摘要
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。
Suspended solid concentration （SSC） is an important parameter of the environmental assessment. Parameter selection problem is transformed into the optimization problem. Particle Swarm Optimizer （ PSO ） is used to optimize the Radial Basis Function （RBF） to establish an improved neural network monitoring model in the coastal of South China. Based on the ETM ＋ and the measured data from Environmental Protection Department to construct a prediction model between the spectral reflectance and the SSC, and to test the model . It＇s concluded that the PSO_RBF neural network has a better fit with the actual value,and the accuracy is 80%. It has a significant improve compared with the linear model and traditional RBF network model.
出处
《海洋环境科学》
CAS
CSCD
北大核心
2013年第5期669-673,共5页
Marine Environmental Science
基金
国家自然科学基金资助项目(U0933005)
