The seepage of the dam is an important representation of the operation characteristics of thedam, and there are many factors affecting the seepage with a certain lag. It is still difficult topredict its change and sensitivity because of complex operating conditions. At present, the lagsensitivityof influence factors of the dam seepage has not been studied. The time seriesinfluence factors of seepage are determined by HTRT (hydrostatic-thermal-rainfall-time)model in this paper. To avoid the pseudo fitting of conventional methods, HTRT model nestedrandom forest algorithm is used to establish the predicting model of the dam seepage. AndMIC algorithm is used to achieve the dual purposes of time lag and sensitivity analysis. Firstly,the time lag of relationship between seepage and its influencing factors is characterized, andthe most appropriate lag time of the HTRT model factors is determined. Secondly, independentcorrelation analysis on all influencing factors is carried out and the sensitivity of each factor isanalyzed by MIC. Meanwhile, the sensitivity of the factors to seepage is quantitatively analyzedby the two parameters of %IncMSE and IncNodePurity of RF algorithm. The sensitivity ofinfluencing factors is analyzed by comparing MIC results with RF results. Combined with thecase, taking the error of fitting prediction as the evaluation index of seepage prediction, theprediction accuracy of MIC-RF model, RF model and MIC-BPNN (Back Propagation neuralnetwork) model is calculated and compared. Case study showed that MIC- RF monitoringmodel has high prediction accuracy, strong adaptability and high robustness in dam seepage,and the sensitivity and time lag of influencing factors can be quantitatively analyzed. Thewater pressure and rainfall of the lag time are 14 days and 16 days respectively. The sensitivitystudy of the time series influencing factors of seepage showed that the water pressurecomponent is the main controlling factor of seepage, and rainfall component is more sensitiveto later stage. The MIC-RF model can be used as a new dam seepage safety monitoringmodel.