# AirQualityBench: A Realistic Evaluation Benchmark for Global Air Quality Forecasting

arXiv: https://arxiv.org/abs/2605.05854 · HTML: https://mlsanity.com/paper/2605.05854/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 24 references that are in the map.
- First posted on arXiv 7 May 2026.

## Builds on (most cited first, 12 of 12)

- [Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecasting](https://mlsanity.com/paper/1709.04875/) (2017)
- [Graph WaveNet for Deep Spatial-Temporal Graph Modeling](https://mlsanity.com/paper/1906.00121/) (2019)
- [Adaptive Graph Convolutional Recurrent Network for Traffic Forecasting](https://mlsanity.com/paper/2007.02842/) (2020)
- [Spatial-Temporal Transformer Networks for Traffic Flow Forecasting](https://mlsanity.com/paper/2001.02908/) (2020)
- [PDFormer: Propagation Delay-Aware Dynamic Long-Range Transformer for Traffic Flow Prediction](https://mlsanity.com/paper/2301.07945/) (2023)
- [Decoupled Dynamic Spatial-Temporal Graph Neural Network for Traffic Forecasting](https://mlsanity.com/paper/2206.09112/) (2022)
- [LargeST: A Benchmark Dataset for Large-Scale Traffic Forecasting](https://mlsanity.com/paper/2306.08259/) (2023)
- [AirFormer: Predicting Nationwide Air Quality in China with Transformers](https://mlsanity.com/paper/2211.15979/) (2022)
- [PM2.5-GNN: A Domain Knowledge Enhanced Graph Neural Network For PM2.5 Forecasting](https://mlsanity.com/paper/2002.12898/) (2020)
- [Deep Air Quality Forecasting Using Hybrid Deep Learning Framework](https://mlsanity.com/paper/1812.04783/) (2018)
- [PCDCNet: A Surrogate Model for Air Quality Forecasting with Physical-Chemical Dynamics and Constraints](https://mlsanity.com/paper/2505.19842/) (2025)
- [Incident-Guided Spatiotemporal Traffic Forecasting](https://mlsanity.com/paper/2602.02528/) (2026)

## Built on by (most cited first, 1 of 1)

- [A foundation model of numerical intelligence with cross-disciplinary generalization](https://mlsanity.com/paper/2607.28432/) (2026)

## Abstract (arXiv)

Air-quality forecasting models are commonly evaluated on regional, preprocessed, and normalized datasets, where missing observations are removed or artificially completed. Such protocols simplify comparison but hide the conditions that dominate real monitoring networks: uneven global coverage, structured missingness, heterogeneous pollutant scales, and deployment cost. We introduce AirQualityBench, a global multi-pollutant benchmark designed to evaluate forecasting models under these realistic conditions. The benchmark contains hourly observations from 3,720 monitoring stations over 2021--2025, covers six major pollutants, and preserves provider-native observation masks. Rather than imputing a dense data tensor, AirQualityBench exposes missingness as part of the forecasting problem and reports errors on valid future observations after inverse transformation to physical concentration scales. Evaluating representative spatio-temporal models under this unified protocol shows that strong performance on sanitized datasets does not reliably transfer to global, fragmented monitoring streams. AirQualityBench therefore serves as a realistic testbed for scalable, mask-aware, and physically interpretable air-quality forecasting. All benchmark data, code, evaluation scripts, and baseline implementations are available at hrefhttps://github.com/Star-Learning/AirQualityBenchGitHub.