The inherent uncertainties in traditional hydrological models present significant chal-lenges for accurately simulating runoff. Combining machine learning models with tradi-tional hydrological models is an essential approach to enhancing the runoff modeling capabilities of hydrological models. However, research on the impact of mixed models on runoff simulation capability is limited. Therefore, this study uses the traditional hy-drological model SIMHYD and the machine learning model LSTM (Long Short-Term Memory) to construct two coupled models: a direct coupling model and a dynamically improved predictive validity hybrid model. These models were evaluated using the US CAMELS dataset to assess the impact of the two model combination methods on runoff modeling capabilities. The results indicate that the runoff modeling capabilities of both model combination methods were improved compared to individual models, with the dynamically improved predictive validity hybrid model demonstrating the optimal mod-eling capability. Compared to LSTM, this hybrid model showed a 12.8% increase in the Nash-Sutcliffe efficiency (NSE) median value for daily runoff during the validation pe-riod, a 28.4% increase in the NSE median value for high flows compared to SIMHYD, this hybrid model showed a 12.5% increase in the NSE median value for daily runoff during the validation period, a 23.6% increase in the NSE median value for high flows, and a significant improvement in the stability of low-flow runoff simulations. In per-formance testing involving varying training period lengths, the PE_trend model trained for 12 years exhibited the best performance, showing a 3.5% and 1.5% increase in the median NES compared to training periods of 6 years and 18 years, respectively