引用本文: | 王淑莹, 许纯领, 尹翠芳,李鹏帅.OPAQ系统两种模式对O3预报准确率的探讨[J].环境监控与预警,2020,12(2):13-16 |
| WANG Shu-ying,XU Chun-ling , YIN Cui-fang, LI Peng-shuai.Discussion on the Accuracy of O3 Prediction by Two Modules of OPAQ System[J].Environmental Monitoring and Forewarning,2020,12(2):13-16 |
|
|
摘要: |
以江苏省宿迁环境监测中心OPAQ系统为例,基于人工神经网络算法的OPAQ空气质量预报系统的2种模式对O<sub>3</sub>预报准确率的进行了分析,结果表明,趋势最优模式(RMSE模式)对预报当天及未来3d的预报值与监测值的相关性系数均>0.78,相对误差在25%以下,在预测当天及未来24、48及72h优-良天的预测准确率较高,分别为88.8%、87.2%、86.3%及84.7%,在预测轻度污染-重度污染的准确率较低;极值最优模式(SI模式)对预报当天及未来3 d的预报值与监测值的相关性系数(R)均>0.76,相对误差<32%,预测未来24和48 h的轻度污染-中度污染的级别准确率>60%。OPAQ系统的极值最优模式(SI模式)更适合作为夏季ρ(O<sub>3</sub>)较高时的预测工具。 |
关键词: 人工神经网络算法 空气质量预报业务系统 O3 预报 准确率 |
DOI: |
分类号:X839.2 |
文献标识码:B |
基金项目: |
|
Discussion on the Accuracy of O3 Prediction by Two Modules of OPAQ System |
WANG Shu-ying,XU Chun-ling , YIN Cui-fang, LI Peng-shuai
|
Abstract: |
In this paper, two models of OPAQ air quality prediction system based on artificial neural network algorithm are used to analyze the accuracy of O<sub>3</sub> prediction. Taking the OPAQ system of Jiangsu Suqian Environmental Center as an example, the results show that the correlation coefficients R of RMSE model for predicting the current day and the next three days are above 0.78 and the relative errors are below 25%. The prediction accuracy of RMSE model for the current day and the 24 hour, 48 hour and 72 hour excellent good days is high, which are 88.8%, 87.2%, 86.3% and 84.7% respectively. The accuracy of RMSE model for predicting the light heavy pollution is low. The correlation coefficients R of the extreme optimal model (SI model) for predicting the current day and the next three days are above 0.76, and the relative errors are below 32%. The accuracy of predicting the level of mild moderate pollution in the next 24 hours and 48 hours is above 60%. In summary, the extreme optimal model (SI model) of OPAQ system is more suitable as a prediction tool when the concentration of O<sub>3</sub> is high in summer. |
Key words: Neural network algorithm OPAQ system Ozone Forecast Accuracy |