基于ARIMA-RBF神经网络的沿海港口吞吐量预测研究

在沿海吞吐量预测中，影响因素多且复杂，传统的计量经济模型很难得到满意的结果。针对此特点，提出一种组合预测模型，先后用ARIM A模型和RBF神经网络模型探求港口吞吐量历史数据的线性和非线性变化规律，最后将两者预测结果组合。对福建省港口货物吞吐量预测作为实例进行验证，结果表明，相对单一预测模型，该方法的预测精确度更高。

Research on Coastal Ports Throughput Prediction Based on RBF Neural Network and ARIMA Series

Coastal ports throughput forecast scientifically is very important to the decision making of transportation and economic development strategies .In the forecast of coastal ports throughput ,it is hard to obtain the satisfactory results with the traditional individual econometric forecasting methods and models for its various relative factors .Therefore ,a combinational model is presented ,which uses ARIMA forecast method and RBF neural network model to find out the change regulation of costal ports throughput .At last ,a forecast example of coastal throughput in Fujian province is presented , and the results prove that the model for forecasting coastal throughput is effective and feasible ,and it has a good practical value .