| 海口市臭氧浓度统计预报模型的构建与效果评估 |
| 摘要点击 5103 全文点击 615 投稿时间：2023-06-05 修订日期：2023-08-06 |
| 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 臭氧（O3） 多元线性回归 支持向量机 BP神经网络 预报评估 海口市 |
| 英文关键词 ozone（O3） multiple linear regression support vector machine BP neural network assessment of forecast results Haikou City |
|
| 中文摘要 |
| 主要利用2015~2020年海口市臭氧（O3）浓度资料和ERA5再分析资料,基于污染物浓度控制方程挑选出海口市O3-8h浓度（日最大8 h滑动平均）的15个关键预报因子,构建了多元线性回归模型（MLR）、支持向量机模型（SVM）和BP神经网络模型（BPNN）,并对2021年海口市O3-8h浓度进行预测和效果检验.结果表明,O3-8h浓度与关键预报因子的相关系数绝对值主要分布在0.2~0.507之间,其中1 000 hPa的相对湿度（RH1000）和风向（WD1000）,875 hPa的经向风（v875）的相关系数绝对值超过了0.4,具有较好的指示作用.3个预报模型基本能预报出海口市O3-8h浓度冬半年偏高,夏半年偏低的变化趋势,其中BPNN模型的标准误差（RMSE）数值最小（22.29 μg·m-3）.实测值与3个统计模型预报值的相关系数从大到小排列为：0.733（BPNN）>0.724（SVM）>0.591（MLR）,均通过了99.9%的信度检验.O3-8h浓度等级预报的结果检验表明,3个预报模型的TS评分均随着O3-8h浓度等级的上升而下降,而漏报率（PO）和空报率（NH）随着O3-8h浓度等级的上升而上升.SVM和BPNN模型在3个等级预报中TS评分均略高于MLR模型,特别是在轻度污染等级,TS评分还维持在70%以上,具有较好的预报性能. |
| 英文摘要 |
| This study selected 15 key predictors of the maximum of 8-hour averaged ozone (O3) concentration (O3-8h), using the O3 concentration of Haikou and ERA5 reanalysis data from 2015 to 2020, and constructed a multiple linear regression (MLR) model, support vector machine (SVM) model, and BP neural network (BPNN) model, to predict and test the O3-8h concentration of Haikou in 2021. The results showed that the absolute value of correlation coefficients between the O3-8h and related key prediction factors was mainly among 0.2 and 0.507. The 1 000 hPa relative humidity (RH1000), wind direction (WD1000), and 875 hPa meridional wind (v875) showed a good indicative effect on the O3-8h, with the absolute correlation value exceeding 0.4. The three prediction models could predict the seasonal variation in the O3-8h in Haikou, which was larger in the winter half year and smaller in the summer half year. The root mean square error(RMSE) was the smallest (22.29 μg·m-3) in the BPNN model. The correlation coefficients between the predicted values of three statistical models and observations were ranked as 0.733 (BPNN) > 0.724 (SVM) > 0.591 (MLR), all passing the 99.9% significance test. For the prediction of the O3-8h level, we found that TS scores of these three prediction models decreased with the increase in O3-8h concentration level. Relatively, the point over rate and not hit rate increased with the rise in O3-8h concentration level. TS scores of the SVM and BPNN model were relatively larger than those of MLR, especially in the light pollution level with TS scores remaining above 70%, indicating a better prediction capability. |
|
|
|
