Your contributions are invaluable! We encourage you to share your insights by submitting individual pull requests for each suggestion.
📚 A Systematic Review of Hybrid Deep Learning Models Based on Graph Convolutional Networks for Air Quality Prediction
This repository provides a comprehensive collection of resources and insights from our systematic review on hybrid deep learning models that utilize Graph Convolutional Networks (GCNs) for air quality prediction. As air pollution remains a pressing issue, leveraging hybrid models has shown significant potential in capturing complex spatiotemporal dependencies, leading to more accurate predictions.
- Detailed Analysis: An in-depth review of the latest hybrid architectures, focusing on the integration of GCNs with various temporal feature extraction models (RNNs, CNNs, Attention-based models).
- Comprehensive Classification: Models are categorized based on their spatial and temporal components, providing a clear understanding of their design and capabilities.
- Critical Insights: Discussion on the strengths and weaknesses of hybrid approaches in different scenarios, aiding researchers and practitioners in selecting the right models for their specific needs.
- 📄 Paper List: A curated collection of significant studies reviewed in this paper.
- 📊 Data Sources: Links to commonly used air quality datasets.
- 🧠 Popular Architectures: Examples and diagrams of key hybrid models for air quality prediction.
- 📈 Implementation Guides: Tutorials and reference implementations for building hybrid GCN-based models.
[1] A hybrid model for spatiotemporal forecasting of PM2.5 based on graph convolutional neural network and long short-term memory
📄 Link
[2] Multi-scale spatiotemporal graph convolution network for air quality prediction
📄 Link
[3] Self-adaptive spatial-temporal network based on heterogeneous data for air quality prediction
📄 Link
[4] Forecasting PM2.5 using hybrid graph convolution-based model considering dynamic wind-field to offer the benefit of spatial interpretability
📄 Link
[5] Near-surface PM2.5 prediction combining the complex network characterization and graph convolution neural network
📄 Link
[6] A graph-based LSTM model for PM2.5 forecasting 📄 Link
[7] Spatio-attention embedded recurrent neural network for air quality prediction 📄 Link
[8] A new multi-data-driven spatiotemporal PM2.5 forecasting model based on an ensemble graph reinforcement learning convolutional network
📄 Link
[9] Spatial-Temporal Dynamic Graph Convolution Neural Network for Air Quality Prediction
📄 Link
[10] A hybrid integrated deep learning model for predicting various air pollutants 📄 Link
[11] Research on Prediction and Source Analysis of Ozone Pollution
📄 Link
[12] A theory-guided graph networks based PM2.5 forecasting method
📄 Link
📃 Code
[13] A dual-path dynamic directed graph convolutional network for air quality prediction 📄 Link
[14] Heterogeneous data fusion considering spatial correlations using graph convolutional networks and its application in air quality prediction 📄 Link
[15] Dynamic graph convolution neural network based on spatial-temporal correlation for air quality prediction 📄 Link
[16] Attention enhanced hybrid model for spatiotemporal short-term forecasting of particulate matter concentrations 📄 Link
[17] Forecasting PM2.5 Concentration in India Using a Cluster Based Hybrid Graph Neural Network Approach 📄 Link
[18] STM2CN: A Multi-graph Attention-based Framework for Sensor Data Prediction in Smart Cities 📄 Link
[19] Spatio-Temporal Modeling For Air Quality Prediction Based On Spectral Graph Convolutional Network And Attention Mechanism 📄 Link
[20] MGC‑LSTM: a deep learning model based on graph convolution of multiple graphs for PM2.5 prediction
📄 Link
[21] Dual-channel spatial–temporal difference graph neural network for PM2.5 forecasting 📄 Link
[22] Graph Neural Network for Air Quality Prediction: A Case Study in Madrid
📄 Link
📃 Code
[23] A hybrid deep learning model for regional O3 and NO2 concentrations prediction based on spatiotemporal dependencies in air quality monitoring network
📄 Link
[24] A novel spatiotemporal multigraph convolutional network for air pollution prediction
📄 Link
[25] Deep Spatio-Temporal Graph Network with Self-Optimization for Air Quality Prediction
📄 Link
[26] A hybrid model for spatial–temporal prediction of PM2.5 based on a time division method
📄 Link
[27] Air Quality Prediction Model Based on Spatio-temporal Graph Convolution Neural Networks
📄 Link
[28] A city-based PM2.5 forecasting framework using Spatially Attentive Cluster-based Graph Neural Network model
📄 Link
[29] Enhancing PM2.5 Predictions Using Combination of Graph Convolutional Network and Bi-LSTM 📄 Link
[30] A Spatio-Temporal Graph Convolutional Network for Air Quality Prediction
📄 Link
[31] Smart solutions for urban health risk assessment: A PM2.5 monitoring system incorporating spatiotemporal long-short term graph convolutional network
📄 Link
[32] Multi-view multi-task spatiotemporal graph convolutional network for air quality prediction
📄 Link
[33] Dynamic graph neural network with adaptive edge attributes for air quality prediction: A case study in China 📄 Link
[34] Spatiotemporal adaptive attention graph convolution network for city‑level air quality prediction 📄 Link 📃 Code
[35] Adaptive scalable spatio-temporal graph convolutional network for PM2.5 prediction 📄 Link
[36] Spatio-temporal fusion of meteorological factors for multi-site PM2.5 prediction: A deep learning and time-variant graph approach 📄 Link
[37] A forecasting framework on fusion of spatiotemporal features for multi-station PM2.5 📄 Link
[38] A multi-graph spatial-temporal attention network for air-quality prediction 📄 Link
[39] Fine-grained PM2.5 prediction in Lanzhou based on the spatiotemporal graph convolutional network 📄 Link
[40] A lightweight spatiotemporal graph dilated convolutional network for urban sensor state prediction 📄 Link 📃 Code
[41] Multi-Site and Multi-Pollutant Air Quality Data Modeling 📄 Link
[42] A Multi-Modal Deep-Learning Air Quality Prediction Method Based on Multi-Station Time-Series Data and Remote-Sensing Images: Case Study of Beijing and Tianjin
📄 Link
[43] Urban AQI Prediction Using an Inverse Variance Weighted GCN and BiLSTM Combined Model 📄 Link
[44] Predicting short-term PM2.5 concentrations at fine temporal resolutions using a multi-branch temporal graph convolutional neural network 📄 Link 📄 Code
[45] An adaptive adjacency matrix‑based graph convolutional recurrent network for air quality prediction 📄 Link 📃 Code
[46] AIoT-driven multi-source sensor emission monitoring and forecasting using multi-source sensor integration with reduced noise series decomposition 📄 Link
[47] Enhancing Air Quality Forecasting: A Novel Spatio-Temporal Model Integrating Graph Convolution and Multi-Head Attention Mechanism 📄 Link
[48] Air Quality Index Prediction Model Integrating Spatiotemporal Information 📄 Link
[49] Learning spatiotemporal dependencies using adaptive hierarchical graph convolutional neural network for air quality prediction 📄 Link
[50] Prediction of PM2.5 Concentration Based on Deep Learning, Multi-Objective Optimization, and Ensemble Forecast 📄 Link
[51] Fine particulate matter concentration prediction based on hybrid convolutional network with aggregated local and global spatiotemporal information: A case study in Beijing and Chongqing 📄 Link
[52] Enhanced Air Quality Prediction through Spatio-temporal Feature Extraction and Fusion: A Self-tuning Hybrid Approach with GCN and GRU 📄 Link
[53] Short-term air pollution prediction using graph convolutional neural networks 📄 Link 📃 Code
[54] Domain knowledge-enhanced multi-spatial multi-temporal PM2.5 forecasting with integrated monitoring and reanalysis data 📄 Link