Coking enterprises in China are recognized as significant sources of SO2 emissions, making them a key industry with high levels of SO2 intensity. Assessing the health risks for different populations around these coking enterprises nationwide is challenging due to the lack of clarity regarding SO2 concentrations at varying distances from these facilities. To address this issue, we developed a buffer Latin hypercube XGBoost particle swarm optimization (BLH-XGB-PSO) algorithm that combines efficient global search capabilities and accurate prediction performance. This algorithm enables effective traversal of monitoring points located at varying distances and directions around the enterprise while automatically seeking optimal model parameters. Using this model, we accurately predicted the concentration of SO2 every 0.5 km within a 10 km radius around China's coking enterprises in 2017, achieving a high prediction accuracy with an R2 value of 0.97. The prediction results indicate that the highest concentration of SO2 in the vicinity of Chinese coking enterprises is observed in the central region of Shanxi province (65.88 μg/m3). The average annual concentration of SO2 around all production enterprises amounts to 27.9 μg/m3. Furthermore, we conducted an assessment on the impact of coking enterprises on different age groups, genders, and regions regarding the number of affected individuals, health exposure risks, and control effectiveness. Our findings reveal that in 2017, around 5.5 thousand newborns (14.5% male, 85.5% female) had a hazard quotient (HQ) exceeding threshold value which poses potential human health risks. The implementation of the control policy successfully prevented 64,375 thousand people from being affected by higher concentrations of SO2. Greater attention should be devoted to the health risks faced by newborns residing in proximity to coking enterprises, with a particular emphasis on female infants.