义。
|
| 关 键 词： | PM2.5 空气质量模式 PCA-kNN |
| 收稿时间： | 2017-12-29 |
APPLICATION OF PCA-kNN METHOD IN IMPROVEMENT OF AIR QUALITY MODEL PM2.5 FORECASTING IN GUANGZHOU |
| |
| Institution: | 1.Guangzhou Climate and Agro-meteorology Center, Guangzhou 511430, China2.Guangdong Provincial Ecological Meteorological Center, Guangzhou 510640, China3.Institute of Tropical and Marine Meteorology/Guangdong Provincial Key Laboratory of Regional Numerical Weather Prediction, CMA, Guangzhou 510640, China |
| |
| Abstract: | In order to improve the ability of objective forecasting of PM2.5 in Guangzhou, a bias correction method combining principal component analysis and k nearest neighbor regression in machine learning (PCA-kNN) was proposed based on the outputs of air quality model (CMAQ), mesoscale numerical weather model (GRAPES-MESO) and PM2.5 observations in the first half of 2017. The parameter scheme for PCA-kNN was determined by parametric tests and then the relevant data of Guangzhou were used to evaluate the performance. Results showed that compared with CMAQ PM2.5 products, the PCA-kNN method performed better in 1~3 d forecast of PM2.5 daily mean: (1) the correlation coefficients between PCA-kNN outputs and PM2.5 observations increased by 20%, 15% and 29% respectively; (2) root mean square errors decreased by 17%, 16% and 20% respectively; (3) mean biases were closer to zero; and (4) TS scores of different PM2.5 concentration levels were comparable or better. By applying machine learning algorithm, the PCA-kNN method can effectively improve air quality model PM2.5 forecasting. This study has implications for objective forecasting and research of other areas and other pollutants. |
| |
| Keywords: | |
| 本文献已被 CNKI 等数据库收录！ |
| 点击此处可从《热带气象学报》浏览原始摘要信息 |
| 点击此处可从《热带气象学报》下载免费的PDF全文 |
|
