摘要
目前激光荧光遥感是探测海面溢油最有效的工具。作者将神经网络(ANN)的自组织特征映射SOM模型引入激光遥感的荧光光谱鉴别领域。本文主要进行的是理论建模和分析工作,而且用计算机软件方法实现了神经网络的模式识别和分类功能,对推广能力进行了实验分析。经过改进神经网络已具有比较理想的推广能力,并认为SOM应作为溢油识别的较理想方法。
In this paper, an artificial neural network (ANN) approach is applied for the spectral data analysis and model of airborne laser (fluorosensor) in order to differentiate between classes of oil at sea. The SOM network used and ANN are trained and tested using the sample data set to the network. The ANN models in theory was not only developed, but also completed software package for spectra intelligent analysis for the (airborne) detection of oil spills at sea by laser-induced fluorescence. The ANN model would play a significant role in the ocean oil-spill (identification) in the future.
出处
《海洋环境科学》
CAS
CSCD
北大核心
2004年第1期47-49,共3页
Marine Environmental Science
