摘要
针对我国当前重污染天气PM2.5浓度的实时预报问题,该文提出了一种基于随机森林算法的PM2.5浓度实时预报方法,并利用此方法对北京市地面空气质量监测数据和气象数据进行分析,建立了基于随机森林算法的PM2.5浓度实时预报模型。实验证明,该模型能够对72h内PM2.5浓度进行较高精度的实时预报,通过使用Spark分布式计算框架,能够有效降低算法耗时,文章基于此模型与Spark分布式计算框架建立了PM2.5实时预报系统。
In order to study the real-time air quality forecasting system suitable for the heavy-polluted weather in China,a real-time forecasting method of PM2.5concentration based on random forest algorithm is put forward,using this algorithm to analyze the ground air quality monitoring data and meteorological data,a real-time forecasting model of PM2.5concentration based on random forest algorithm was established.The experimental results show that the model can predict the PM2.5concentration from 0to72 hours in real time and can reduce the time consuming of the algorithm by using the Spark distributed computing framework.Therefore,based on this model and Spark distributed computing framework the PM2.5real-time forecasting system was established.
出处
《测绘科学》
CSCD
北大核心
2017年第1期1-6,共6页
Science of Surveying and Mapping