Cirrus cloud retrieval with MSG/SEVIRI using artificial neural networks

Cirrus clouds play an important role in climate as they tend to warm the Earth-Atmosphere system. Nevertheless they remain one of the largest uncertainties in atmospheric research. To better understand the physical processes of cirrus clouds and their climate impact, enhanced satellite observations are necessary. In this paper we present a new algorithm, CiPS (Cirrus Properties from SEVIRI), that detects cirrus clouds and retrieves the corresponding cloud top height, ice optical thickness and ice water path using the SEVIRI imager aboard the geostationary Meteosat Second Generation satellites. CiPS utilises a set of artificial neural networks trained with SEVIRI thermal observations, CALIOP backscatter products, the ECMWF surface temperature and auxiliary data. CiPS detects 71 and 95 % of all cirrus clouds with an optical thickness of 0.1 and 1.0 respectively, that are retrieved by CALIOP. Among the cirrus free pixels, CiPS classifies 96 % correctly. With respect to CALIOP, the cloud top height retrieved by CiPS has a mean absolute percentage error of 10 % or less for cirrus clouds with a top height greater than 8 km. For the ice optical thickness, CiPS has a mean absolute percentage error of 50 % or less for cirrus clouds with an optical thickness between 0.35 and 1.8, and of 100 % or less for cirrus clouds with an optical thickness down to 0.07, with respect to the optical thickness retrieved by CALIOP. The ice water path retrieved by CiPS shows a similar performance, with mean absolute percentage errors of 100 % or less for cirrus clouds with an ice water path down to 1.7 g m −2 . Since the training reference data from CALIOP only include ice water path and optical thickness for comparably thin clouds, CiPS does also retrieve an opacity flag, which tells whether a retrieved cirrus is likely to be too thick for CiPS to accurately derive the ice water path and optical thickness. By retrieving CALIOP like cirrus properties with the large spatial coverage and high temporal resolution of SEVIRI during both day and night, CiPS is a powerful tool for analysing the temporal evolution of cirrus clouds including their optical and physical properties. To demonstrate this, the life cycle of a thin cirrus cloud is analysed.

[1]  L. Bugliaro,et al.  Characterisation of the artificial neural network CiPS for cirrus cloud remote sensing with MSG/SEVIRI , 2017 .

[2]  Zhibo Zhang,et al.  Retrieval of ice cloud properties using an optimal estimation algorithm and MODIS infrared observations: 1. Forward model, error analysis, and information content , 2016, Journal of geophysical research. Atmospheres : JGR.

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

[4]  Steven Platnick,et al.  Resolving ice cloud optical thickness biases between CALIOP and MODIS using infrared retrievals , 2015 .

[5]  H. Mannstein,et al.  Contrail life cycle and properties from 1 year of MSG/SEVIRI rapid-scan images , 2015 .

[6]  Steven Platnick,et al.  Retrieval of Cirrus Cloud Optical Depth under Day and Night Conditions from MODIS Collection 6 Cloud Property Data , 2015, Remote. Sens..

[7]  Fabio Del Frate,et al.  Multilayer Perceptron Neural Networks Model for Meteosat Second Generation SEVIRI Daytime Cloud Masking , 2015, Remote. Sens..

[8]  Jürgen Schmidhuber,et al.  Deep learning in neural networks: An overview , 2014, Neural Networks.

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

[10]  Steven Platnick,et al.  Remote sensing of cloud top pressure/height from SEVIRI: analysis of ten current retrieval algorithms , 2014 .

[11]  J. F. Meirink,et al.  CLAAS: the CM SAF cloud property data set using SEVIRI , 2014 .

[12]  Jana Mendrok,et al.  SPARE‐ICE: Synergistic ice water path from passive operational sensors , 2014 .

[13]  Dong L. Wu,et al.  MLS and CALIOP Cloud Ice Measurements in the Upper Troposphere: A Constraint from Microwave on Cloud Microphysics , 2014 .

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

[15]  Tom Schaul,et al.  No more pesky learning rates , 2012, ICML.

[16]  Luca Bugliaro,et al.  An improved cirrus detection algorithm MeCiDA2 for SEVIRI and its evaluation with MODIS , 2012 .

[17]  Mark A. Vaughan,et al.  Airborne validation of cirrus cloud properties derived from CALIPSO lidar measurements: Optical properties: CALIPSO VALIDATION-OPTICAL PROPERTIES , 2012 .

[18]  D. Winker,et al.  Cloud ice water content retrieved from the CALIOP space‐based lidar , 2012 .

[19]  Yoshua Bengio,et al.  Random Search for Hyper-Parameter Optimization , 2012, J. Mach. Learn. Res..

[20]  Klaus-Robert Müller,et al.  Efficient BackProp , 2012, Neural Networks: Tricks of the Trade.

[21]  M. Vaughan,et al.  Airborne validation of cirrus cloud properties derived from CALIPSO lidar measurements: Spatial properties , 2011 .

[22]  Ralf Bennartz,et al.  Retrieval of two‐layer cloud properties from multispectral observations using optimal estimation , 2011 .

[23]  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.

[24]  J. Thepaut,et al.  The ERA‐Interim reanalysis: configuration and performance of the data assimilation system , 2011 .

[25]  H. Chepfer,et al.  Properties of cirrus and subvisible cirrus from nighttime Cloud‐Aerosol Lidar with Orthogonal Polarization (CALIOP), related to atmospheric dynamics and water vapor , 2011 .

[26]  Mathias Milz,et al.  Assessing observed and modelled spatial distributions of ice water path using satellite data , 2011 .

[27]  Philip Watts,et al.  Global retrieval of ATSR cloud parameters and evaluation (GRAPE): dataset assessment , 2010 .

[28]  B. Mayer,et al.  Validation of cloud property retrievals with simulated satellite radiances: a case study for SEVIRI , 2010 .

[29]  Claudia J. Stubenrauch,et al.  A 6-year global cloud climatology from the Atmospheric InfraRed Sounder AIRS and a statistical analysis in synergy with CALIPSO and CloudSat , 2010 .

[30]  K. Rosenlof,et al.  In Situ and Lidar Observations of Tropopause Subvisible Cirrus Clouds During TC4 , 2010 .

[31]  E. O'connor,et al.  The Evaluation of CloudSat and CALIPSO Ice Microphysical Products Using Ground-Based Cloud Radar and Lidar Observations , 2010 .

[32]  D. Winker,et al.  Overview of the CALIPSO Mission and CALIOP Data Processing Algorithms , 2009 .

[33]  K. Stamnes,et al.  CALIPSO/CALIOP Cloud Phase Discrimination Algorithm , 2009 .

[34]  David M. Winker,et al.  Fully Automated Detection of Cloud and Aerosol Layers in the CALIPSO Lidar Measurements , 2009 .

[35]  David M. Winker,et al.  The CALIPSO Lidar Cloud and Aerosol Discrimination: Version 2 Algorithm and Initial Assessment of Performance , 2009 .

[36]  Michael J. Pavolonis,et al.  Gazing at Cirrus Clouds for 25 Years through a Split Window. Part I: Methodology , 2009 .

[37]  Mark A. Vaughan,et al.  The Retrieval of Profiles of Particulate Extinction from Cloud-Aerosol Lidar Infrared Pathfinder Satellite Observations (CALIPSO) Data: Algorithm Description , 2009 .

[38]  Kuo-Nan Liou,et al.  Cirrus cloud optical and microphysical properties determined from AIRS infrared spectra , 2009 .

[39]  Dong Liu,et al.  Cirrus clouds and deep convection in the tropics: Insights from CALIPSO and CloudSat , 2009 .

[40]  Steven A. Ackerman,et al.  Cloud Detection with MODIS. Part II: Validation , 2008 .

[41]  Steven A. Ackerman,et al.  Global Moderate Resolution Imaging Spectroradiometer (MODIS) cloud detection and height evaluation using CALIOP , 2008 .

[42]  W. Paul Menzel,et al.  MODIS Global Cloud-Top Pressure and Amount Estimation: Algorithm Description and Results , 2008 .

[43]  Luca Bugliaro,et al.  Technical note: A new day- and night-time Meteosat Second Generation Cirrus Detection Algorithm MeCiDA , 2007 .

[44]  Dong L. Wu,et al.  Cloud ice: A climate model challenge with signs and expectations of progress , 2007 .

[45]  David M. Winker,et al.  Airborne validation of spatial properties measured by the CALIPSO lidar , 2007 .

[46]  P. Pilewskie,et al.  Effects of ice crystal habit on thermal infrared radiative properties and forcing of cirrus , 2007 .

[47]  J. C. Perez,et al.  Remote Sensing of Water Cloud Parameters Using Neural Networks , 2007 .

[48]  A. Cerdena,et al.  Neural Network based Retrieval of Cirrus Properties , 2006, 2006 IEEE International Symposium on Geoscience and Remote Sensing.

[49]  M. Derrien,et al.  MSG/SEVIRI cloud mask and type from SAFNWC , 2005 .

[50]  Andrew J. Heymsfield,et al.  Extinction‐ice water content‐effective radius algorithms for CALIPSO , 2005 .

[51]  William B. Rossow,et al.  Characterizing Tropical Cirrus Life Cycle, Evolution, and Interaction with Upper-Tropospheric Water Vapor Using Lagrangian Trajectory Analysis of Satellite Observations , 2004 .

[52]  W. Paul Menzel,et al.  The MODIS cloud products: algorithms and examples from Terra , 2003, IEEE Trans. Geosci. Remote. Sens..

[53]  Andrea Rossa,et al.  Tracking cloud patterns by METEOSAT rapid scan imagery in complex terrain , 2003 .

[54]  K. T. Kriebel,et al.  The cloud analysis tool APOLLO: Improvements and validations , 2003 .

[55]  V. S. Scott,et al.  Cloud physics lidar: instrument description and initial measurement results. , 2013, Applied optics.

[56]  E. O'connor,et al.  The CloudSat mission and the A-train: a new dimension of space-based observations of clouds and precipitation , 2002 .

[57]  Ping Yang,et al.  An algorithm using visible and 1.38-μm channels to retrieve cirrus cloud reflectances from aircraft and satellite data , 2002, IEEE Trans. Geosci. Remote. Sens..

[58]  W. Menzel,et al.  Improvement in thin cirrus retrievals using an emissivity-adjusted CO2 slicing algorithm , 2002 .

[59]  J. Schmetz,et al.  AN INTRODUCTION TO METEOSAT SECOND GENERATION (MSG) , 2002 .

[60]  J. van Leeuwen,et al.  Neural Networks: Tricks of the Trade , 2002, Lecture Notes in Computer Science.

[61]  M. Desbois,et al.  Monitoring the life cycle of cirrus clouds using Meteosat‐4 data during ICE‐1989 , 2001 .

[62]  William B. Rossow,et al.  Radiative Effects of Cloud-Type Variations , 2000 .

[63]  U. Schumann,et al.  Radiative forcing by contrails , 1999 .

[64]  Andreas Macke,et al.  Effect of crystal size spectrum and crystal shape on stratiform cirrus radiative forcing , 1999 .

[65]  W. Menzel,et al.  Discriminating clear sky from clouds with MODIS , 1998 .

[66]  Stefan Kinne,et al.  Tropical cirrus cloud radiative forcing: Sensitivity studies , 1994 .

[67]  M. Derrien,et al.  Automatic cloud detection applied to NOAA-11 /AVHRR imagery , 1993 .

[68]  Steven J. Nieman,et al.  A Comparison of Several Techniques to Assign Heights to Cloud Tracers , 1993 .

[69]  Q. Fu,et al.  Parameterization of the Radiative Properties of Cirrus Clouds , 1993 .

[70]  J. Schmetz,et al.  Operational Cloud-Motion Winds from Meteosat Infrared Images , 1993 .

[71]  M. King,et al.  Determination of the Optical Thickness and Effective Particle Radius of Clouds from Reflected Solar Radiation Measurements. Part II: Marine Stratocumulus Observations , 1991 .

[72]  Steven A. Ackerman,et al.  The 27–28 October 1986 FIRE IFO Cirrus Case Study: Spectral Properties of Cirrus Clouds in the 8–12 μm Window , 1990 .

[73]  M. King,et al.  Determination of the optical thickness and effective particle radius of clouds from reflected solar , 1990 .

[74]  Bernard Widrow,et al.  Improving the learning speed of 2-layer neural networks by choosing initial values of the adaptive weights , 1990, 1990 IJCNN International Joint Conference on Neural Networks.

[75]  W. Paul Menzel,et al.  Retrieval of Cloud Parameters from Satellite Sounder Data: A Simulation Study , 1989 .

[76]  Robert J. Curran,et al.  Thin cirrus clouds - Seasonal distribution over oceans deduced from Nimbus-4 IRIS , 1988 .

[77]  R. Saunders,et al.  An improved method for detecting clear sky and cloudy radiances from AVHRR data , 1988 .

[78]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[79]  Toshiro Inoue,et al.  On the Temperature and Effective Emissivity Determination of Semi-Transparent Cirrus Clouds by Bi-Spectral Measurements in the 10μm Window Region , 1985 .

[80]  William L. Smith,et al.  Improved Cloud Motion Wind Vector and Altitude Assignment Using VAS. , 1983 .

[81]  G. Szejwach.  Determination of semi-transparent cirrus cloud temperature from infrared radiances - Application to Meteosat , 1982 .

[82]  C. Bohren,et al.  An introduction to atmospheric radiation , 1981 .

[83]  William L. Smith,et al.  Comparison of Satellite-Deduced Cloud Heights with Indications from Radiosonde and Ground-Based Laser Measurements , 1978 .

[84]  William L. Smith,et al.  A REGRESSION METHOD FOR OBTAINING REAL-TIME TEMPERATURE AND GEOPOTENTIAL HEIGHT PROFILES FROM SATELLITE SPECTROMETER MEASUREMENTS AND ITS APPLICATION TO NIMBUS 3 “SIRS” OBSERVATIONS , 1970 .