Remote Sensing of Environment 199 (2017) 218–240 Contents lists available at ScienceDirect Remote Sensing of Environment journal homepage: www.elsevier.com/locate/rse Atmospheric correction over coastal waters using multilayer neural networks Yongzhen Fan a, * , Wei Li a , Charles K. Gatebe b , Cédric Jamet c , Giuseppe Zibordi d , Thomas Schroeder e , Knut Stamnes a a Light & Life Laboratory, Department of Physics and Engineering Physics, Stevens Institute of Technology, Hoboken, NJ 07307, USA b NASA’s Goddard Space Flight Center, Greenbelt, MD 20771, USA c Univ. Lille, CNRS, Univ. Littoral Côte d’Opale, UMR 8187, LOG, Laboratoire d’Océanologie et de Géosciences, F 62930 Wimereux, France d European Commission, Joint Research Centre, Institute for Environment and Sustainability, Ispra 21027, Italy e Commonwealth Scientific and Industrial Research Organisation (CSIRO), Oceans and Atmosphere, Brisbane, QLD 4001, Australia ARTICLE INFO Article history: Received 8 December 2016 Received in revised form 24 June 2017 Accepted 16 July 2017 Available online xxxx Keywords: Remote sensing Atmosphere correction Ocean color Coastal area Multilayer neural network SeaDAS AERONET-OC MODIS ABSTRACT 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 (L w ) or remote sensing reflectance (R rs ). 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 (L rc ) at the top of the atmosphere (TOA) and the R rs just above the surface simultaneously, and train a MLNN to derive the aerosol optical depth (AOD) and R rs directly from the TOA L rc . 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 normalized L w in 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 normalized L w by 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 normalized L w by 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. © 2017 Elsevier Inc. All rights reserved. 1. Introduction Atmospheric correction (AC) is the first and a very important step in many ocean color algorithms. Ideally, it should remove * Corresponding author. E-mail address: yfan@stevens.edu (Y. Fan). the radiance contribution of the atmosphere (including that of air molecules and aerosols) and surface reflection from the satellite measured radiances to produce water-leaving radiances (L w ), which can be used to derive ocean color products such as the chlorophyll- a concentration (CHLa). The atmosphere may contribute about 90% to the TOA radiance measured by a satellite sensor, and in coastal areas this contribution could be even higher, especially in the blue bands, or way less in sediment dominated extremely turbid waters, http://dx.doi.org/10.1016/j.rse.2017.07.016 0034-4257/© 2017 Elsevier Inc. All rights reserved.