mlsanityData to 7 Oct 2026

AirFormer: Predicting Nationwide Air Quality in China with Transformers

arXiv 2211.15979 ↗First posted 29 Nov 2022eess.SP cs.LGcited by 73

Not on the map. Why?

Abstract (arXiv)

Air pollution is a crucial issue affecting human health and livelihoods, as well as one of the barriers to economic and social growth. Forecasting air quality has become an increasingly important endeavor with significant social impacts, especially in emerging countries like China. In this paper, we present a novel Transformer architecture termed AirFormer to collectively predict nationwide air quality in China, with an unprecedented fine spatial granularity covering thousands of locations. AirFormer decouples the learning process into two stages -- 1) a bottom-up deterministic stage that contains two new types of self-attention mechanisms to efficiently learn spatio-temporal representations; 2) a top-down stochastic stage with latent variables to capture the intrinsic uncertainty of air quality data. We evaluate AirFormer with 4-year data from 1,085 stations in the Chinese Mainland. Compared to the state-of-the-art model, AirFormer reduces prediction errors by 5%~8% on 72-hour future predictions. Our source code is available at https://github.com/yoshall/airformer.

Key facts. Cited by 73 papers in the map (data through 7 Oct 2026). Builds on 19 of its 43 references that are in the map. First posted on arXiv 29 Nov 2022.

Builds on

19 of 43 references.

References · 19

  1. 2017Attention Is All You Needcited by 59,932
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2016WaveNet: A Generative Model for Raw Audiocited by 1,710
  4. 2022FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecastingcited by 1,200
  5. 2017Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecastingcited by 1,125
  6. 2019Graph WaveNet for Deep Spatial-Temporal Graph Modelingcited by 820
  7. 2020Connecting the Dots: Multivariate Time Series Forecasting with Graph Neural Networkscited by 563
  8. 2022Transformers in Time Series: A Surveycited by 489
  9. 2019GMAN: A Graph Multi-Attention Network for Traffic Predictioncited by 433
  10. 2016Deep Spatio-Temporal Residual Networks for Citywide Crowd Flows Predictioncited by 330
  11. 2016Ladder Variational Autoencoderscited by 315
  12. 2021Rethinking and Improving Relative Position Encoding for Vision Transformercited by 206
7 more
  1. 2020Spatial-Temporal Transformer Networks for Traffic Flow Forecastingcited by 179
  2. 2022Pre-training Enhanced Spatial-temporal Graph Neural Network for Multivariate Time Series Forecastingcited by 117
  3. 2020PM2.5-GNN: A Domain Knowledge Enhanced Graph Neural Network For PM2.5 Forecastingcited by 52
  4. 2021Group-Aware Graph Neural Network for Nationwide City Air Quality Forecastingcited by 32
  5. 2019STCN: Stochastic Temporal Convolutional Networkscited by 26
  6. 2021HighAir: A Hierarchical Graph Neural Network-Based Air Quality Forecasting Methodcited by 12
  7. 2018HyperST-Net: Hypernetworks for Spatio-Temporal Forecastingcited by 11

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 13; 2024: 16; 2025: 25; 2026: 19.

73 papers.

Sort:

By area:

  1. 2023Spatio-Temporal Graph Neural Networks for Predictive Learning in Urban Computing: A Surveycited by 140
  2. 2023Large Models for Time Series and Spatio-Temporal Data: A Survey and Outlookcited by 109
  3. 2023DiffSTG: Probabilistic Spatio-Temporal Graph Forecasting with Denoising Diffusion Modelscited by 81
  4. 2023CARD: Channel Aligned Robust Blend Transformer for Time Series Forecastingcited by 55
  5. 2023Deciphering Spatio-Temporal Graph Forecasting: A Causal Lens and Treatmentcited by 47
  6. 2024Deep Learning for Cross-Domain Data Fusion in Urban Computing: Taxonomy, Advances, and Outlookcited by 33
  7. 2024AirPhyNet: Harnessing Physics-Guided Neural Networks for Air Quality Predictioncited by 25
  8. 2024Air Quality Prediction with Physics-Guided Dual Neural ODEs in Open Systemscited by 25
  9. 2024STG-Mamba: Spatial-Temporal Graph Learning via Selective State Space Modelcited by 24
  10. 2025Foundation Models for Spatio-Temporal Data Science: A Tutorial and Surveycited by 23
  11. 2023PromptST: Prompt-Enhanced Spatio-Temporal Multi-Attribute Predictioncited by 20
  12. 2023Graph Neural Processes for Spatio-Temporal Extrapolationcited by 18
38 more
  1. 2025Deep Learning and Foundation Models for Weather Prediction: A Surveycited by 15
  2. 2024Spatio-Temporal Field Neural Networks for Air Quality Inferencecited by 12
  3. 2024Expand and Compress: Exploring Tuning Principles for Continual Spatio-Temporal Graph Forecastingcited by 10
  4. 2025Unraveling Spatio-Temporal Foundation Models via the Pipeline Lens: A Comprehensive Reviewcited by 10
  5. 2024ST-LoRA: Low-rank Adaptation for Spatio-Temporal Forecastingcited by 9
  6. 2023Machine Learning for Urban Air Quality Analytics: A Surveycited by 8
  7. 2025ARROW: An Adaptive Rollout and Routing Method for Global Weather Forecastingcited by 8
  8. 2023GBT: Two-stage transformer framework for non-stationary time series forecastingcited by 7
  9. 2024On the Integration of Spatial-Temporal Knowledge: A Lightweight Approach to Atmospheric Time Series Forecastingcited by 7
  10. 2024Quantformer: from attention to profit with a quantitative transformer trading strategycited by 6
  11. 2025Instructor-Worker Large Language Model System for Policy Recommendation: a Case Study on Air Quality Analysis of the January 2025 Los Angeles Wildfirescited by 6
  12. 2024NRFormer: Nationwide Nuclear Radiation Forecasting with Spatio-Temporal Transformercited by 4
  13. 2025Spatiotemporal Causal Decoupling Model for Air Quality Forecastingcited by 3
  14. 2026OATS: Online Data Augmentation for Time Series Foundation Modelscited by 3
  15. 2023Unleashing Realistic Air Quality Forecasting: Introducing the Ready-to-Use PurpleAirSF Datasetcited by 2
  16. 2023TPRNN: A Top-Down Pyramidal Recurrent Neural Network for Time Series Forecastingcited by 2
  17. 2025AirRadar: Inferring Nationwide Air Quality in China with Deep Neural Networkscited by 2
  18. 2025Urban Computing in the Era of Large Language Modelscited by 2
  19. 2025ST-Hyper: Learning High-Order Dependencies Across Multiple Spatial-Temporal Scales for Multivariate Time Series Forecastingcited by 2
  20. 2026Learning to Factorize and Adapt: A Versatile Approach Toward Universal Spatio-Temporal Foundation Modelscited by 2
  21. 2023TransGlow: Attention-augmented Transduction model based on Graph Neural Networks for Water Flow Forecastingcited by 1
  22. 2024Scalable Numerical Embeddings for Multivariate Time Series: Enhancing Healthcare Data Representation Learningcited by 1
  23. 2024Predicting Parking Availability in Singapore with Cross-Domain Data: A New Dataset and A Data-Driven Approachcited by 1
  24. 2024TCNFormer: Temporal Convolutional Network Former for Short-Term Wind Speed Forecastingcited by 1
  25. 2024Space to Policy: Scalable Brick Kiln Detection and Automatic Compliance Monitoring with Geospatial Datacited by 1
  26. 2025Fremer: Lightweight and Effective Frequency Transformer for Workload Forecasting in Cloud Servicescited by 1
  27. 2025A Causality-Aware Spatiotemporal Model for Multi-Region and Multi-Pollutant Air Quality Forecastingcited by 1
  28. 2025FlowNet: Modeling Dynamic Spatio-Temporal Systems via Flow Propagationcited by 1
  29. 2025HieraMix: A Hierarchical MLP-Mixer for Large-Scale Traffic Forecastingcited by 1
  30. 2026FaST: Efficient and Effective Long-Horizon Forecasting for Large-Scale Spatial-Temporal Graphs via Mixture-of-Expertscited by 1
  31. 2026Breaking the Regional Barrier: Inductive Semantic Topology Learning for Worldwide Air Quality Forecastingcited by 1
  32. 2026AirDDE: Multifactor Neural Delay Differential Equations for Air Quality Forecastingcited by 1
  33. 2026Causality-inspired Federated Learning for Dynamic Spatio-Temporal Graphscited by 1
  34. 2026Discrete Prototypical Memories for Federated Time Series Foundation Modelscited by 1
  35. 2026AirQualityBench: A Realistic Evaluation Benchmark for Global Air Quality Forecastingcited by 1
  36. 2023Opportunistic Air Quality Monitoring and Forecasting with Expandable Graph Neural Networkscited by 0
  37. 2024ComS2T: A complementary spatiotemporal learning system for data-adaptive model evolutioncited by 0
  38. 2024Navigating the Smog: A Cooperative Multi-Agent RL for Accurate Air Pollution Mapping through Data Assimilationcited by 0

50 most cited of 73 All 73 (JSON)