Satellite-Based Rainfall Retrieval: From Generalized Linear Models to Artificial Neural Networks

In this study, we develop and compare satellite rainfall retrievals based on generalized linear models and artificial neural networks. Both approaches are used in classification mode in a first step to identify the precipitating areas (precipitation detection) and in regression mode in a second step to estimate the rainfall intensity at the ground (rain rate). The input predictors are geostationary satellite infrared (IR) brightness temperatures and Satellite Application Facility (SAF) nowcasting products which consist of cloud properties, such as cloud top height and cloud type. Additionally, a set of auxiliary location-describing input variables is employed. The output predictand is the ground-based instantaneous rain rate provided by the European-scale radar composite OPERA, that was additionally quality-controlled. We compare our results to a precipitation product which uses a single infrared (IR) channel for the rainfall retrieval. Specifically, we choose the operational PR-OBS-3 hydrology SAF product as a representative example for this type of approach. With generalized linear models, we show that we are able to substantially improve in terms of hits by considering more IR channels and cloud property predictors. Furthermore, we demonstrate the added value of using artificial neural networks to further improve prediction skill by additionally reducing false alarms. In the rain rate estimation, the indirect relationship between surface rain rates and the cloud properties measurable with geostationary satellites limit the skill of all models, which leads to smooth predictions close to the mean rainfall intensity. Probability matching is explored as a tool to recover higher order statistics to obtain a more realistic rain rate distribution.

[1]  R. Scofield,et al.  The Operational GOES Infrared Rainfall Estimation Technique , 1998 .

[2]  Thomas Nauss,et al.  Revealing the potential of spectral and textural predictor variables in a neural network-based rainfall retrieval technique , 2017 .

[3]  B. N. Meisner,et al.  The Relationship between Large-Scale Convective Rainfall and Cold Cloud over the Western Hemisphere during 1982-84 , 1987 .

[4]  Harri Hohti,et al.  Operational Measurement of Precipitation in Cold Climates , 2004 .

[5]  E. D. Coning,et al.  South African Weather Service operational satellite based precipitation estimation technique: applications and improvements , 2010 .

[6]  Jörg Bendix,et al.  Discriminating raining from non-raining clouds at mid-latitudes using meteosat second generation daytime data , 2007 .

[7]  Y. Hong,et al.  The TRMM Multisatellite Precipitation Analysis (TMPA): Quasi-Global, Multiyear, Combined-Sensor Precipitation Estimates at Fine Scales , 2007 .

[8]  M. Kitchen,et al.  Representativeness errors in comparisons between radar and gauge measurements of rainfall , 1992 .

[9]  John Kochendorfer,et al.  Analysis of single-Alter-shielded and unshielded measurements of mixed and solid precipitation from WMO-SPICE , 2017 .

[10]  J. Janowiak,et al.  COMPARISON OF NEAR-REAL-TIME PRECIPITATION ESTIMATES FROM SATELLITE OBSERVATIONS AND NUMERICAL MODELS , 2007 .

[11]  Silas C. Michaelides,et al.  Range adjustment for ground-based radar, derived with the spaceborne TRMM precipitation radar , 2006, IEEE Transactions on Geoscience and Remote Sensing.

[12]  Timothy D. Crum,et al.  The WSR-88D and the WSR-88D Operational Support Facility , 1993 .

[13]  Jörg Bendix,et al.  Discriminating raining from non‐raining cloud areas at mid‐latitudes using meteosat second generation SEVIRI night‐time data , 2008 .

[14]  Boris Sevruk,et al.  Estimation of Wind-Induced Error of Rainfall Gauge Measurements Using a Numerical Simulation , 1999 .

[15]  Giovanni Emilio Perona,et al.  Optimizing quantitative precipitation estimates using a noncoherent and a coherent radar operating on the same area , 2000 .

[16]  Ulrich Hamann,et al.  PyTroll An Open-Source, Community-Driven Python Framework to Process Earth Observation Satellite Data , 2018 .

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

[18]  A. Gruber,et al.  GOES Multispectral Rainfall Algorithm (GMSRA) , 2001 .

[19]  J. Gourley,et al.  An Exploratory Multisensor Technique for Quantitative Estimation of Stratiform Rainfall , 2002 .

[20]  Damaris Zurell,et al.  Collinearity: a review of methods to deal with it and a simulation study evaluating their performance , 2013 .

[21]  Giulia Panegrossi,et al.  Precipitation products from the hydrology SAF , 2013 .

[22]  Daniel S. Wilks,et al.  Empirical Distributions and Exploratory Data Analysis , 2011 .

[23]  Laurent Delobbe,et al.  Evaluation of radar-gauge merging methods for quantitative precipitation estimates , 2009 .

[24]  K. Okamoto,et al.  Rain profiling algorithm for the TRMM precipitation radar , 1997, IGARSS'97. 1997 IEEE International Geoscience and Remote Sensing Symposium Proceedings. Remote Sensing - A Scientific Vision for Sustainable Development.

[25]  Tanvir Islam,et al.  Non-parametric rain/no rain screening method for satellite-borne passive microwave radiometers at 19–85 GHz channels with the Random Forests algorithm , 2014 .

[26]  Kuolin Hsu,et al.  Intercomparison of High-Resolution Precipitation Products over Northwest Europe , 2012 .

[27]  Frank S. Marzano,et al.  A Neural Networks–Based Fusion Technique to Estimate Half-Hourly Rainfall Estimates at 0.1° Resolution from Satellite Passive Microwave and Infrared Data , 2004 .

[28]  Chris Kidd,et al.  Global Precipitation Measurement , 2008 .

[29]  R. Scofield,et al.  Status and Outlook of Operational Satellite Precipitation Algorithms for Extreme-Precipitation Events , 2003 .

[30]  V. Kousky,et al.  Assessing objective techniques for gauge‐based analyses of global daily precipitation , 2008 .

[31]  A. Ihler,et al.  Precipitation Identification with Bispectral Satellite Information Using Deep Learning Approaches , 2017 .

[32]  Robert F. Adler,et al.  Estimation of Monthly Rainfall over Japan and Surrounding Waters from a Combination of Low-Orbit Microwave and Geosynchronous IR Data , 1993 .

[33]  J. Janowiak,et al.  CMORPH: A Method that Produces Global Precipitation Estimates from Passive Microwave and Infrared Data at High Spatial and Temporal Resolution , 2004 .

[34]  Estelle de Coning,et al.  Optimizing Satellite-Based Precipitation Estimation for Nowcasting of Rainfall and Flash Flood Events over the South African Domain , 2013, Remote. Sens..

[35]  J. McGinley,et al.  Improving QPE and Very Short Term QPF: An Initiative for a Community-Wide Integrated Approach , 2007 .

[36]  Christian Onof,et al.  A Comparative Analysis of TRMM-Rain Gauge Data Merging Techniques at the Daily Time Scale for Distributed Rainfall-Runoff Modeling Applications , 2015 .

[37]  Witold F. Krajewski,et al.  Review of the Different Sources of Uncertainty in Single Polarization Radar-Based Estimates of Rainfall , 2010 .

[38]  Urs Germann,et al.  Operational Measurement of Precipitation in Mountainous Terrain , 2004 .

[39]  Elena Saltikoff,et al.  The Operational Weather Radar Network in Europe , 2014 .

[40]  Robin J. Hogan,et al.  Deterministic Forecasts of Binary Events , 2012 .

[41]  Y. Hong,et al.  Precipitation Estimation from Remotely Sensed Imagery Using an Artificial Neural Network Cloud Classification System , 2004 .

[42]  Jörg Bendix,et al.  Rainfall-Rate Assignment Using MSG SEVIRI Data—A Promising Approach to Spaceborne Rainfall-Rate Retrieval for Midlatitudes , 2010 .

[43]  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 .

[44]  Witold F. Krajewski,et al.  Radar for hydrology: unfulfilled promise or unrecognized potential? , 2013 .

[45]  A. Hou,et al.  The Global Precipitation Measurement Mission , 2014 .

[46]  A. Gruber,et al.  Results from the GPCP Algorithm Intercomparison Programme , 1996 .

[47]  Sabine Chamoun,et al.  Nonstationarity in Intermittent Rainfall: The “Dry Drift” , 2013 .

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

[49]  V. Levizzani,et al.  Status of satellite precipitation retrievals , 2009 .

[50]  Tim Appelhans,et al.  Comparison of four machine learning algorithms for their applicability in satellite-based optical rainfall retrievals , 2015 .

[51]  Pierre-Emmanuel Kirstetter,et al.  A new methodology for rain identification from passive microwave data in the Tropics using neural networks , 2013 .

[52]  U. Schneider,et al.  Global gridded precipitation over land: a description of the new GPCC First Guess Daily product , 2013 .

[53]  J. Janowiak,et al.  The Version 2 Global Precipitation Climatology Project (GPCP) Monthly Precipitation Analysis (1979-Present) , 2003 .

[54]  Jian Zhang,et al.  Radar-Based Quantitative Precipitation Estimation for the Cool Season in Complex Terrain: Case Studies from the NOAA Hydrometeorology Testbed , 2012 .

[55]  C. Frei,et al.  The climate of daily precipitation in the Alps: development and analysis of a high‐resolution grid dataset from pan‐Alpine rain‐gauge data , 2014 .

[56]  D. S. Wilks,et al.  Chapter 8 - Forecast Verification , 2011 .

[57]  F. Pappenberger,et al.  Global-scale evaluation of 22 precipitation datasets using gauge observations and hydrological modeling , 2017 .

[58]  U. Germann,et al.  Real‐time radar–rain‐gauge merging using spatio‐temporal co‐kriging with external drift in the alpine terrain of Switzerland , 2014 .

[59]  Kuolin Hsu,et al.  Evaluating the Utility of Multispectral Information in Delineating the Areal Extent of Precipitation , 2009 .

[60]  Ziad S. Haddad,et al.  The TRMM 'Day-1' Radar/Radiometer Combined Rain-Profiling Algorithm , 1997 .

[61]  B. J. Conway,et al.  Delineation of precipitation areas from MODIS visible and infrared imagery with artificial neural networks , 2005 .

[62]  R. A. Roebeling,et al.  SEVIRI rainfall retrieval and validation using weather radar observations , 2009 .

[63]  Emmanouil N. Anagnostou,et al.  Overview of Overland Satellite Rainfall Estimation for Hydro-Meteorological Applications , 2004 .

[64]  S. Sorooshian,et al.  Evaluation of PERSIANN system satellite-based estimates of tropical rainfall , 2000 .

[65]  R. Moore,et al.  Rainfall and sampling uncertainties: A rain gauge perspective , 2008 .

[66]  Kuolin Hsu,et al.  Neural networks in satellite rainfall estimation , 2004 .