Long-Term PM2.5 Forecasting Using a DTW-Enhanced CNN-GRU Model

TL;DR

This paper introduces a novel deep learning framework combining DTW and CNN-GRU for stable long-term PM2.5 forecasting in cities with sparse monitoring, achieving high accuracy up to 10 days ahead.

Contribution

It presents a scalable, efficient deep learning approach that leverages DTW for station similarity and extends reliable PM2.5 predictions beyond 48 hours in resource-limited urban settings.

Findings

Achieved R2=0.91 for 24-hour forecasts

Demonstrated stable 10-day forecasting with R2=0.73

Outperformed existing deep learning methods

Abstract

Reliable long-term forecasting of PM2.5 concentrations is critical for public health early-warning systems, yet existing deep learning approaches struggle to maintain prediction stability beyond 48 hours, especially in cities with sparse monitoring networks. This paper presents a deep learning framework that combines Dynamic Time Warping (DTW) for intelligent station similarity selection with a CNN-GRU architecture to enable extended-horizon PM2.5 forecasting in Isfahan, Iran, a city characterized by complex pollution dynamics and limited monitoring coverage. Unlike existing approaches that rely on computationally intensive transformer models or external simulation tools, our method integrates three key innovations: (i) DTW-based historical sampling to identify similar pollution patterns across peer stations, (ii) a lightweight CNN-GRU architecture augmented with meteorological features, and (iii) a scalable design optimized for sparse networks. Experimental validation using multi-year hourly data from eight monitoring stations demonstrates superior performance compared to state-of-the-art deep learning methods, achieving R2 = 0.91 for 24-hour forecasts. Notably, this is the first study to demonstrate stable 10-day PM2.5 forecasting (R2 = 0.73 at 240 hours) without performance degradation, addressing critical early-warning system requirements. The framework's computational efficiency and independence from external tools make it particularly suitable for deployment in resource-constrained urban environments.