A Neural Networks–Based Fusion Technique to Estimate Half-Hourly Rainfall Estimates at 0.1° Resolution from Satellite Passive Microwave and Infrared Data

Abstract The purpose of this paper is to evaluate a new operational procedure to produce half-hourly rainfall estimates at 0.1° spatial resolution. Rainfall is estimated using a neural networks (NN)–based approach utilizing passive microwave (PMW) and infrared satellite measurements. Several neural networks are tested, from multilayer perceptron to adaptative resonance theory architectures. The NN analytical selection process is explained. Half- hourly rain gauge data over Andalusia, Spain, are used for validation purposes. Several interpolation procedures are tested to transform point to areal measurements, including the maximum entropy estimation method. Rainfall estimations are also compared with Geostationary Operational Environmental Satellite precipitation index and histogram-matching results. Half-hourly rainfall estimates give ∼0.6 correlations with PMW data (∼0.2 with gauge), and average correlations of up to 0.7 and 0.6 are obtained for 0.5° and 0.1° monthly accumulated estimates, respectively.

[1]  Warren S. Sarle,et al.  Neural Networks and Statistical Models , 1994 .

[2]  J. Skilling,et al.  Maximum entropy image reconstruction: general algorithm , 1984 .

[3]  Dominikus Noll,et al.  Restoration of Degraded Images with Maximum Entropy , 1997, J. Glob. Optim..

[4]  R. Washington,et al.  A Simple Method to Retrieve 3-Hourly Estimates of Global Tropical and Subtropical Precipitation from International Satellite Cloud Climatology Program (ISCCP) D1 Data , 1999 .

[5]  J. Janowiak,et al.  A Real–Time Global Half–Hourly Pixel–Resolution Infrared Dataset and Its Applications , 2001 .

[6]  D. Kniveton,et al.  A statistical modelling approach to passive microwave rainfall retrieval , 1998 .

[7]  C. Duchon,et al.  Assessment of Rainfall Estimates Using a Standard Z-R Relationship and the Probability Matching Method Applied to Composite Radar Data in Central Florida , 1996 .

[8]  Ec Barrett,et al.  Satellite Identification of Rain Days over the Upper Nile River Basin Using an Optimum Infrared Rain/No-Rain Threshold Temperature Model , 1995 .

[9]  Yuh-Ming Lee,et al.  Estimation and simulation of lognormal random fields , 1997 .

[10]  P. Arkin,et al.  On the Relationship between Satellite-Observed Cloud Cover and Precipitation , 1981 .

[11]  S. Sorooshian,et al.  A Microwave Infrared Threshold Technique to Improve the GOES Precipitation Index , 1999 .

[12]  Shun-ichi Amari,et al.  Network information criterion-determining the number of hidden units for an artificial neural network model , 1994, IEEE Trans. Neural Networks.

[13]  E. Jaynes.  Information Theory and Statistical Mechanics , 1957 .

[14]  Rodney W. Johnson,et al.  Axiomatic derivation of the principle of maximum entropy and the principle of minimum cross-entropy , 1980, IEEE Trans. Inf. Theory.

[15]  Chris Kidd,et al.  On rainfall retrieval using polarization-corrected temperatures , 1998 .

[16]  R. Brown,et al.  Delineation of Precipitation Areas Using Meteosat Infrared and Visible Data in the Region of the United Kingdom , 1993 .

[17]  Stephen Grossberg,et al.  Invariant recognition of cluttered scenes by a self-organizing ART architecture: CORT-X boundary segmentation , 1989, Neural Networks.

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

[19]  Kazumi Murata,et al.  Maximum entropy image reconstruction from projections , 1981 .

[20]  Jose L. Casanova,et al.  An algorithm for the fusion of images based on Jaynes' maximum entropy method , 2002 .

[21]  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 .

[22]  Sang Joon Kim,et al.  A Mathematical Theory of Communication , 2006 .

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

[24]  Christian D. Kummerow,et al.  A method for combining passive microwave and infrared rainfall observations , 1995 .

[25]  Issam Dagher,et al.  An ordering algorithm for pattern presentation in fuzzy ARTMAP that tends to improve generalization performance , 1999, IEEE Trans. Neural Networks.

[26]  Johannes Schmetz,et al.  Precipitation estimations from geostationary orbit and prospects for METEOSAT Second Generation , 2001 .

[27]  Alexander Linden,et al.  Inversion of neural networks by gradient descent , 1990, Parallel Comput..

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

[29]  Kuolin Hsu,et al.  Estimation of physical variables from multichannel remotely sensed imagery using a neural network: Application to rainfall estimation , 1999 .

[30]  Li Li,et al.  Microwave radiometric technique to retrieve vapor, liquid and ice. II. Joint studies of radiometer and radar in winter clouds , 1997, IEEE Trans. Geosci. Remote. Sens..

[31]  Stephen J. Wernecke,et al.  Maximum Entropy Image Reconstruction , 1977, IEEE Transactions on Computers.

[32]  M. Todd,et al.  A Combined Satellite Infrared and Passive Microwave Technique for Estimation of Small-Scale Rainfall , 1999 .

[33]  Frank S. Marzano,et al.  Results of WetNet PIP-2 Project , 1998 .

[34]  S. Grossberg.  Some Networks That Can Learn, Remember, and Reproduce any Number of Complicated Space-Time Patterns, I , 1969 .

[35]  Robert J. Marks,et al.  Inversion of feedforward neural networks: algorithms and applications , 1999, Proc. IEEE.

[36]  Kurt Hornik,et al.  Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

[37]  Frank S. Marzano,et al.  Statistical integration of satellite passive microwave and infrared data for high-temporal sampling retrieval of rainfall , 2002, IEEE International Geoscience and Remote Sensing Symposium.

[38]  A. Herman,et al.  Objectively determined 10-day African rainfall estimates created for famine early warning systems , 1997 .

[39]  Gail A. Carpenter,et al.  ART neural networks for remote sensing: vegetation classification from Landsat TM and terrain data , 1997, IEEE Trans. Geosci. Remote. Sens..

[40]  F. Marzano,et al.  Results of WetNet PIP2 Project , 1998 .

[41]  Chris Kidd,et al.  Rainfall Estimation from a Combination of TRMM Precipitation Radar and GOES Multispectral Satellite Imagery through the Use of an Artificial Neural Network , 2000 .

[42]  Li Li,et al.  Microwave radiometric technique to retrieve vapor, liquid and ice. I. Development of a neural network-based inversion method , 1997, IEEE Trans. Geosci. Remote. Sens..

[43]  Yuh-Ming Lee.  A Methodological Study of the Application of the Maximum Entropy Estimator to Spatial Interpolation , 1998 .

[44]  Eric A. Smith,et al.  Bayesian estimation of precipitating cloud parameters from combined measurements of spaceborne microwave radiometer and radar , 1999, IEEE Trans. Geosci. Remote. Sens..

[45]  George Cybenko,et al.  Approximation by superpositions of a sigmoidal function , 1992, Math. Control. Signals Syst..

[46]  J. N. Kapur,et al.  Entropy optimization principles with applications , 1992 .

[47]  Ralph Ferraro,et al.  Special sensor microwave imager derived global rainfall estimates for climatological applications , 1997 .

[48]  A. Linden,et al.  Inversion of multilayer nets , 1989, International 1989 Joint Conference on Neural Networks.

[49]  F. Joseph Turk,et al.  Validation and applications of a realtime global precipitation analysis , 2002, IEEE International Geoscience and Remote Sensing Symposium.

[50]  Murugesu Sivapalan,et al.  Transformation of point rainfall to areal rainfall: Intensity-duration-frequency curves , 1998 .

[51]  George Christakos,et al.  Some Applications of the Bayesian, Maximum-Entropy Concept in Geostatistics , 1991 .

[52]  Ulrich Anders,et al.  Model selection in neural networks , 1999, Neural Networks.