| 融合EOF分解及CNN-LSTM神经网络的PM2.5预测 |
| 摘要点击 1274 全文点击 165 投稿时间：2024-01-04 修订日期：2024-04-18 |
| 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 气象特征 EOF分解 PM2.5浓度 CNN神经网络 LSTM神经网络 预测 |
| 英文关键词 meteorological characteristics EOF decomposition PM2.5 concentration CNN neural network LSTM neural network forecast |
|
| 中文摘要 |
| 利用2016~2020年太原市地面气象资料和环境空气质量资料,分析了太原市PM2.5浓度的时间和空间的变化特征,运用EOF分解诊断分析方法,对太原市PM2.5浓度时空变化特征进行了研究,同时利用随机森林模型分析了气象因子的重要性,建立基于CNN-LSTM神经网络的PM2.5浓度预报模型. 结果表明,2016~2020年太原市区PM2.5浓度年均值总体上呈现出逐年减少的趋势,高值主要出现在11月、12月、1月和2月,18：00至翌日的02：00易出现PM2.5浓度峰值,PM2.5浓度年均值呈现自西北向东南逐渐增加的趋势. PM2.5浓度的EOF分解：模态1特征向量的方差贡献率为49.4%,模态2特征向量的方差贡献率为30.8%,以晋源-巨轮-南寨为界,负值区主要在东南,中心位于东南部的小店,正值区则主要位于西北,其中心位于金胜. PM2.5浓度与相对湿度、露点温度之间显著正相关；与风速、降水量和混合层高度主要表现为负相关,与通风量和自净能力也主要呈现一般负相关,与气温相关性不明显. 相对湿度、露点温气压、度和混合层高度在四个季节特征排序中均占较为重要的地位,其次是风速、风向、通风量和自净能力重要程度相对一般. 采用CNN-LSTM模型建模,PM2.5浓度预测的R2在春、夏、秋和冬这4个季节分别为0.805、0.826、0.897和0.901,4个季节R2均在0.8以上,在4个季节CNN-LSTM模型的预测残差值均近似于正态分布,模型的绝对误差控制在10 μg·m-3以下的预测结果夏季最高达到81.2%,秋季和春季次之,分别为75.9%和62.9%,冬季表现一般,有51.5%预测结果的绝对误差低于10 μg·m-3. |
| 英文摘要 |
| Based on the surface meteorological data and ambient air quality data of Taiyuan from 2016 to 2020, the temporal and spatial variation characteristics of PM2.5 concentration in Taiyuan were analyzed. The temporal and spatial variation characteristics of PM2.5 concentration in Taiyuan were studied using the EOF decomposition diagnostic analysis method. At the same time, the importance of meteorological factors was analyzed using a random forest model, and a PM2.5 concentration prediction model based on the CNN-LSTM neural network was established. The results showed that from 2016 to 2020, the annual mean PM2.5 concentration in the urban area of Taiyuan generally exhibited a decreasing trend from year to year, and the high value mainly appeared in November, December, January, and February. From 18：00 to 02：00 of the next day, the peak value of PM2.5 concentration was easily reached, and the annual average value of PM2.5 concentration gradually increased from northwest to southeast. The EOF decomposition of PM2.5 concentration was as follows： the variance contribution rate of modal 1 eigenvector was 49.4%, and the variance contribution rate of modal 2 eigenvector was 30.8%. Considering Nanzhai-Julun-Jinyuan as the boundary, it was a positive area to the northwest and a negative area to the southeast. The positive center appeared in Jinsheng district, and the negative center appeared in Xiaodian in the southeast. PM2.5 concentration was positively correlated with relative humidity and dew point temperature. Moreover, it was mainly negatively correlated with wind speed, precipitation, and mixing layer height and generally negatively correlated with ventilation and self-purification capacity, with no significant correlations involving temperature. Relative humidity, dew point temperature, air pressure, humidity, and mixing layer height all played an important role in the ranking of the four seasonal characteristics, followed by wind speed, wind direction, ventilation volume, and self-purification capacity. Using the CNN-LSTM model for modeling, the R2 of PM2.5 concentration prediction was 0.805, 0.826, 0.897, and 0.901 in spring, summer, autumn, and winter, respectively. R2 was above 0.8 in all four seasons. The predicted residuals of the CNN-LSTM model in all four seasons were approximately normally distributed, and the absolute error of the model was controlled within 10 μg·m-3. The prediction results below 10 μg·m-3 reached a maximum of 81.2% in summer, followed by 75.9% and 62.9% in autumn and spring, respectively. The performance in winter was average, with 51.5% of the prediction results having an absolute error below 10 μg·m-3. |
|
|
|
