论文部分内容阅读
为快速高效地进行云检测和云相态识别,提出了基于BP神经网络的云检测和云相态识别方法,并针对中分辨率成像光谱仪(MODIS)的相关数据建立了BP神经网络。利用该算法对MODIS图像进行了云检测和云相态识别,并把识别结果与MOD06数据进行了对比,对比结果表明,该算法对冰云、水云以及混合云的识别准确率分别达到了100%、100%以及99.94%。该算法快速、准确,消除了未确定态,具有很强的自主学习能力。
In order to quickly and efficiently perform cloud detection and cloud phase identification, a cloud detection and cloud phase identification method based on BP neural network is proposed. A BP neural network is established for the relative data of mid-resolution imaging spectrometer (MODIS). By using this algorithm, cloud detection and cloud phase identification of MODIS images are carried out. The recognition results are compared with that of MOD06 data. The comparison results show that the accuracy of this algorithm for ice cloud, water cloud and hybrid cloud is 100 %, 100% and 99.94%. The algorithm is fast and accurate, eliminating the undetermined state, with strong self-learning ability.