[Key Drivers of PM_2.5 in Qingdao from 2013 to 2023 Using an Interpretable Machine Learning Model]

To elucidate the deceleration trend in PM_2.5 concentration reduction and its formation mechanisms， this study analyzed PM_2.5 concentration variations in Qingdao from 2013 to 2023， combined with factors such as air pollutants， meteorology， and emissions. A phased interpretable machine learning model was applied to predict the variations of PM_2.5， investigate the formation mechanisms， and identify key drivers under evolving environmental policies. The results showed that PM_2.5 concentration decreased from （56.3±43.66） μg·m^-3 in 2013 to （30.2±24.50） μg·m^-3 in 2023 in Qingdao， with a reduction of approximately 46.3%， primarily driven by the reduction in secondary aerosols. Notably， the fastest decline of PM_2.5 occurred before 2017 at a rate of -4.33 μg·（m³·a）^-1， mainly due to reduced formation of secondary sulfate from the end-of-pipe control in the industrial and power sectors. After 2017， the deceleration in the decline of PM_2.5 concentrations stemmed from asynchronous reductions in sulfate， nitrate， and ammonium precursors， leading to enhanced secondary PM_2.5 formation. The machine learning model indicated the enhanced sensitivity of PM_2.5 to NO₂ under low SO₂ conditions， with the contribution of NO₂ to PM_2.5 concentrations increasing by approximately 6%， while that of SO₂ became negligible. Additionally， meteorological factor contribution to PM_2.5 concentrations increased by 5.1%. PM_2.5 concentrations exhibited a seasonal variation in the order of winter > spring > autumn > summer. Influenced by increased primary emissions from the residential sector， winter PM_2.5 concentrations showed the slowest decline over the years. Therefore， controlling residential sources can reduce primary PM_2.5 emissions， and a coordinated multi-pollutant emission control strategy can effectively reduce secondary PM_2.5 formation.