The main objective of the present study was to predict the associated health endpoint of PM_2.5 using an artificial neural network (ANN). The neural network used in this work contains a hidden layer with 27 neurons, an input layer with 8 parameters, and an output layer. First, the artificial neural network was implemented with 80% of data for training then with 90% of data for training. The value of R for the data validation of these two networks was 0.80 and 0.83 respectively. The World Health Organization AirQ ⁺ software was utilized for assessing Health effects of PM_2.5 levels. The mean PM_2.5 over the 9-year study period was 63.27(μg/m³), about six times higher than the WHO guideline. However, the PM_2.5 concentration in the last year decreased by about 25% compared to the first year, which is statistically significant (P-value = 0.0048). This reduced pollutant concentration led to a decrease in the number of deaths from 1785 in 2008 to 1059 in 2016. Moreover, a positive correlation was found between PM_2.5 concentration and temperature and wind speed. Considering the importance of predicting PM_2.5 concentration for accurate and timely decisions as well as the accuracy of the artificial neural network used in this study, the artificial neural network can be utilized as an effective instrument to reduce health and economic effects.

本研究的主要目的是使用人工神经网络 (ANN)预测 PM _2.5的相关健康终点。这项工作中使用的神经网络包含一个具有 27 个神经元的隐藏层、一个具有 8 个参数的输入层和一个输出层。首先，人工神经网络使用 80% 的数据进行训练，然后使用 90% 的数据进行训练。这两个网络的数据验证的 R 值分别为 0.80 和 0.83。世界卫生组织 AirQ  ⁺ 软件用于评估 PM _2.5水平对健康的影响。9 年研究期间的平均 PM _2.5为 63.27(μg/m ³ )，比 WHO 指南高出约 6 倍。然而，总理去年的_2.5浓度与第一年相比下降了约25%，具有统计学意义（P值=0.0048）。污染物浓度的降低导致死亡人数从 2008 年的 1785 人减少到 2016 年的 1059 人。此外，发现 PM _2.5浓度与温度和风速之间存在正相关关系。考虑到预测 PM _2.5浓度对于准确及时决策的重要性以及本研究中使用的人工神经网络的准确性，人工神经网络可用作减少健康和经济影响的有效工具。