| 利用人工神经网络对空气中O3浓度进行预测 |
| |
| 引用本文： | 万显烈,杨凤林,王慧卿.利用人工神经网络对空气中O3浓度进行预测[J].中国环境科学,2003,23(1):110-112. |
| |
| 作者姓名： | 万显烈 杨凤林 王慧卿 |
| |
| 作者单位： | 1. 大连理工大学环境工程学院,辽宁,大连,116012
2. 大连市环境监测中心,辽宁,大连,116023 |
| |
| 摘 要： | 将人工神经网络应用于对空气中O3的浓度预测,提出了完整的预测模型,选取风速、风向、相对湿度、云量、平均气温、最高气温等6项气象因子作为输入量,经过两个月的预测实验,结果表明,实测值与预测值的平均相对误差为21.49%,相关系数为0.837.表明人工神经网络对O3的浓度预测是一种有效的工具.
|
| 关 键 词： | 人工神经网络 O3 浓度 预测 |
| 文章编号： | 1000-6923(2003)01-0110-03 |
| 修稿时间： | 2002年5月11日 |
The approach of artificial neural network applied in ambient ozone forecast |
| |
| WAN Xian-lie,YANG Feng-lin,WANG Hui-qing.The approach of artificial neural network applied in ambient ozone forecast[J].China Environmental Science,2003,23(1):110-112. |
| |
| Authors: | WAN Xian-lie YANG Feng-lin WANG Hui-qing |
| |
| Affiliation: | WAN Xian-lie1,YANG Feng-lin1,WANG Hui-qing2 |
| |
| Abstract: | In view of the complex mechanism of O3 formation in air, artificial neural network is applied in forecasting O3 concentration in air; and the integrated forecast model is suggested. Six meteorological factors, such as wind velocity, wind direction, relative humidity, cloud, average temperature, highest temperature, are selected as input variants. After two months forecast test, the results show mean relative error of O3 concentration between forecast value and actual value is 21.49%, correlate coefficient is 0.837. Artificial neural network is a effective method to forecast the O3 concentration. |
| |
| Keywords: | artificial neural network ozone concentration forecast |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
|
