基于多机器学习算法耦合的空气质量数值预报订正方法研究及应用
Research and application of an ensemble forecasting method based on coupled multi-machine learning algorithms
-
摘要: 应用多种机器学习算法进行时空耦合从而建立一种新的多模式集合预报订正方法(简称ET-BPNN),对四种常规污染物(NO2、O3、PM2.5和PM10)的空气质量模型预报结果进行订正。先利用随机森林、极端随机树和梯度提升树算法进行第一次优化,采用四个空气质量数值预报模式(CMAQ、CAMx、NAQPMS和WRFChem)的多尺度污染物浓度预报数据、中尺度天气模式(WRF)的气象因子预报数据(包括2m温度、2m湿度、10m风速、10m风向、气压和小时累计降水量)以及污染物浓度观测数据,训练结果进入基于均方根误差的择优选择器,选取三种决策树算法中优化效果最好的算法,再利用BP神经网络对数据集进行二次优化,最终通过加权平均获得集合模式订正预报结果。结果表明:①ET-BPNN算法与四个模式集合平均算法相比,对四项污染物预报结果订正后的均方根误差分别减小了30.4%、18.9%、43.3%和38.1%;②ET-BPNN算法的优化效果较随机森林、极端随机树和梯度提升树三个机器学习算法有明显提升,与极端随机树相比,订正后的均方根误差分别降低了42.7%、20.1%、19.7%和9.7%;③ET-BPNN在较易发生污染的秋冬季对PM2.5的预报具有明显的优化效果;此外,该算法明显缩小了不同站点预报和不同预报时效之间的偏差,具有较好的鲁棒性;④对O3_8h和PM2.5污染而言,经ET-BPNN优化后的预报结果能够更好地把握污染过程,对污染物峰值浓度的预报也较集合平均更为准确。Abstract: In order to optimize and evaluate the air quality forecasting accuracies of four kinds of pollutants (NO2, O3, PM2.5 and PM10) in Shanghai, a new spatial-temporal coupling ensemble forecasting method (ET-BPNN, short for ensemble tree- back propagation neural network) was established based on four machine learning algorithms. Firstly, the forecasting results are optimized using random forest, extreme random tree and gradient boosting decision tree, with input features selected from multi-scale forecasting data based on four air quality numerical forecasting models (CMAQ, CAMx, NAQPMS and WRFChem), the meteorological data of mesoscale weather model (WRF, including 2m temperature, 2m humidity, 10m wind speed, 10m wind direction, atmospheric pressure and hourly accumulated precipitation) and observations. The best machine learning algorithm was chosen by comparing the root mean square error. Secondly, further optimization was proceeded with BP neural network. Results show that: (1) Compared with the traditional ensemble mean algorithm, the root mean square error (RMSE) between the ET-BPNN simulation and observed hourly concentration of NO2, O3, PM2.5 and PM10 are reduced by 51.9%, 60.1%, 63.0% and 60%, respectively. (2) The optimization effect of ET-BPNN algorithm is significantly improved compared with three machine learning algorithms, and the RMSE of NO2, O3, PM2.5 and PM10 are reduced by 42.7%, 20.1%, 19.7% and 9.7%, respectively. (3) ET-BPNN shows an effective optimization on PM2.5 forecasting in autumn and winter when its concentration is higher, with decreased forecasting bias found at different stations. (4) The ET-BPNN also improves the forecasting performance on pollution process of O3_8h and PM2.5, with peak value simulated more accurate than the traditional ensemble average algorithm.
-
Key words:
- machine learning /
- ensemble mean /
- ET-BPNN
点击查看大图
计量
- 文章访问数: 151
- HTML全文浏览量: 18
- PDF下载量: 34
- 被引次数: 0