1 School of Economics and Management, East China University of Technology, Nanchang 330013, China
2 School of Science, East China University of Technology, Nanchang 330013, China
Show less
文章历史+
Received
Published
2025-01-27
2026-01-08
Online Date
2026-05-27
PDF (15706K)
摘要
为了提高空气质量指数预测的准确性,引入Logistic混沌映射策略、折射反向学习策略、自适应权重、Levy飞行策略和柯西变异策略对共生生物搜索(symbiotic organisms search,SOS)算法进行了改进,将改进算法对变分模态分解(variational mode decomposition,VMD)算法和长短期记忆神经网络(long short-term memory,LSTM)模型的参数进行优化,提出了改进的共生生物搜索(modified symbiotic organisms search,MSOS)算法优化的ARIMAX-VMD-LSTM误差修正空气质量指数组合预测模型。首先采用递归特征消除(recursive feature elimination,RFE)筛选特征;接着利用引入外生变量的自回归移动平均(autoregressive integrated moving average with exogenous input,ARIMAX)模型捕捉空气质量时间序列中的线性关系;其次采用VMD算法对非线性且复杂度较高的ARIMAX误差进行分解,得到若干个模态分量和一个残差余量;然后利用MSOS算法优化的LSTM模型分别对分解的子序列进行预测,捕捉ARIMAX误差中的非线性关系;最后叠加各子序列预测结果得到误差预测结果,并对ARIMAX预测值进行修正。仿真实验结果表明,融合深度学习与统计学算法的组合模型能进一步提高预测精度,变分模态分解不仅能大大降低误差序列的非线性和复杂度,而且还能提高稳定性,误差修正能进一步提高模型的预测能力。与其他模型对比,该组合预测模型的各评价指标均为最优,具有更高的预测精度和泛化性能,为空气质量预测提供了新的方法。
Abstract
In order to improve the accuracy of air quality information prediction, Logistic chaotic mapping strategy, refraction reverse learning strategy, adaptive weights, Levy flight strategy and Cauchy mutation strategy were introduced to improve the symbiotic organisms search (SOS) algorithm. The parameters of variational mode decomposition (VMD) algorithm and long short-term memory(LSTM) neural network model were optimized by the improved algorithm, and the ARIMAX-VMD-LSTM error correction air quality index combined prediction model optimized by the modified symbiotic organisms search (MSOS) algorithm was proposed. Firstly, recursive feature elimination (RFE) was used to filter the features. Secondly, autoregressive integrated moving average with exogenous input (ARIMAX) model was used to capture the linear relationship in air quality time series. Thirdly, VMD algorithm was used to decompose the nonlinear and complex ARIMAX error, and several modal components and a residual margin were obtained. LSTM model optimized by MSOS algorithm was used to predict the decomposed sub-sequences respectively, and the nonlinear relationship in ARIMAX error was captured. Finally, the error prediction result was obtained by superposition of each sub-sequence prediction result, and the ARIMAX prediction value was modified. The simulation results show that the combined model combining deep learning and statistical algorithm can further improve the prediction accuracy, and the variational mode decomposition can not only greatly reduce the nonlinear and complexity of the error sequence, but also improve the stability, and the error correction can further improve the prediction ability of the model. Compared with other models, the combined prediction model has the best evaluation indexes, higher prediction accuracy and generalization performance, and provides a new method for air quality prediction.
LI Jia-nan, YAN Qi-sheng.
Air Quality Prediction Model with Error Correction and Parameter Optimization[J].
Science Technology and Engineering, 2026, 26(1): 223-238 DOI:10.12404/j.issn.1671-1815.2500650
引入外生变量的自回归移动平均模型(autoregressive integrated moving average with exogenous input,ARIMAX)是一种用于分析和预测时间序列数据的统计模型,其基本思想是利用数据本身的历史信息,试图通过数据的自相关性和差分的方式,提取出隐藏在数据背后的时间序列模式,并加入外生变量来捕捉时间序列数据与外部因素之间的线性关系。ARIMAX模型根据变量历史值可以预测变量未来值,同时考虑外生变量对该变量历史值的影响。ARIMAX模型由以下4个部分组成。
LiXiyan, LinXueqin, WangDai. Spatiotemporal evolution characteristics and influencing factors of urban air quality in China[J]. Journal of Xi’an University of Technology, 2022, 38(4): 487-499.
[3]
XiaoD, XuJ, LiQ. The “Double-Edged Sword” effect of air quality information disclosure policy: empirical evidence based on the digital transformation of Chinese listed companies[J]. Energy Economics, 2024, 133: 107513.
[4]
PyaeS T, KallawichaK. First temporal distribution model of ambient air pollutants (PM2. 5, PM10, and O3) in Yangon City, Myanmar during 2019-2021[J]. Environmental Pollution, 2024, 347: 123718.
YanYaping, WangGang, JiangShengji, et al. Research progress of artificial neural networks in the field of environment[J]. Applied Chemical Industry, 2022, 51(1): 170-176.
ZhuJiaying, AnJunlin, FengYuezheng, et al. Atmospheric ozone concentration prediction in Nanjing based on LightGBM[J]. Environmental Science, 2023, 44(7): 3685-3694.
GaoYuxiao, WangWei, HuangYonghai, et al. Comparison and analysis of PM2.5 forecast in key areas based on the neural network model and numerical model[J]. Environmental Science, 2022, 43(2): 663-674.
[11]
XuS, LiW, ZhuY, et al. A novel hybrid model for six main pollutant concentrations forecasting based on improved LSTM neural networks[J]. Scientific Reports, 2022, 12(1): 1-17.
[12]
WuC, HeH, SongR, et al. Prediction of air pollutants on roadside of the elevated roads with combination of pollutants periodicity and deep learning method[J]. Building and Environment, 2022, 207: 108436.
[13]
HuangG, ZhaoX, LuQ. A new cross-domain prediction model of air pollutant concentration based on secure federated learning and optimized LSTM neural net work[J]. Environmental Science and Pollution Research International, 2022, 30: 5103-5125.
[14]
ZhangZ, ZhangS, ChenC, et al. A systematic survey of air quality prediction based on deep learning[J]. Alexandria Engineering Journal, 2024, 93: 128-141.
[15]
WuZ, TianY, LiM, et al. Prediction of air pollutant concentrations based on the long short-term memory neural network[J]. Journal of Hazardous Materials, 2024, 465: 133099.
[16]
ZhangH, WangJ, NieY. A novel optimization model based on fuzzy time series for short-term air quality index forecasting[J]. Knowledge-based Systems, 2024, 296: 111905.
DengGuoqu, ChenHu. Research on short-term air quality prediction based on unequal weight clustering hybrid PSO-SVR[J]. Operations Research and Management Science, 2023, 32(12): 106-111.
ZhangTianjiao, HaiTao, WangJun, et al. Air quality monitoring system based on LPWAN and AQI index predictions[J]. Science Technology and Engineering, 2024, 24(15): 6558-6566.
WeiZhenyu, JiangXuesong, YangLifa. Short term prediction of wind power based on error compensation and IDBO-BiLSTM[J]. Science Technology and Engineering, 2025, 25(6): 2397-2405.
LongYu, XuHaoran, YuHuayun, et al. Prediction of railway freight volume based on ARIMA-LSTM-XGBoost combination model[J]. Science Technology and Engineering, 2023, 23(25): 10879-10886.
LeiBingbing, MuYunfei, WangXiaofeng, et al. Application of improved beluga whale optimization convolutional network for air quality prediction in Yinchuan City[J]. Journal of Safety and Environment, 2024, 24(10): 4079-4093.
ZhangLi, ZhangXiaoqing, SunMinmin, et al. Beluga optimization algorithm based on butterfly search and dynamic inverse learning cauchy variation[J]. Computer Engineering and Applications, 2025, 61(10): 96-110.
QiaoYinwei, JiaXinchun, GuanYanpeng, et al. Air quality prediction method and its application of Elman neural network based on DE-WOA[J/OL]. Control Engineering of China, 1-8[2025-10-11]. https://doi.org/10.14107/j.cnki.kzgc.20220929.
[33]
ChengM Y, PrayogoD. Symbiotic organisms search: a new metaheuristic optimization algorithm[J]. Computers & Structures, 2014, 139: 98-112.
XuJianan, ZhangTianrui, LiYulong. Micro-location and optimization of wind farm based on the adaptive GA-PSO algorithm[J]. Science Technology and Engineering, 2023, 23(16): 6917-6922.
WuXueli, WangChao, ZhaoJunqi, et al. Improved sparrow algorithm for UAV 3D path planning[J]. Science Technology and Engineering, 2024, 24(15): 6534-6542.