Atmospheric correction over coastal waters using multilayer neural networks
Atmospheric correction over coastal waters using multilayer neural networks
复制标题
DOI：
10.1016/j.rse.2017.07.016
复制
发表时间：
2017-09
影响因子：
13.5
通讯作者：
Yongzhen Fan;Wei Li;C. Gatebe;C. Jamet;G. Zibordi;T. Schroeder;K. Stamnes
中科院分区：
文献类型：
--
作者：
Yongzhen Fan;Wei Li;C. Gatebe;C. Jamet;G. Zibordi;T. Schroeder;K. Stamnes
标准的大气校正(AC)算法在水的固有光学性质(IOP)与有色颗粒相关的开阔海域工作得很好。然而，浑浊近岸水域的IOPS可能会随着色素颗粒、悬浮无机颗粒和有色溶解有机物(CDOM)的不同而独立变化。在浑浊的沿海水域，标准交流算法往往存在很大的误差，这可能会导致负的离水辐射(LW)或遥感反射比(RRS)。提出了一种基于多层神经网络(MLNN)的近海大气校正新算法。我们使用大气-海洋耦合辐射传输模式同时模拟大气顶部的瑞利校正辐射(TOA)和地表上方的RRS，并训练一个多层神经网络(MLNN)直接从TOALrc得到气溶胶光学厚度(AOD)和RRS。该方法使用合成数据集和气溶胶机器人网络-海洋颜色(AERONET-OC)测量进行了验证。SEADAS NIR算法、SEADAS NIR/SWIR算法和CASE 2区域水海岸颜色(C2RCC)算法的MODIS版本也被包括在与AERONET-OC测量的比较中。用皮尔逊相关系数(R)、平均百分比差(APD)、平均百分比偏差和均方根差(RMSD)四个统计指标对AC算法的性能进行了评估。与AERONET-OC测量结果的比较表明，MLNN算法显著提高了归一化Lwin蓝波段(412 nm和443 nm)的恢复能力，而对绿波段和红波段的恢复效果较其他三种算法略有改善。在全球范围内，与标准SEADAS NIR算法相比，MLNN算法在归一化Lwwt中减少了高达13%的apd，在绿色和红色波段减少了2-7%。与标准SEADAS近红外算法相比，在波罗的海等高吸收率的近海水域，MLNN算法在归一化的Lww蓝波段的时差降低了60%以上，而在高度散射的近海水域，例如黑海，MLNN算法使时差降低了25%以上。这些结果表明，MLNN算法适合在浑浊的近海水域应用。MLNN算法在几个沿海地区的MODIS Aqua图像上的应用也表明，该算法对由于陆地和云边的反光或邻近效应造成的污染具有较强的鲁棒性和恢复能力。一旦神经网络经过适当的训练，MLNN算法是非常快的，因此适合于操作使用。MLNN算法的一个显著优点是它不需要SWIR波段。
Standard atmospheric correction (AC) algorithms work well in open ocean areas where the water inherent optical properties (IOPs) are correlated with pigmented particles. However, the IOPs of turbid coastal waters may independently vary with pigmented particles, suspended inorganic particles, and colored dissolved organic matter (CDOM). In turbid coastal waters standard AC algorithms often exhibit large inaccuracies that may lead to negative water-leaving radiances (Lw) or remote sensing reflectance (Rrs). We introduce a new atmospheric correction algorithm for coastal waters based on a multilayer neural network (MLNN) method. We use a coupled atmosphere-ocean radiative transfer model to simulate the Rayleigh-corrected radiance (Lrc) at the top of the atmosphere (TOA) and theRrsjust above the surface simultaneously, and train a MLNN to derive the aerosol optical depth (AOD) andRrsdirectly from the TOALrc. The method is validated using both a synthetic dataset and Aerosol Robotic Network – Ocean Color (AERONET–OC) measurements. The SeaDAS NIR algorithm, the SeaDAS NIR/SWIR algorithm, and the MODIS version of the Case 2 regional water - CoastColour (C2RCC) algorithm are also included in the comparison with AERONET–OC measurements. The performance of the AC algorithms is evaluated with four statistical metrics: the Pearson correlation coefficient (R), the average percentage difference (APD), the mean percentage bias, and the root mean square difference (RMSD). The comparison with AERONET–OC measurements shows that the MLNN algorithm significantly improves retrieval of normalizedLwin blue bands (412 nm and 443 nm) and yields minor improvements in green and red bands compared with the other three algorithms. On a global scale, the MLNN algorithm reduces APD in normalizedLwby up to 13% in blue bands and by 2–7% in green and red bands when compared with the standard SeaDAS NIR algorithm. In highly absorbing coastal waters, such as the Baltic Sea, the MLNN algorithm reduces APD in normalizedLwby more than 60% in blue bands compared to the standard SeaDAS NIR algorithm, while in highly scattering coastal waters, such as the Black Sea, the MLNN algorithm reduces APD by more than 25%. These results indicate that the MLNN algorithm is suitable for application in turbid coastal waters. Application of the MLNN algorithm to MODIS Aqua images in several coastal areas also shows that it is robust and resilient to contamination due to sunglint or adjacency effects of land and cloud edges. The MLNN algorithm is very fast once the neural network has been properly trained and is therefore suitable for operational use. A significant advantage of the MLNN algorithm is that it does not need SWIR bands.