论文部分内容阅读
根据马尔可夫链不同步长的状态转移概率矩阵间存在的关系,在充分运用历史样本信息的基础上,采用自相关技术确定模型的显著相关历史状态步长,以熵权描述历史状态对未来状态预测的影响,构建了可调整状态转移概率矩阵的改进马尔可夫链预测模型。并将该模型应用于梅雨和干旱强度指数状态预测中。与已有的马尔可夫链预测模型比较结果表明,改进的马尔可夫链预测模型对梅雨和干旱强度指数状态预测更准确,状态转移概率矩阵和权重的确定更为合理,在水文水资源预测中具有推广应用价值。
According to the relationship between the state transition probability matrices with different steps in Markov chain, based on the full use of historical sample information, the autocorrelation technique is used to determine the significant related historical step of the model. The entropy weight is used to describe the historical state of the future State prediction, an improved Markov chain prediction model with adjustable state transition probability matrix is constructed. The model is applied to predict the state of meiyu and drought intensity index. Compared with the existing Markov chain prediction model, the results show that the improved Markov chain prediction model is more accurate for predicting the state of meiyu and drought intensity index, and the determination of state transition probability matrix and weight is more reasonable. In the prediction of hydrology and water resources In the promotion and application of value.