Abstract
Negative Air Ions (NAIs), essential for environmental and human health, facilitate air purification and offer antimicrobial benefits. Our study achieves hourly estimations of NAIs using a machine learning framework, developed from a multi-layer selection pipeline of over 200 variables, to identify the key determinants critical for adapting to high-resolution NAIs dynamics. Addressing site sparsity and NAIs volatility, we introduced a hybrid stacking incorporating pseudo sites generated from Kriging Spatiotemporal Augmentation (KSTA) to mitigate spatial overfitting. Our approach, validated in Zhejiang, China, demonstrates exceptional accuracy, achieving R
2 values of 0.90 (sample-based), 0.85 (temporal-based), and 0.79 (site-based). This work not only sheds light on NAIs behavior in relation to diurnal shifts, land use, and environmental events, but also integrates a health grading system, enhancing public health strategies through precise air quality assessment.