湖北民族大学学报（自然科学版）2025，Vol.43Issue(1)：67-72,85,7.DOI:10.13501/j.cnki.42-1908/n.2025.03.009
基于GCN-GRU-Attention的多站点PM2.5质量浓度预测方法
Multi-site PM2.5 Mass Concentration Prediction Method Based on GCN-GRU-Attention
摘要
Abstract
To improve the accuracy of particulate matter 2.5(PM2.5)mass concentration prediction and provide decision-making support for the formulation of air quality management strategies and the implementation of pollution control measures,the multi-site PM2.5 mass concentration prediction method based on a combined model of graph convolutional network-gated recurrent unit-attention mechanism(GCN-GRU-Attention)was proposed.The model dynamically constructed spatiotemporal graphs between monitoring sites to capture dynamic correlations and enhanced the interaction of spatiotemporal features through the attention mechanism.The results showed that,in long-term forecasting,the GCN-GRU-Attention model outperformed the best-performing PM2.5-graph neural network(PM2.5-GNN)model among the comparison models,with reduction of 3.2%in mean absolute error and 1.8%in root mean squared error.In short-term prediction and high pollution peak prediction,significant enhancements were also observed compared to traditional models and fixed graph structure models.These results demonstrated significant improvements over traditional models and fixed graph structure models.The ablation experiments further confirmed the effectiveness of dynamic graph modeling and the attention mechanism in enhancing model performance.This research provided new insights into PM2.5mass concentration prediction in dynamic environments and offered a reliable basis for air quality management and public health protection.关键词
PM2.5/质量浓度预测/动态图/注意力机制/时空特征融合/污染治理/安徽省Key words
PM2.5/mass concentration prediction/dynamic graph/attention mechanism/spatiotemporal feature fusion/pollution treatment/Anhui Province分类
信息技术与安全科学引用本文复制引用
朱振业,唐超礼..基于GCN-GRU-Attention的多站点PM2.5质量浓度预测方法[J].湖北民族大学学报（自然科学版）,2025,43(1):67-72,85,7.基金项目
安徽省研究生创新创业实践项目(2023cxcysj089) （2023cxcysj089）
安徽理工大学研究生创新基金(2023cx2092). （2023cx2092）
