基于神经网络模型的绵阳市空气质量指数预测

Prediction of Mianyang Air Quality Index based on neural network model

随着工业化的不断推进和城市化不断的发展,空气质量变差的问题在全国范围内都变得普遍,空气质量指数(AQI)是反映空气中污染物程度的综合指标,通过Python语言编写RF模型、CNN-LSTM模型以及GRU模型分别对绵阳市2016-2021年的空气质量数据和气象数据进行训练,并预测出2022年1月1日至2022年1月7日的AQI具体值,对比预测值与真实值,结果显示RF模型准确率更高,因此RF模型更适合用于对AQI的预测,为防治大气污染提供更科学的方法.

With the continuous progress of industrialization and urbanization,the problem of air quality deterioration has become common across the country.The Air Quality Index(AQI)is a comprehensive index reflecting the degree of pollutants in the air.The RF model,CNN-LSTM model and GRU model were written in Python language to train the air quality data and meteorological data of Mianyang City from 2016 to 2021,and the specific value of AQI was predicted from January 1,2022 to January 7,2022.The predicted value was compared with the real value.The results show that the RF model has higher accuracy,so the RF model is more suitable for the prediction of AQI and can provide a more scientific method for the prevention and control of air pollution.