| 基于粒子群优化XGBoost模型的PM2.5质量浓度反演 |
| 摘要点击 3188 全文点击 670 投稿时间：2024-07-26 修订日期：2024-09-25 |
| 查看HTML全文
查看全文 查看/发表评论 下载PDF阅读器 |
| 中文关键词 PM2.5 机器学习 反演 气溶胶光学厚度（AOD） XGBoost模型 影响因素 |
| 英文关键词 PM2.5 machine learning inversion aerosol optical depth（AOD） XGBoost model influencing factors |
| DOI 10.13227/j.hjkx.202407279 |
|
| 中文摘要 |
| PM2.5作为大气污染的主要污染源,对人体健康构成了严重威胁,研究PM2.5质量浓度估算方法有助于识别污染源,优化空气质量管理措施,进而有效改善城市环境质量. 为了获得大范围PM2.5质量浓度空间分布,提高PM2.5估算精度,提出一种粒子群优化XGBoost的模型（PSO-XGB）,引入粒子群优化算法（PSO）对XGBoost参数进行优化,通过集成中分辨率成像光谱仪（MODIS）的气溶胶光学厚度产品（AOD）和气象数据构建基于PSO-XGB的PM2.5质量浓度反演模型,随后对2022年全国PM2.5质量浓度数据分年度和季节进行反演,并使用十折交叉验证法评估PSO-XGB模型性能,最后使用全国7 a和仅1 a的PM2.5质量浓度数据分别输入模型进行训练,分析数据量对模型性能的影响. 结果表明,PSO-XGB模型能够有效反演PM2.5质量浓度,且整体R2达到0.9以上,其中冬季的反演效果最好,R2为0.98、秋季R2为0.96、夏季R2为0.90及春季R2为0.89. 同时通过对比分析得出,数据量的多少对于优化模型的反演性能基本没有影响,而将数据按时间序列划分为适当的段,即划分季节,能够更准确地评估模型性能的稳定性和适用性. |
| 英文摘要 |
| As a major source of air pollution, PM2.5 poses a serious threat to human health, and the study of PM2.5 concentration estimation methods helps to identify pollution sources, optimize air quality management measures, and effectively improve the quality of the urban environment. To obtain the spatial distribution of PM2.5 mass concentration over a large range and improve the accuracy of PM2.5 estimation, a model of particle swarm optimized XGBoost （PSO-XGB） was proposed, and a particle swarm optimization algorithm （PSO） was introduced to optimize the parameters of XGBoost. By integrating the aerosol optical depth product （AOD） from the moderate resolution imaging spectroradiometer （MODIS） and meteorological data, the PSO-XGB-based PM2.5 mass concentration inversion model was constructed, followed by inversion of the national PM2.5 mass concentration data in 2022 by year and season, and the PSO-XGB model performance was evaluated using the ten-fold cross-validation method. Finally, the national PM2.5 mass concentration data of seven years and only one year were used to input into the model for training, respectively, to analyze the effect of the amount of data on model performance. The results showed that the PSO-XGB model was able to effectively invert PM2.5 mass concentration, and the overall R2 reached more than 0.9, of which the best inversion effect was 0.98 in winter, 0.96 in autumn, 0.90 in summer, and 0.89 in spring. Simultaneously, the comparative analysis showed that the amount of data had no effect on the inversion performance of the optimization model, while dividing the data into appropriate chunks by time series, or dividing seasons, could more accurately assess the stability and applicability of the performance of the model. |
|
|
|
