AI model achieves stable 10-day PM2.5 forecasts using DTW-CNN-GRU

A research paper proposes a novel deep learning framework for long-term PM2.5 concentration forecasting, specifically designed for cities with limited monitoring networks like Isfahan, Iran. The model integrates Dynamic Time Warping (DTW) for station similarity selection with a CNN-GRU architecture, enhanced by meteorological features. This approach demonstrates stable 10-day forecasting capabilities, achieving an R2 score of 0.73 at 240 hours, outperforming existing methods without requiring computationally intensive transformer models or external tools. AI

IMPACT Enables more reliable public health early-warning systems in areas with sparse environmental monitoring data.

RANK_REASON Research paper detailing a novel AI model for environmental forecasting. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

• Amirali Ataee Naeini
• arXiv
• Dynamic Time Warping
• PM2.5

• paper
• model release

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →