Deep Spatio-Temporal Neural Network for Air Quality Reanalysis

TL;DR

AQ-Net is a novel spatiotemporal neural network that improves air quality reanalysis by integrating LSTM, multi-head attention, cyclic encoding, and neural kNN for better spatial and temporal predictions.

Contribution

The paper introduces AQ-Net, combining LSTM, attention, cyclic encoding, and neural kNN to enhance spatiotemporal air quality reanalysis, especially in unobserved areas.

Findings

AQ-Net outperforms existing models in PM2.5 reanalysis accuracy.

The model effectively captures spatial and temporal variability in urban air quality.

Experiments demonstrate AQ-Net's potential for environmental monitoring.

Abstract

Air quality prediction is key to mitigating health impacts and guiding decisions, yet existing models tend to focus on temporal trends while overlooking spatial generalization. We propose AQ-Net, a spatiotemporal reanalysis model for both observed and unobserved stations in the near future. AQ-Net utilizes the LSTM and multi-head attention for the temporal regression. We also propose a cyclic encoding technique to ensure continuous time representation. To learn fine-grained spatial air quality estimation, we incorporate AQ-Net with the neural kNN to explore feature-based interpolation, such that we can fill the spatial gaps given coarse observation stations. To demonstrate the efficiency of our model for spatiotemporal reanalysis, we use data from 2013-2017 collected in northern China for PM2.5 analysis. Extensive experiments show that AQ-Net excels in air quality reanalysis, highlighting the potential of hybrid spatio-temporal models to better capture environmental dynamics, especially in urban areas where both spatial and temporal variability are critical.