# TopoFlow: Topography-aware Pollutant Flow Learning for High-Resolution Air Quality Prediction

arXiv: https://arxiv.org/abs/2602.16821 · HTML: https://mlsanity.com/paper/2602.16821/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 45 references that are in the map.
- First posted on arXiv 18 Feb 2026.

## Builds on (most cited first, 9 of 9)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [SwinIR: Image Restoration Using Swin Transformer](https://mlsanity.com/paper/2108.10257/) (2021)
- [ClimaX: A foundation model for weather and climate](https://mlsanity.com/paper/2301.10343/) (2023)
- [AirPhyNet: Harnessing Physics-Guided Neural Networks for Air Quality Prediction](https://mlsanity.com/paper/2402.03784/) (2024)
- [Permutation Equivariance of Transformers and Its Applications](https://mlsanity.com/paper/2304.07735/) (2023)
- [Neural Network Emulator for Atmospheric Chemical ODE](https://mlsanity.com/paper/2408.01829/) (2024)
- [Deep Spatio-Temporal Neural Network for Air Quality Reanalysis](https://mlsanity.com/paper/2502.11941/) (2025)
- [AirCast: Improving Air Pollution Forecasting Through Multi-Variable Data Alignment](https://mlsanity.com/paper/2502.17919/) (2025)

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

- [Cross-Resolution Attention Network for High-Resolution PM2.5 Prediction](https://mlsanity.com/paper/2603.11725/) (2026)

## Abstract (arXiv)

We propose TopoFlow (Topography-aware pollutant Flow learning), a physics-guided neural network for efficient, high-resolution air quality prediction. To explicitly embed physical processes into the learning framework, we identify two critical factors governing pollutant dynamics: topography and wind direction. Complex terrain can channel, block, and trap pollutants, while wind acts as a primary driver of their transport and dispersion. Building on these insights, TopoFlow leverages a vision transformer architecture with two novel mechanisms: topography-aware attention, which explicitly models terrain-induced flow patterns, and wind-guided patch reordering, which aligns spatial representations with prevailing wind directions. Trained on six years of high-resolution reanalysis data assimilating observations from over 1,400 surface monitoring stations across China, TopoFlow achieves a PM2.5 RMSE of 9.71 ug/m3, representing a 71-80% improvement over operational forecasting systems and a 13% improvement over state-of-the-art AI baselines. Forecast errors remain well below China's 24-hour air quality threshold of 75 ug/m3 (GB 3095-2012), enabling reliable discrimination between clean and polluted conditions. These performance gains are consistent across all four major pollutants and forecast lead times from 12 to 96 hours, demonstrating that principled integration of physical knowledge into neural networks can fundamentally advance air quality prediction.