Retrieval of cloud top properties from advanced geostationary satellite imager measurements based on machine learning algorithms

Abstract The cloud-top height (CTH) product derived from passive satellite instrument measurements is often used to make climate data records (CDR). CALIPSO (Cloud-Aerosol Lidar and Infrared Pathfinder Satellite Observations) provides CTH parameters with high accuracy, but with limited temporal-spatial resolution. Recently, the Advanced Himawari Imager (AHI) onboard Japanese Himawari-8/-9, provides high temporal (every 10 min) and high spatial (2 km at nadir) resolution measurements with 16 spectral bands. This paper reports on a study to derive the CTH from combined AHI and CALIPSO using advanced machine learning (ML) algorithms with better accuracy than that from the traditional physical (TRA) algorithms. We find significant CTH improvements (1.54–2.72 km for mean absolute error, MAE) from four different machine learning algorithms (original MAE from TRA method is about 3.24 km based on CALIPSO data validation), particularly in high and optically thin clouds. In addition, we also develop a joint algorithm to combine optimal machine learning and traditional physical (TRA) algorithms of CTH to further reduce MAE to 1.53 km and enhance the layered accuracy (CTH

[1]  H. Treut,et al.  THE CALIPSO MISSION: A Global 3D View of Aerosols and Clouds , 2010 .

[2]  Zhiqing Zhang,et al.  Introducing the New Generation of Chinese Geostationary Weather Satellites, Fengyun-4 , 2017 .

[3]  Tim Appelhans,et al.  Precipitation Estimates from MSG SEVIRI Daytime, Nighttime, and Twilight Data with Random Forests , 2014 .

[4]  Clive D Rodgers,et al.  Inverse Methods for Atmospheric Sounding: Theory and Practice , 2000 .

[5]  M. Baker,et al.  Cloud Microphysics and Climate , 1997 .

[6]  Tim Appelhans,et al.  Improving the accuracy of rainfall rates from optical satellite sensors with machine learning — A random forests-based approach applied to MSG SEVIRI , 2014 .

[7]  W. Paul Menzel,et al.  Variational Retrieval of Cloud Parameters from GOES Sounder Longwave Cloudy Radiance Measurements , 2001 .

[8]  G. Kattawar,et al.  Scattering and absorption property database for nonspherical ice particles in the near- through far-infrared spectral region. , 2005, Applied optics.

[9]  Lijuan Cao,et al.  Support vector machines experts for time series forecasting , 2003, Neurocomputing.

[10]  Jungho Im,et al.  ISPRS Journal of Photogrammetry and Remote Sensing , 2022 .

[11]  Min Min,et al.  On the influence of cloud fraction diurnal cycle and sub-grid cloud optical thickness variability on all-sky direct aerosol radiative forcing , 2014 .

[12]  Jun Li,et al.  Estimating Summertime Precipitation from Himawari-8 and Global Forecast System Based on Machine Learning , 2019, IEEE Transactions on Geoscience and Remote Sensing.

[13]  Ying Zhang,et al.  Extinction effects of atmospheric compositions on return signals of space-based lidar from numerical simulation , 2018 .

[14]  Alexander J. Smola,et al.  Support Vector Regression Machines , 1996, NIPS.

[15]  Andi Walther,et al.  A Naive Bayesian Cloud-Detection Scheme Derived fromCALIPSOand Applied within PATMOS-x , 2012 .

[16]  Masao Kanamitsu,et al.  Description of the NMC Global Data Assimilation and Forecast System , 1989 .

[17]  Lin Chen,et al.  Developing the science product algorithm testbed for Chinese next-generation geostationary meteorological satellites: Fengyun-4 series , 2017, Journal of Meteorological Research.

[18]  Kenneth Sassen,et al.  Classifying clouds around the globe with the CloudSat radar: 1‐year of results , 2008 .

[19]  Knut Stamnes,et al.  A new approach to retrieve cloud base height of marine boundary layer clouds , 2013 .

[20]  Markus Quante,et al.  A midlatitude cirrus cloud climatology from the facility for atmospheric remote sensing. Part V Cloud structural properties , 2007 .

[21]  N. Altman.  An Introduction to Kernel and Nearest-Neighbor Nonparametric Regression , 1992 .

[22]  Lixin Dong,et al.  A method for monitoring the on-orbit performance of a satellite sensor infrared window band using oceanic drifters , 2014 .

[23]  H. Woolf,et al.  Transmittance of atmospheric gases in the microwave region: a fast model. , 1988, Applied optics.

[24]  W. Paul Menzel,et al.  INTRODUCING THE NEXT-GENERATION ADVANCED BASELINE IMAGER ON GOES-R , 2005 .

[25]  Steven A. Ackerman,et al.  High-Spectral- and High-Temporal-Resolution Infrared Measurements from Geostationary Orbit , 2009 .

[26]  Danyu Qin,et al.  Local Severe Storm Tracking and Warning in Pre-Convection Stage from the New Generation Geostationary Weather Satellite Measurements , 2019, Remote. Sens..

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

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

[29]  James R. Campbell,et al.  Midlatitude cirrus cloud radiative forcing over China , 2010 .

[30]  W. Paul Menzel,et al.  MODIS Cloud-Top Property Refinements for Collection 6 , 2012 .

[31]  Jerome Riedi,et al.  Ice Cloud Properties From Himawari-8/AHI Next-Generation Geostationary Satellite: Capability of the AHI to Monitor the DC Cloud Generation Process , 2019, IEEE Transactions on Geoscience and Remote Sensing.

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

[33]  Chuanfeng Zhao,et al.  Long-term variation of cloud droplet number concentrations from space-based Lidar , 2018, Remote Sensing of Environment.

[34]  Jian Li,et al.  The Cloud Top Distribution and Diurnal Variation of Clouds Over East Asia: Preliminary Results From Advanced Himawari Imager , 2018 .

[35]  Danyu Qin,et al.  Refined Typhoon Geometric Center Derived From a High Spatiotemporal Resolution Geostationary Satellite Imaging System , 2019, IEEE Geoscience and Remote Sensing Letters.

[36]  Nina Håkansson,et al.  Neural network cloud top pressure and height for MODIS , 2018, Atmospheric Measurement Techniques.

[37]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[38]  W. Menzel,et al.  Comparison of AIRS, MODIS, CloudSat and CALIPSO cloud top height retrievals , 2007 .

[39]  C. Rodgers,et al.  Retrieval of atmospheric temperature and composition from remote measurements of thermal radiation , 1976 .

[40]  Jun Li,et al.  An efficient radiative transfer model for hyperspectral IR radiance simulation and applications under cloudy‐sky conditions , 2017 .

[41]  J. Friedman.  Stochastic gradient boosting , 2002 .

[42]  Bo Li,et al.  Intercomparisons of Cloud Mask Products Among Fengyun-4A, Himawari-8, and MODIS , 2019, IEEE Transactions on Geoscience and Remote Sensing.

[43]  David M. Winker,et al.  The CALIPSO Version 4 Automated Aerosol Classification and Lidar Ratio Selection Algorithm. , 2018, Atmospheric measurement techniques.

[44]  Kenneth Levenberg.  A METHOD FOR THE SOLUTION OF CERTAIN NON – LINEAR PROBLEMS IN LEAST SQUARES , 1944 .

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

[46]  Bryan A. Baum,et al.  Spectrally Consistent Scattering, Absorption, and Polarization Properties of Atmospheric Ice Crystals at Wavelengths from 0.2 to 100 um , 2013 .

[47]  D. Coomans,et al.  Alternative k-nearest neighbour rules in supervised pattern recognition : Part 1. k-Nearest neighbour classification by using alternative voting rules , 1982 .

[48]  Bryan A. Baum,et al.  Using CALIPSO to explore the sensitivity to cirrus height in the infrared observations from NPOESS/VIIRS and GOES‐R/ABI , 2010 .

[49]  R. Reynolds,et al.  The NCEP/NCAR 40-Year Reanalysis Project , 1996, Renewable Energy.

[50]  David M. Winker,et al.  Discriminating between clouds and aerosols in the CALIOP version 4.1 data products , 2018, Atmospheric Measurement Techniques.