Seamless Hourly Estimation of Negative Air Ion Concentrations: Integrating Hybrid Stacked Machine Learning Models With Kriging Spatiotemporal Augmentation.

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 R2 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. Plain Language Summary: Our study advances the environmental science by developing a machine‐learning model capable of estimation the hourly concentrations of negative air ions (NAIs) across Zhejiang Province, China. NAIs, vital for air purification and human health, are significantly related to environmental conditions. Taking advantage of a novel approach that reduces errors commonly seen in similar models, we provide a highly accurate, hour‐by‐hour analysis of air quality. Our research goes beyond mere prediction; it investigates how various factors like vegetation, soil type, and weather events influence NAI levels. The insights gained offer a comprehensive view of how NAI distribution changes over time and across different landscapes, informing environmental policy and public health strategies with precise air quality assessments. This study contributes significantly to the field by introducing an essential tool for continuous environmental monitoring, thereby facilitating more effective decision‐making in environmental and public health sectors. Key Points: A hybrid stacking machine learning framework shows superior accuracy (R2 = 0.90), combing a filter pipeline dealing with more than 200 variablesKriging Spatiotemporal Augmentation (KSTA) as a pseudo‐label strategy to resolve spatial overfitting due to sparse sitesAn hourly estimate of NAIs reveals NAIs dynamics correlations with environmental factors and land use, supporting public health policy [ABSTRACT FROM AUTHOR]