华南理工大学学报(自然科学版) ›› 2025, Vol. 53 ›› Issue (5): 66-81.doi: 10.12141/j.issn.1000-565X.240356

• 计算机科学与技术 • 上一篇    下一篇

基于SD-ISSA-DALSTM的交通运输业碳排放预测

王庆荣1, 王俊杰1, 朱昌锋2, 郝福乐1   

  1. 1.兰州交通大学 电子与信息工程学院,甘肃 兰州 730070
    2.兰州交通大学 交通运输学院,甘肃 兰州 730070
  • 收稿日期:2024-07-15 出版日期:2025-05-25 发布日期:2024-11-12
  • 通信作者: 王俊杰(1998—),男,硕士生,主要从事交通大数据预测与分析研究。 E-mail:876087843@qq.com
  • 作者简介:王庆荣(1977—),女,教授,主要从事交通运输系统优化与分析研究。E-mail: 329046272@qq.com
  • 基金资助:
    国家自然科学基金项目(72161024);甘肃省教育厅“双一流”重大研究项目(GSSYLXM-04)

Carbon Emission Prediction in Transportation Industry Based on SD-ISSA-DALSTM

WANG Qingrong1, WANG Junjie1, ZHU Changfeng2, HAO Fule1   

  1. 1.School of Electronic and Information Engineering,Lanzhou Jiaotong University,Lanzhou 730070,Gansu,China
    2.School of Transportation,Lanzhou Jiaotong University,Lanzhou 730070,Gansu,China
  • Received:2024-07-15 Online:2025-05-25 Published:2024-11-12
  • Contact: 王俊杰(1998—),男,硕士生,主要从事交通大数据预测与分析研究。 E-mail:876087843@qq.com
  • About author:王庆荣(1977—),女,教授,主要从事交通运输系统优化与分析研究。E-mail: 329046272@qq.com
  • Supported by:
    the National Natural Science Foundation of China(72161024);the “Double-First Class” Major Research Programs of the Educational Department of Gansu Province(GSSYLXM-04)

摘要:

针对交通运输业碳排放数据序列的波动性和非线性影响预测精度的问题,提出了一种结合二次分解、双重注意力机制、改进麻雀搜索算法(ISSA)和长短期记忆(LSTM)网络的交通运输业碳排放预测模型。首先,引入自适应噪声完备集合经验模态分解,将交通碳排放数据序列分解为不同频率的模态分量,再利用样本熵对各分量复杂度进行量化,并利用变分模态分解对熵值最高的分量进行二次分解,进一步弱化交通碳排放数据序列的波动性和非线性;然后,为挖掘交通碳排放量与其影响因素间的关联性,构建基于双重注意力机制优化的LSTM(DALSTM)模型,在LSTM模型的输入端嵌入特征注意力机制,突出关键输入特征;同时,在输出端嵌入时间注意力机制,提取关键历史时刻信息;最后,结合Circle混沌映射、动态惯性权重因子和混合变异算子策略改进SSA算法,并对各模态分量分别建立ISSA-DALSTM模型,接着对各模态分量预测值进行重构。用所测算的中国交通运输业1990—2019年碳排放数据来对模型进行验证,结果表明,所提模型的均方根误差、均方误差、平均绝对百分比误差分别为5.308 8、3.566 1、0.443 9,均优于其他对比模型,验证了所提模型的有效性。

关键词: 交通运输业, 碳排放预测, 二次分解, 双重注意力机制, 改进麻雀搜索算法

Abstract:

Aiming at the low accuracy of carbon emission prediction caused by the high volatility and nonlinearity of the carbon emission data series in transportation industry, a transportation carbon emission prediction model combining the secondary decomposition, dual attention mechanism, improved sparrow search algorithm (ISSA) and long short-term memory (LSTM) network is proposed. First, complete ensemble empirical mode decomposition with adaptive noise is introduced to decompose the transportation carbon emission data series into modal components with different frequencies, then sample entropy is used to quantify the complexity of each component, and secondary decomposition is performed on the component with the highest entropy value via variational mode decomposition, which further weakens the volatility and nonlinearity of the transportation carbon emission data series. Next, in order to explore the correlation between transportation carbon emission and its influencing factors, a double attention mechanism-optimized LSTM (DALSTM) model is constructed, in which a feature attention mechanism is added to the input side of the LSTM to highlight the key input features. Meanwhile, a temporal attention mechanism is added to the output side to extract the key historical moments. Finally, the SSA algorithm is improved by combining the Circle chaotic mapping, the dynamic inertia weight factor and the mixed variance operator strategies, ISSA-DALSTM models are established for each component separately, and the predicted values of each component are reconstructed. By measuring the carbon emission data of China’s transportation industry from 1990 to 2019, it is found that the root mean square error, mean square error, and mean absolute percentage error of the proposed model are respectively 5.308 8, 3.566 1 and 0.443 9, which are better than those of other comparative models, thus verifying the validity of the proposed model.

Key words: transportation industry, carbon emission prediction, secondary decomposition, dual attention mechanism, improved sparrow search algorithm

中图分类号: