Estimating the pollution loads in the Tuhai River is essential for developing a water quality standard scheme. This study utilized the improved output coe cient method to estimate the total pollution loads in the river basin while analyzing the in uencing factors based on the STIRPAT (Stochastic Impacts by Regression on Population, A uence, and Technology) model. Findings indicated that the projected point source pollution loads for total phosphorus, COD, and ammonia nitrogen would amount to 3937.22 t, 335523.25 t, and 13946.92 t in 2021, respectively. Among these, COD pollution would pose the greatest concern. The primary contributors to the pollution loads were rural scattered life, large-scale livestock and poultry breeding, and surface runoff. Per capita GDP emerged as the most in uential factor affecting the pollution loads, followed by cultivated land area, while the urbanization rate demonstrated the least impact.1 Background of the researchThe conservation of the environment and high-quality development in the Yellow River basin have become vital elements of national strategy. The Tuhai River, located on the north side of the Yellow River, has been heavily polluted since the 1970s due to the population growth and industrial development of coastal areas. According to the National Surface Water Quality Automatic Monitoring Real-time Data Release System, since the third quarter of 2022, the surface water quality of Xiakou, Qianyoufang and Fuguo state-controlled sections of the Tuhai River has been classi ed V and inferior V many times, and the pollution problem of the Tuhai River is more serious.Accurately estimating the non-point source pollution load in the basin is essential for developing standard plans and implementing effective treatment measures. Researchers have proposed various methods to estimate non-point source pollution loads, including the mechanism model method and the output coe cient method (Xue and Yang 2009). Mechanism model methods, such as SWAT, HSPF, and AnnAGNPS models, need to take into account the water cycle processes, such as rainfall, runoff, and evaporation, and combine with the watershed production and sinks to analyze the amount of non-point source pollution loads (Shen et al. 2014;Wang et al. 2018; Ti et al. 2017). However, this method requires a large amount of primary geographic data and is complex. The output coe cient method, on the other hand, estimates the watershed's pollutant output by utilizing readily available data such as the current land use status (