Continued climate change has led to the melting of polar ice and the opening of the Arctic passage. Because of the uncertainty of navigability in a key sea through Arctic Northeast Passage and the typical time series nature of the statistical data, the assessment and forecasting technology for the risk affecting the navigability of the Northeast Passage based on Dynamic Bayesian Network is proposed. Through determination of the key sea and index; construction of the structure and parameter learning of the Bayesian Network; reasoning and computation based on evidence; and testing of the superiority of Dynamic Bayesian Network, a risk assessment and forecasting model based on Dynamic Bayesian Network is established. The results show that the Dynamic Bayesian Network technology can not only deal with the dynamic data but can also reduce the effect of inaccurate data on the results. The Dynamic Bayesian Network is superior to the traditional evaluation technology, and the predicted results of the model are more accurate in the short term. This result has an important significance for judging the navigability of the Arctic Northeast Passage.