Detection of single and multilayer clouds in an artificial neural network approach

Determining whether a scene observed with a satellite imager is composed of a thin cirrus over a water cloud or thick cirrus contiguous with underlying layers of ice and water clouds is often difficult because of similarities in the observed radiance values. In this paper an artificial neural network (ANN) algorithm, employing several Aqua MODIS infrared channels and the retrieved total cloud visible optical depth, is trained to detect multilayer ice-over-water cloud systems as identified by matched April 2009 CloudSat and CALIPSO (CC) data. The CC lidar and radar profiles provide the vertical structure that serves as output truth for a multilayer ANN, or MLANN, algorithm. Applying the trained MLANN to independent July 2008 MODIS data resulted in a combined ML and single layer hit rate of 75% (72%) for nonpolar regions during the day (night). The results are comparable to or more accurate than currently available methods. Areas of improvement are identified and will be addressed in future versions of the MLANN.

[1]  H. Chepfer,et al.  Assessment of Global Cloud Datasets from Satellites: Project and Database Initiated by the GEWEX Radiation Panel , 2013 .

[2]  Christian Jakob,et al.  The Response of the ECMWF Model to Changes in the Cloud Overlap Assumption , 2000 .

[3]  Patrick Minnis,et al.  Relationships among cloud occurrence frequency, overlap, and effective thickness derived from CALIPSO and CloudSat merged cloud vertical profiles , 2010 .

[4]  William B. Rossow,et al.  Sensitivity of Atmospheric Radiative Heating Rate Profiles to Variations of Cloud Layer Overlap , 2000 .

[5]  Michael J. Pavolonis,et al.  Daytime Cloud Overlap Detection from AVHRR and VIIRS , 2004 .

[6]  Anastasios N. Venetsanopoulos,et al.  Efficient learning algorithms for neural networks (ELEANNE) , 1993, IEEE Trans. Syst. Man Cybern..

[7]  Patrick Minnis,et al.  Ice cloud properties in ice-over-water cloud systems using Tropical Rainfall Measuring Mission (TRMM) visible and infrared scanner and TRMM Microwave Imager data , 2007 .

[8]  Patrick Minnis,et al.  Uncertainties Associated With the Surface Texture of Ice Particles in Satellite-Based Retrieval of Cirrus Clouds: Part II—Effect of Particle Surface Roughness on Retrieved Cloud Optical Thickness and Effective Particle Size , 2008, IEEE Transactions on Geoscience and Remote Sensing.

[9]  Steven D. Miller,et al.  Estimating nocturnal opaque ice cloud optical depth from MODIS multispectral infrared radiances using a neural network method , 2016 .

[10]  Patrick Minnis,et al.  Estimation of water cloud properties from satellite microwave , 1998 .

[11]  Patrick Minnis,et al.  Evaluation of Satellite-Based Upper Troposphere Cloud Top Height Retrievals in Multilayer Cloud Conditions During TC4 , 2010 .

[12]  Patrick Minnis,et al.  Parameterizations of reflectance and effective emittance for satellite remote sensing of cloud properties , 1998 .

[13]  Patrick Minnis,et al.  Radiative effect differences between multi-layered and single-layer clouds derived from CERES, CALIPSO, and CloudSat data , 2011 .

[14]  S. Kox,et al.  Retrieval of cirrus cloud optical thickness and top altitude from geostationary remote sensing , 2014 .

[15]  Fu-Lung Chang.  On the satellite determination of multi-layered multi-phase cloud properties , 2010 .

[16]  Zhanqing Li,et al.  A New Method for Detection of Cirrus Overlapping Water Clouds and Determination of Their Optical Properties , 2005 .

[17]  Steven Platnick,et al.  Multilayer Cloud Detection with the MODIS Near-Infrared Water Vapor Absorption Band , 2010 .

[18]  Jerome Riedi,et al.  A Global Multilayer Cloud Identification with POLDER/PARASOL , 2017 .

[19]  Sunny Sun-Mack,et al.  CERES Edition-2 Cloud Property Retrievals Using TRMM VIRS and Terra and Aqua MODIS Data—Part I: Algorithms , 2011, IEEE Transactions on Geoscience and Remote Sensing.

[20]  Patrick Minnis,et al.  Ice Cloud Properties in Ice-Over-Water Cloud Systems Using TRMM VIRS and TMI Data , 2007 .