Xiong Qinqing, Wang Wenju, Wang Mingya, Zhang Chunhui, Zhang Xuechun, Chen Chun, Wang Mingshi
College of Resource and Environment, Henan Polytechnic University, Jiaozuo 454003, China.
Henan Key Laboratory for Environmental Monitoring Technology, Zhengzhou 450004, China.
iScience. 2022 Nov 23;25(12):105658. doi: 10.1016/j.isci.2022.105658. eCollection 2022 Dec 22.
Current approaches to ozone prediction using hybrid neural networks are numerous but not perfect. Decomposition algorithms ignore the correlation between predictors and ozone, and feature extraction methods rarely select appropriate predictors in terms of correlation, especially for VOCs. Therefore, this study proposes a hybrid neural network model SOM-NARX based on the correlation of predictors. The model is based on MIC to filter predictors, using SOM to make predictors as feature sequences and using NARX networks to make predictions. Data from the JCDZURI site were used for training, testing, and validation. The results show that the correlation of the predictors, classification numbers of SOM, neuron numbers, and delay steps can affect prediction accuracy. Model comparison shows that the SOM-NARX model has 13.82, 10.60, 6.58% and 12.05, 9.44, 68.14% RMSE, MAE, and MAEP in winter and summer, which is smaller than CNN-LSTM, CNN-BiLSTM, CNN-GRU, SOM-LSTM, SOM-BiLSTM, and SOM-GRU.
当前使用混合神经网络进行臭氧预测的方法众多但并不完美。分解算法忽略了预测变量与臭氧之间的相关性，并且特征提取方法很少根据相关性选择合适的预测变量，尤其是对于挥发性有机化合物（VOCs）而言。因此，本研究提出了一种基于预测变量相关性的混合神经网络模型SOM-NARX。该模型基于互信息系数（MIC）来筛选预测变量，使用自组织映射（SOM）将预测变量转换为特征序列，并使用NARX网络进行预测。来自JCDZURI站点的数据用于训练、测试和验证。结果表明，预测变量的相关性、SOM的分类数、神经元数量和延迟步长会影响预测精度。模型比较表明，SOM-NARX模型在冬季和夏季的均方根误差（RMSE）、平均绝对误差（MAE）和平均绝对百分比误差（MAEP）分别为13.82%、10.60%、6.58%和12.05%、9.44%、68.14%，低于卷积神经网络-长短期记忆网络（CNN-LSTM）、卷积神经网络-双向长短期记忆网络（CNN-BiLSTM）、卷积神经网络-门控循环单元（CNN-GRU）、自组织映射-长短期记忆网络（SOM-LSTM）、自组织映射-双向长短期记忆网络（SOM-BiLSTM）和自组织映射-门控循环单元（SOM-GRU）。
Zotero 插件
