论文部分内容阅读
悬浮物浓度(suspended solid concentration,SSC)是近岸海域环境评价的重要参数,利用粒子群优化算法(PSO)优化径向基函数(RBF)神经网络,将网络结构中参数的选取转化为参数的优化,建立一种改进的用于南海近岸水体悬浮物浓度监测评估的神经网络模型。基于2009年3月份的ETM+影像数据和香港环保署实测采样点数据,建立光谱反射率与悬浮物浓度之间的预测模型。结果表明,PSO_RBF网络模型的预测结果与实际情况吻合度较高,模型精度达到80%,与线性模型和传统RBF网络模型相比,预测精度有了明显的提升。
The suspended solid concentration (SSC) is an important parameter of offshore environment assessment. By using the Particle Swarm Optimization (PSO) algorithm, the Radial Basis Function (RBF) neural network is optimized and the parameter selection in the network structure is transformed into the parameter Optimize and establish an improved neural network model for monitoring and evaluating the concentration of suspended matter in coastal waters of the South China Sea. Based on the March 2009 ETM + image data and the data collected by the Hong Kong Environmental Protection Agency (EPD), a prediction model was established between spectral reflectance and suspended matter concentration. The results show that the prediction results of the PSO_RBF network model are in good agreement with the actual situation, and the accuracy of the model is up to 80%. Compared with the linear model and the traditional RBF network model, the prediction accuracy has been significantly improved.