This study, through establishing the regression model, inverts the annual runoff of 1766- 1911 AD, builds up and improves the annual runoff series of 1766- 2000 AD in flood season in Lanzhou, Qingtongxia and Sanmenxia by using the records of water level stake of three gauge stations in the Upper- Middle Yellow River (UMYR) in the Qing Dynasty. Combining the annual runoff of 1766- 1911 AD at Tangnaihai Station in riverhead reach, the study builds the runoff series of four stations at the riverhead and UMYR, which is presently the clearest runoff curve of the Yellow River by historical records. According to the research, the heavy "river disaster" that appeared in the lower Yellow River in the mid-19th century was caused by sudden changes of the runoff at the Qingtongxia-Sanmenxia section. Drought period of the river in the 1920s existed from the riverhead to the middle reach, but it was not caused by sudden changes. Meanwhile, the study also reveals that PDO and the runoff of the UMYR had a periodic inverse phase relationship on the interdecadal scale. In the early and mid-20th century, the runoff of the four stations had an inverse phase relationship on the scale of 8-16 years. In the 1830-1850s, the inverse phase relationship between PDO and flow on the scale of 4- 6 years was more obvious at Lanzhou- Sanmenxia section. According to the interactive wavelet analysis, there is a significant inverse correlation between PDO and the amount of water in the UMYR on a scale of 8- 16 years, but only at the Sanmenxia- Lanzhou section, suggesting that the relationship between summer rainfall in the UMYR and PDO had obvious temporal and spatial differences. (1) During the study period, the change of runoff flow in the UMYR had obvious differences; On the natural state, there was no obvious consistency in the flow change of the UMYR. The occurrence of sudden change time point was not synchronous in history. In the long term, the runoff change of the UMYR had a unique phenomenon. The simultaneous reduction of flows of each reach since the 1970s is a special phenomenon, at least it is the only phenomenon discussed in this study within this time range. (2) It is concluded that the correlation between the PDO and runoff in the UMYR is periodic and there is no special obvious linear relationship, but regional differences are more obvious. The inverse correlation between PDO and runoff in the study reaches is mainly on a decadal scale. The Lanzhou- Sanmenxia section is relatively sensitive in the face of the change of the PDO on the decadal scale. When formulating the water resources strategy of the Yellow River, we should notice the differences in the response of different sections to the same environmental background. (3) In the mid- 19th century, many large- scale floods in the lower reach resulted from the sudden increase of runoff in the middle reach. In the reign of Emperor Daoguang of the mid- 19th century, the Qing Dynasty declined rapidly. During this period, large- scale flood disasters occurred in many parts of eastern China, especially in the populous North China Plain and Taihu Basin. The flood brought huge financial and social losses. Among them, eastern Henan of North China Plain suffered from the flood disaster in successive years by burst of the Yellow River in the 1840s, and the central government spent a huge amount of money to solve the problem of the river, which greatly aggravated the financial difficulties in that period.