干旱区研究

干旱区研究 ›› 2022, Vol. 39 ›› Issue (4): 1056-1065.doi: 10.13866/j.azr.2022.04.07

• 天气与应用气候 • 上一篇    下一篇

基于决策树模型的区域PM2.5污染管控时空识别——以关中地区为例

贾册1(),陈臻2,3,韩梅4()   

  1. 1.中国人民大学环境学院,北京 100872
    2.中国科学院科技战略咨询研究院,北京 100190
    3.中国科学院大学公共政策与管理学院,北京 100049
    4.陕西省环境调查评估中心,陕西 西安 710054
  • 收稿日期:2022-01-18 修回日期:2022-04-23 出版日期:2022-07-15 发布日期:2022-09-26
  • 通讯作者: 韩梅
  • 作者简介:贾册（1994-）,男,博士研究生,主要从事环境政策与管理. E-mail: adam-jia@qq.com
  • 基金资助:
    中国人民大学科学研究基金（中央高校基本科研业务费专项资金资助）项目成果(21XNH057);陕西省重点研发计划(2021SF-501)

Optimal time period for PM2.5 control based on decision tree model: A case study of Guanzhong, China

JIA Ce1(),CHEN Zhen2,3,HAN Mei4()   

  1. 1. School of Environment & Nature Resources, Renmin University of China, Beijing 100872, China
    2. Institutes of Science and Development, Chinese Academy of Sciences, Beijing 100190, China
    3. School of Public Policy and Management, University of Chinese Academy of Sciences, Beijing 100049, China
    4. Shaanxi Provincial Investigation and Ecological Assessment Center, Xi’an 710054, Shaanxi, China
  • Received:2022-01-18 Revised:2022-04-23 Online:2022-07-15 Published:2022-09-26
  • Contact: Mei HAN

RichHTML

5

PDF (PC)

230

赞

摘要：

以关中地区为研究区域,基于时空聚类和决策树模型提出一种简易的PM2.5污染管控时空识别方法。首先使用时空聚类算法对冬防期PM2.5浓度进行聚类,识别不同的PM2.5污染区域,基于不同区域的气象数据分别构建决策树模型,识别不同区域影响PM2.5浓度最不利扩散的气象条件,分析最不利气象条件下的PM2.5浓度变化情况,以此确定各区域需要进行污染管控的时间段。结果表明：（1） 时空聚类方法识别出关中地区PM2.5分布主要呈现出低海拔平原区域和海拔相对较高的山脉区域。（2） 决策树模型分析结果显示：高海拔区域在Ⅰ-10（1.57 h≤日照时数<7.88 h、最大风速<3.72 m·s-1）和Ⅰ-11（日照时数<1.57 h、最大风速<3.72 m·s-1）两类气象条件下,区域的PM2.5浓度保持较高水平;低海拔区域在Ⅱ-10（小型蒸发量≥0.96 mm、平均相对湿度≥45.38%、日照时数<8.55 h、平均风速≥2.43 m·s-1）和Ⅱ-11（小型蒸发量<0.96 mm）两类气象条件下,区域的PM2.5浓度保持较高水平。（3） 回归结果显示,关中地区低海拔区域和高海拔区域在最不利气象条件下,PM2.5浓度平均会持续上升4.76 d,直至最高浓度。

关键词: 决策树模型, PM2.5, 分区管控, 重污染

Abstract:

A simple spatiotemporal identification method for PM2.5 pollution control based on a machine learning model is proposed. A spatiotemporal clustering algorithm was used to cluster PM2.5 in the winter prevention period, and different PM2.5 polluted areas were identified. Furthermore, a decision tree model was constructed using the meteorological data of different areas to identify the most unfavorable influences on PM2.5 concentration in different areas. The changes in PM2.5 under the most unfavorable meteorological conditions were analyzed, and the optimal time period for PM2.5 pollution control in the different study areas was determined. Using the Guanzhong area as an example, the correlation analysis of the spatial clustering of mean daily PM2.5 in winter showed that the Guanzhong area is mainly divided into a low-altitude plain area (the Guanzhong Plain) and a relatively high mountain range. The classification tree model was then constructed, using the meteorological data of the plain and mountain areas. The analysis showed that the mountain elevations have a higher PM2.5 concentrations under Ⅰ-10 (1.57 h ≤ sunshine hours < 7.88 h; maximum wind speed < 3.72 m·s-1) and Ⅰ-11 (sunshine hours < 1.57 h; maximum wind speed < 3.72 m·s-1) meteorological conditions; low-altitude areas have a higher PM2.5 concentrations under Ⅱ-10 (small-scale evaporation ≥ 0.96 mm; average relative humidity ≥ 45.38%; sunshine hours < 8.55 h; average wind speed ≥ 2.43 m·s-1) and Ⅱ-11 (small evaporation < 0.96 mm) meteorological conditions. Lastly, the regression analysis results showed that in the mountain elevations area in the Ⅰ-10, Ⅰ-11 category and the plain altitude area under the most unfavorable meteorological conditions (Ⅱ-10 and Ⅱ-11 category), the PM2.5 concentration will continue to increase for 4.76 days on average, before reaching a maximum concentration.

Key words: decision tree model, PM2.5, meteorological classification, heavy pollution