TopoFlow: Physics-guided Neural Networks for high-resolution air quality prediction

• URL: http://arxiv.org/abs/2602.16821v1
• Date: Wed, 18 Feb 2026 19:38:11 GMT
• Title: TopoFlow: Physics-guided Neural Networks for high-resolution air quality prediction
• Authors: Ammar Kheder, Helmi Toropainen, Wenqing Peng, Samuel Antão, Jia Chen, Zhi-Song Liu, Michael Boy,
• Abstract summary: TopoFlow is a physics-guided neural network for efficient, high-resolution air quality prediction.<n>We identify two critical factors governing pollutant dynamics: topography and wind direction.<n>TopoFlow achieves a PM2.5 RMSE of 9.71 ug/m3, representing a 71-80% improvement over operational forecasting systems.
• Score: 8.841726805480361
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Breaking the Regional Barrier: Inductive Semantic Topology Learning for Worldwide Air Quality Forecasting [99.4484686548807]
  We propose OmniAir, a semantic topology learning framework tailored for global station-level prediction.<n>Our approach effectively captures long-range non-Euclidean correlations and physical diffusion patterns across unevenly distributed global networks.<n>Experiments show that OmniAir achieves state-of-the-art performance against 18 baselines, maintaining high efficiency and scalability with speeds nearly 10 times faster than existing models.
  arXiv  Detail & Related papers  (2026-01-29T15:58:07Z)
• HydroGEM: A Self Supervised Zero Shot Hybrid TCN Transformer Foundation Model for Continental Scale Streamflow Quality Control [2.153503585184628]
  We introduce HydroGEM, a foundation model for continental-scale streamflow quality control.<n>HydroGEM uses two-stage training: self-supervised pretraining on 6.03 million sequences from 3,724 stations.<n>On held-out synthetic tests, HydroGEM F1 = 0.792 for detection and 6 reconstruction-error reduction, a 36.3% improvement over existing methods.
  arXiv  Detail & Related papers  (2025-12-16T05:39:26Z)
• Interpretable Air Pollution Forecasting by Physics-Guided Spatiotemporal Decoupling [4.606462413596598]
  This study proposes a physics-guided, interpretable-by-temporal learning framework.<n>Our model consistently outperforms state-of-the-art baselines across multiple forecasting horizons.<n>Our model's integration of predictive performance and interpretability provides a more reliable foundation for operational air-quality management in real-world applications.
  arXiv  Detail & Related papers  (2025-11-25T12:36:27Z)
• Synergistic Neural Forecasting of Air Pollution with Stochastic Sampling [50.3911487821783]
  Air pollution remains a leading global health and environmental risk, particularly in regions vulnerable to episodic air pollution spikes due to wildfires, urban haze and dust storms.<n>Here, we present SynCast, a high-resolution neural forecasting model that integrates meteorological and air composition data to improve predictions of both average and extreme pollution levels.
  arXiv  Detail & Related papers  (2025-10-28T01:18:00Z)
• MVAR: MultiVariate AutoRegressive Air Pollutants Forecasting Model [18.785110680719235]
  Existing studies predominantly focus on single-pollutant forecasting, neglecting the interactions among different pollutants and their diverse spatial responses.<n>We propose MultiVariate AutoRegressive air pollutants forecasting model, which reduces the dependency on long-time-window inputs.<n>We construct a comprehensive dataset covering 6 major pollutants across 75 cities in North China from 2018 to 2023, including ERA5 reanalysis data and FuXi-2.0 forecast data.
  arXiv  Detail & Related papers  (2025-07-16T08:30:41Z)
• Air Quality Prediction with A Meteorology-Guided Modality-Decoupled Spatio-Temporal Network [47.699409089023696]
  Air quality prediction plays a crucial role in public health and environmental protection.<n>Existing works underestimate the critical role atmospheric conditions in air quality prediction.<n> MDSTNet is an encoder framework explicitly that captures atmosphere-pollution dependencies for prediction.<n>ChinaAirNet is the first dataset combining air quality records with multi-pressure-level meteorological observations.
  arXiv  Detail & Related papers  (2025-04-14T09:18:11Z)
• Offline Meteorology-Pollution Coupling Global Air Pollution Forecasting Model with Bilinear Pooling [5.236306661644172]
  Traditional physics-based models forecast global air pollution by coupling meteorology and pollution processes.<n>Existing deep learning (DL) solutions employ online coupling strategies for global air pollution forecasting.<n>This study pioneers a DL-based offline coupling framework that utilizes bilinear pooling to achieve offline coupling between meteorological fields and pollutants.
  arXiv  Detail & Related papers  (2025-03-24T07:24:31Z)
• A HEART for the environment: Transformer-Based Spatiotemporal Modeling for Air Quality Prediction [0.0]
  llull-environment is a sophisticated and scalable forecasting system for air pollution.<n>It contains an encoder-decoder convolutional neural network to forecast mean pollution levels for four key pollutants.<n>This paper investigates the augmentation of this neural network with an attention mechanism to improve predictive accuracy.
  arXiv  Detail & Related papers  (2025-02-26T10:54:27Z)
• FengWu-W2S: A deep learning model for seamless weather-to-subseasonal forecast of global atmosphere [53.22497376154084]
  We propose FengWu-Weather to Subseasonal (FengWu-W2S), which builds on the FengWu global weather forecast model and incorporates an ocean-atmosphere-land coupling structure along with a diverse perturbation strategy. Our hindcast results demonstrate that FengWu-W2S reliably predicts atmospheric conditions out to 3-6 weeks ahead, enhancing predictive capabilities for global surface air temperature, precipitation, geopotential height and intraseasonal signals such as the Madden-Julian Oscillation (MJO) and North Atlantic Oscillation (NAO) Our ablation experiments on forecast error growth from daily to seasonal timescales reveal potential
  arXiv  Detail & Related papers  (2024-11-15T13:44:37Z)
• Residual Corrective Diffusion Modeling for Km-scale Atmospheric Downscaling [58.456404022536425]
  State of the art for physical hazard prediction from weather and climate requires expensive km-scale numerical simulations driven by coarser resolution global inputs. Here, a generative diffusion architecture is explored for downscaling such global inputs to km-scale, as a cost-effective machine learning alternative. The model is trained to predict 2km data from a regional weather model over Taiwan, conditioned on a 25km global reanalysis.
  arXiv  Detail & Related papers  (2023-09-24T19:57:22Z)
• FengWu: Pushing the Skillful Global Medium-range Weather Forecast beyond 10 Days Lead [93.67314652898547]
  We present FengWu, an advanced data-driven global medium-range weather forecast system based on Artificial Intelligence (AI) FengWu is able to accurately reproduce the atmospheric dynamics and predict the future land and atmosphere states at 37 vertical levels on a 0.25deg latitude-longitude resolution. The results suggest that FengWu can significantly improve the forecast skill and extend the skillful global medium-range weather forecast out to 10.75 days lead.
  arXiv  Detail & Related papers  (2023-04-06T09:16:39Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.