Cross-Resolution Attention Network for High-Resolution PM2.5 Prediction

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Kheder, Ammar, Toropainen, Helmi, Peng, Wenqing, Antão, Samuel, Liu, Zhi-Song, Boy, Michael
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866911508472004608
author Kheder, Ammar
Toropainen, Helmi
Peng, Wenqing
Antão, Samuel
Liu, Zhi-Song
Boy, Michael
author_facet Kheder, Ammar
Toropainen, Helmi
Peng, Wenqing
Antão, Samuel
Liu, Zhi-Song
Boy, Michael
contents Vision Transformers have achieved remarkable success in spatio-temporal prediction, but their scalability remains limited for ultra-high-resolution, continent-scale domains required in real-world environmental monitoring. A single European air-quality map at 1 km resolution comprises 29 million pixels, far beyond the limits of naive self-attention. We introduce CRAN-PM, a dual-branch Vision Transformer that leverages cross-resolution attention to efficiently fuse global meteorological data (25 km) with local high-resolution PM2.5 at the current time (1 km). Instead of including physically driven factors like temperature and topography as input, we further introduce elevation-aware self-attention and wind-guided cross-attention to force the network to learn physically consistent feature representations for PM2.5 forecasting. CRAN-PM is fully trainable and memory-efficient, generating the complete 29-million-pixel European map in 1.8 seconds on a single GPU. Evaluated on daily PM2.5 forecasting throughout Europe in 2022 (362 days, 2,971 European Environment Agency (EEA) stations), it reduces RMSE by 4.7% at T+1 and 10.7% at T+3 compared to the best single-scale baseline, while reducing bias in complex terrain by 36%.
format Preprint
id arxiv_https___arxiv_org_abs_2603_11725
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Cross-Resolution Attention Network for High-Resolution PM2.5 Prediction
Kheder, Ammar
Toropainen, Helmi
Peng, Wenqing
Antão, Samuel
Liu, Zhi-Song
Boy, Michael
Computer Vision and Pattern Recognition
Machine Learning
Vision Transformers have achieved remarkable success in spatio-temporal prediction, but their scalability remains limited for ultra-high-resolution, continent-scale domains required in real-world environmental monitoring. A single European air-quality map at 1 km resolution comprises 29 million pixels, far beyond the limits of naive self-attention. We introduce CRAN-PM, a dual-branch Vision Transformer that leverages cross-resolution attention to efficiently fuse global meteorological data (25 km) with local high-resolution PM2.5 at the current time (1 km). Instead of including physically driven factors like temperature and topography as input, we further introduce elevation-aware self-attention and wind-guided cross-attention to force the network to learn physically consistent feature representations for PM2.5 forecasting. CRAN-PM is fully trainable and memory-efficient, generating the complete 29-million-pixel European map in 1.8 seconds on a single GPU. Evaluated on daily PM2.5 forecasting throughout Europe in 2022 (362 days, 2,971 European Environment Agency (EEA) stations), it reduces RMSE by 4.7% at T+1 and 10.7% at T+3 compared to the best single-scale baseline, while reducing bias in complex terrain by 36%.
title Cross-Resolution Attention Network for High-Resolution PM2.5 Prediction
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2603.11725