Quantifying source contributions to ambient NH3 using Geo-AI with time lag and parcel tracking functions.

• AutoML, time lag and parcel tracking functions were used to develop model. • The SHAP function was used to analyze feature importance. • Developed model has the potential to account for up to 96% of the total variance. • Waterbody, traffic and agriculture were improtant factors for NH 3 concentrations. Ambient ammonia (NH 3) plays an important compound in forming particulate matters (PMs), and therefore, it is crucial to comprehend NH 3 ′s properties in order to better reduce PMs. However, it is not easy to achieve this goal due to the limited range/real-time NH 3 data monitored by the air quality stations. While there were other studies to predict NH 3 and its source apportionment, this manuscript provides a novel method (i.e., GEO-AI)) to look into NH 3 predictions and their contribution sources. This study represents a pioneering effort in the application of a novel geospatial-artificial intelligence (Geo-AI) base model with parcel tracking functions. This innovative approach seamlessly integrates various machine learning algorithms and geographic predictor variables to estimate NH 3 concentrations, marking the first instance of such a comprehensive methodology. The Shapley additive explanation (SHAP) was used to further analyze source contribution of NH 3 with domain knowledge. From 2016 to 2018, Taichung's hourly average NH 3 values were predicted with total variance up to 96%. SHAP values revealed that waterbody, traffic and agriculture emissions were the most significant factors to affect NH 3 concentrations in Taichung among all the characteristics. Our methodology is a vital first step for shaping future policies and regulations and is adaptable to regions with limited monitoring sites. [ABSTRACT FROM AUTHOR]