光电工程, 2015, 42 (12): 0020, 网络出版: 2016-01-20
SOFM 神经网络的FY-3A/VIRR 多光谱图像云相态反演方法
A Cloud Phase Retrieval Approach Based on SOFM Neural Network Using FY-3A/VIRR Multi-channel Images
人工神经网络 云相态 阈值方法 业务产品 artificial neural network FY-3A/VIRR FY-3A/VIRR cloud phase threshold method operational product
摘要
针对使用阈值方法反演云相态存在的不足,本文提出了一种基于Self-Organizing Feature Map(SOFM)神经网络的云相态反演方法。采用覆盖中国地域的FengYun-3A/Visible and InfRared Radiometer(FY-3A/VIRR)多光谱图像开展了云相态反演实验。实验结果表明:SOFM 神经网络方法与K-means 方法的结果具有较好的一致性,且SOFM神经网络方法反演云相态的准确性优于FY-3A 业务产品。此外,SOFM 神经网络方法反演云相态所需时间仅为FY-3A 业务产品的约1/3。
Abstract
To address problems of cloud phase retrieval using the threshold method, a cloud phase retrieval approach based on Self-Organizing Feature Map (SOFM) neural network was proposed. Cloud phase retrieval experiments were conducted using FengYun-3A/Visible and InfRared Radiometer (FY-3A/VIRR) multi-channel images, which cover the China’s territory. Experiment results indicated that the results from the SOFM neural network approach and the K-means method have good consistency, and the retrieval accuracy of the SOFM neural network exceeds that of the FY-3A operational product. Additionally, retrieval time consumed by the SOFM neural network approach is only about one third of that of the FY-3A operational product.
郭晶, 杨春平, 叶玉堂, 饶长辉. SOFM 神经网络的FY-3A/VIRR 多光谱图像云相态反演方法[J]. 光电工程, 2015, 42(12): 0020. GUO Jing, YANG Chunping, YE Yutang, RAO Changhui. A Cloud Phase Retrieval Approach Based on SOFM Neural Network Using FY-3A/VIRR Multi-channel Images[J]. Opto-Electronic Engineering, 2015, 42(12): 0020.