Accurately Predicting Spatiotemporal Variations of Near-Surface Nitrous Acid (HONO) Based on a Deep Learning Approach

Gaseous nitrous acid (HONO) is identified as a critical precursor of hydroxyl radicals (OH), influencing atmospheric oxidation capacity and the formation of secondary pollutants. However, large uncertainties persist regarding its formation and elimination mechanisms, impeding accurate simulation of HONO levels using chemical models. In this study, a deep neural network (DNN) model was established based on routine air quality data (O₃, NO₂, CO, and PM_2.5) and meteorological parameters (temperature, relative humidity, solar zenith angle, and season) collected from four typical megacity clusters in China. The model exhibited robust performance on both the train sets [slope = 1.0, r² = 0.94, root mean squared error (RMSE) = 0.29 ppbv] and two independent test sets (slope = 1.0, r² = 0.79, and RMSE = 0.39 ppbv), demonstrated excellent capability in reproducing the spatiotemporal variations of HONO, and outperformed an observation-constrained box model incorporated with newly proposed HONO formation mechanisms. Nitrogen dioxide (NO₂) was identified as the most impactful features for HONO prediction using the SHapely Additive exPlanation (SHAP) approach, highlighting the importance of NO₂ conversion in HONO formation. The DNN model was further employed to predict the future change of HONO levels in different NO_x abatement scenarios, which is expected to decrease 27-44% in summer as the result of 30-50% NO_x reduction. These results suggest a dual effect brought by abatement of NO_x emissions, leading to not only reduction of O₃ and nitrate precursors but also decrease in HONO levels and hence primary radical production rates (P_ROx). In summary, this study demonstrates the feasibility of using deep learning approach to predict HONO concentrations, offering a promising supplement to traditional chemical models. Additionally, stringent NOx abatement would be beneficial for collaborative alleviation of O₃ and secondary PM2.5.