Rainfall Intensity Classification Method Based on Textural and Spectral Parameters from MSG-SEVIRI

Yacine Mohia(1*), Soltane Ameur(2), Mourad Lazri(3), Jean Michel Brucker(4)

(1) Laboratory for Analysis and Modeling Random Phenomena (LAMPA), University of Tizi Ouzou, 15000, Tizi Ouzou, Algeria
(2) Laboratory for Analysis and Modeling Random Phenomena (LAMPA), University of Tizi Ouzou, 15000, Tizi Ouzou, Algeria
(3) Laboratory for Analysis and Modeling Random Phenomena (LAMPA), University of Tizi Ouzou, 15000, Tizi Ouzou, Algeria
(4) School of engineers (EPMI), EPMI - 13 Boulevard de l'Hautil 95092, Cergy Pontoise, Cedex, Paris, France
(*) Corresponding author


DOI's assignment:
the author of the article can submit here a request for assignment of a DOI number to this resource!
Cost of the service: euros 10,00 (for a DOI)

Abstract


In this paper we propose the rainfall intensity classification algorithm .The study is carried out over north of Algeria. The developed rain intensities classification technique (RICT) is based on the artificial neural multilayer perceptron network (MLP). The (MLP) model is created with three layers (input, hidden, and output) that consist of 15 input neurons, which as ten spectral features that were calculated from MSG (Meteosat Second Generation satellite) thermal infrared brilliance temperature (BT) and brilliance temperature difference (BTD) and as five textural features, and 6 output neurons in the output layer that represent the 6 rain intensities classes: very high, moderate to high, moderate, light to moderate, light and no rain. The precipitation process areas and the rainfall intensity subareas classified by the proposed technique are validated against groundbased radar data. The rainfall rates used in the training set are derived from Setif radar measurements (Algeria). The results obtained after applying this method for the north of Algeria zone show the neural network performs very well and indicate an encouraging performance of the new algorithm concerning rain area classification using MSG SEVIRI. We found that the introduction of textural parameters as additional information works in improving the classification of different rainfall intensities pixels in the MSG–SEVIRI imagery compared to the techniques based only on spectral information.


Copyright © 2014 Praise Worthy Prize - All rights reserved.

Keywords


Artificial Neural Network; Convective and Stratiform Cloud; Image Classification; Radar Data; Rainfall Intensities; Satellite Image; Spectral and Textural Features

Full Text:

PDF


References


Fritz S, Laszlo I : Detection of water vapor in the stratosphere over very high clouds in the tropics. J Geophys Res 98 D12):22959–22967, 1993.

Krebs W, Mannstein H, Bugliaro L, Mayer B: A new day and night time meteosat second generation cirrus detection algorithm mecida. J Atmospheric Chemistry and Physics 7:10933–10969, 2007.

Ameur Z, Ameur S, Adane A, Sauvageot H, Bara K : Cloud classification using the textural features of Meteosat images. Int J Remote Sens 25:4491–4503, 2004.

Anagnostou EN, Kummerow C : Stratiform and convective classification of rainfall using SSM/I 85-GHz brightness temperature observations. J Atmos Ocean Techn 14:570–575,1997.

Chen DW, Sengupta SK, Welch RM : Cloud field classification based upon high spatial resolution textural features. Part 2. Simplified vector approaches. J Geophys Res 94:14749–14765, 1989.

Feidas H, Giannakos A : Classifying convective and stratiform rain using multispectral infrared Meteosat Second Generation satellite data. Theor. Appl. Climatol. DOI 10.1007/s00704-011-0557-y, 2011.

Adler, R. F. & Negri, A. J. : A satellite technique to estimate tropical convective and stratiform rainfall. - Journal of Applied Meteorology, 27: 30–51,1988.

Ebert EE, Manton MJ : Performance of satellite rainfall estimation algorithms during TOGA COARE. J Atmos Sci 55:1538–1557, 1998.

Feidas H, Kokolatos G, Negri A, Manyin M, Chrysoulakis N, Kamarianakis, Y : Validation of an infrared-based satellite algorithm to estimate accumulated rainfall over the Mediterranean basin, Theor. Appl. Climatol. DOI 10.1007/s00704-007-0360-y, 2008.

Hsu K, Gao X, Sorooshian S, Gupta HV: Precipitation estimation from remotely sensed imagery using an artificial neura network. J Appl Meteor 36:1176–1190, 1997.

Lazri M, Ameur S, Mohia Y: Instantaneous rainfall estimation using neural network from multispectral observations of SEVIRI radiometer and its application in estimation of daily and monthly rainfall. Advances in Space Research, 53(1), 138-155, 2014.

Aminou, D. M. A. : MSG’s SEVIRI instrument. - ESA Bulletin,111: 15–17,2002.

Schmetz, J, Pili P, Tjemkes S, Just D, Kerkmann J, Rota S and Ratier A: An introduction to Meteosat Second Generation(MSG). - Bulletin of the American Meteorological Society, 83: 977–992,2002.

Adler, R. F. & Mack, R. A.: Thunderstorm cloud heightrainfall rate relations for use with satellite rainfall estimation techniques. - Journal of Climate and Applied Meteorology, 23: 280 –296, 1984.

Nauss T and Kokhanovsky A.A: Discriminating raining from non-raining clouds at mid-latitudes using multispectral satellite data. -Atmospheric Chemistry and Physics, 6: 5031–5036, 2006.

Nauss T and Kokhanovsky A.A: Assignment of rainfall confidence values using multispectral satellite data at mid-latitudes:first results. - Advances in Geosciences, 10: 99–102, 2007.

Thies B, Nauss T and Bendix J : Discriminating raining from non-raining cloud areas at mid-latitudes using Meteosat Second Generation SEVIRI night-time data. - Meteorological Applications, DOI: 10.1002/met.56, 2008.

Thies B, Nauss Τ, Bendix J: Discriminating raining from nonraining cloud areas at mid-latitudes using meteosat second generation SEVIRI night-time data. Meteorol Appl 15:219–230, 2008.

Tian B, Shaikh MA, Mahmood RA-S, Vonder Haar TH, Reinke DL: A study of cloud classification with neural networks using spectral and textural features. IEEE Transactions on Neural Networks 10(1):138–151, 1999.

Houze RL: Stratiform precipitation in regions of convection: a meteorological paradox. Bull Amer Meteor Soc 78:2179–2196, 1997.

Levizzani V, Schmetz J, Lutz HJ, Kerkmann J, Alberoni PP, Cervino M: Precipitation estimations from geostationary orbit and prospects for Meteosat Second Generation. Meteorol Appl 8:23–41, 2001.

Levizzani V: Satellite rainfall estimates: new perspectives formeteorology and climate from the EURAINSAT project. Ann Geophys 46(2):363–372, 2003.

Hong Y, Kummerow CD, Olson WS: Separation of convective and stratiform precipitation using microwave brightness temperature. J Appl Meteor 38:1195–1213, 1999.

Laviola S, Levizzani V: The 183-WSL fast rain rate retrieval algorithm. Part I. Retrieval design. Atmos Res 99(3-4):443–461, 2001.

Inoue T: An instantaneous delineation of convective rainfall areas using split window data of NOAA-7 AVHRR. J Meteor Soc Japan 65:469–481, 1987.

Arkin PA, Meisner BN : The relationship between large-scale convective rainfall and cold cloud over the western hemisphere during 1982–84. Mon Wea Rev 115:51–74, 1987.

Simpson J, Adler RF, North G: A proposed Tropical Rainfall Measurement Mission (TRMM) satellite. Bull Am Meteorol Soc 69:278–295, 1998.

Shenk WE, Holub RJ, Neff RA : A multispectral cloud type identification method using Nimbus-3 MRIR measurements. MonWea Rev 104:284–291, 1976.

Reynolds DW, Vonder Haar TH: A bispectral method of cloud parameter determination. Mon Wea Rev 105:446–457, 1977.

Rossow WB, Schiffer RA: ISCCP cloud data products. Bull Amer Meteor Soc 72:2–20, 1991.

Kaur R, Ganju A: Cloud classification in NOAA AVHRR imageries using spectral and textural features. J Indian Soc Remote Sens 36:167–174, 2008.

Thies B, Nauss T and Bendix J: Discriminating raining from non-raining cloud areas at mid-latitudes using Meteosat Second Generation SEVIRI day-time data. - Atmospheric Chemistry and Physics: 8, 1-9, 2008.

Feidas H, Giannakos A : Classifying convective and stratiform rain using multispectral infrared Meteosat Second Generation satellite data. Theor Appl Climatol 108(3):613–630, 2012.

Hong Y, Hsu K, Sorooshian S, Gao X : Precipitation estimation from remotely sensed imagery using an artificial neural network cloud classification system. J Appl Meteor 43:1834–1852, 2004.

Thies B, Nauss Τ, Bendix J: Precipitation process and rainfall intensity differentiation using Meteosat second generation spinning enhanced visible and infrared imager data. Geophys Res 113: D23206. DOI: 10.1029/2008JD010464, 2008.

Shou Y, Li S, Shou S, Zhao Z: Application of a cloud-texture analysis scheme to the cloud cluster structure recognition and rainfall estimation in a mesoscale rainstorm process. Adv Atmos Sc 23(5):767–774, 2006.

Lamei N, Hutchison KD, Crawford MM : Cloud-type discrimination via multispectral textural analysis. Opt Eng 33:1303–1313, 1994.

Reudenbach C, Nauss T and Bendix J : Retrieving precipitation with GOES, Meteosat and Terra/MSG at the tropics and mid-latitudes. In: Levizzani, V., P. Bauer, and F. J. TURK (Ed.): Measuring precipitation form space. - Advances in global change research, 28.Springer: Netherlands, 2007.

Bendix, J,Reudenbach J.C and Rollenbeck R: The Marburg Satellite Station. Proceedings of the 2002 Meteorological Satellite Users’ Conference. Dublin, EUMETSAT: 139–146, 2003.

EUMETSAT: MSG CHANNELS Interpretation Guide: Weather, Surface conditions and Atmospheric constituents, http://oiswww.eumetsat.org, 2006.

EUMETSAT: Applications of Meteosat Second Generation-conversion from counts to radiances and from radiances to rightness temperatures and reflectance. http://oiswww.eumetsat.org/WEBOPS/msg_interpretation/index.html, 2004, 2008.

Feidas H: Study of a mesoscale convective complex over the eastern Mediterranean basin with Meteosat data. Eumetsat Meteorological Satellite Conference, Oslo, Norway, 5 - 9 September, 2011.

Feidas H, Giannakos A : Identifying precipitating clouds in Greece using multispectral infrared Meteosat Second Generation satellite data. Theor Appl Climatol. DOI:10.1007/s00704-010-0316-5, 2010.

Inoue T: On the temperature and effective emissivity determination of semi-transparent cirrus clouds by bi-spectral measurements in the 10-mm window region. J Meteor Soc Japan 63:88–99, 1985.

Inoue T: A cloud type classification with NOAA-7 splitwindow measurements. J Geophys Res 92:3991–4000, 1987.

Inoue T, Wu X, Bessho K: Life cycle of convective activity in terms of cloud type observed by split window. 11th Conference on Satellite Meteorology and Oceanography, Madison, WI, USA, 2001.

Mecikalski JR, Bedka KM, Mackenzie WM, Simon JP: Convective Initiation and Lightning Prediction: The potential of the MTG-FC imagery mission, Atmospheric Science Department, University of Alabama in Huntsville, Cooperative Institute for Meteorological Satellite Studies University of Wisconsin-Madison Meteorological Satellite Conference, Amsterdam, TheNetherlands, 24–28, 2007.

Mecikalski JR, Bedka KM: Forecasting convective initiation by monitoring the evolution of moving cumulus in daytime GOES imagery. Mon Wea Rev 134:49–68, 2006.

Strabala KI, Ackerman SA, Menzel WP: Cloud properties inferred from 8–12 micron data. J Appl Meteor 33(2):212–229, 1994.

Kwon E, Sohn B, Schmetz J, Wats P: Intercomparison of height assignment methods for opaque clouds over the tropics. J Atmos Sci 46(1):11–19, 2010.

Lutz H-J, Inoue T, Schmetz J: NOTES AND CORRESPONDENCE Comparison of a split-window and a multi-spectral cloud classification for MODIS observations. J Meteor Society of Japan 81(3):623–631, 2003.

Schmetz J, Tjemkes S,Gube M and Van De Berg L : Monitoring deep convection and convective overshooting with Meteosat. - Advances in Space Research, 19: 433-441, 1997.

Narasimha Rao P.V, Sesha Sai M.V.R, Sreenivas K.,Krishna Rao M.V, Rao B.R.M ,Dwivendi R.S and Venkataratnam I.,”Textural analyses of IRS-ID panchromatic data for land cover classification,”International Journal of Remote Sensing. Vol. 23 , N°. 17?PP. 3327-3345 , 2002.

Press W.H, Flannery B.P, Teukolsky S.A, Vetterling W.T, Numerical Recipes, The Art of Scientific Computing, Cambridge University Press, Cambridge, 1987.

Haralick R.M ,Shanmungan .K, and Dinstein .I : Textural features for image classification. IEE Transactions on Systems, Man, and Cybernetics, 3(6):610-621, November 1973.

Rosin J. Barba D. and Raboisson S: Comparaison between cooccurrence matrices, local histogram for texture characterization and curvilinear integration. In SPIE,Vol 596 ,page 98-11,1985.

Haralick R.M, Shanmugam K and Dinstein I : "Textural features for image classification" ; IEEE Transactions on Systems, Man and Cybernetics ; vol. 3 ; n° 6 ; 610-621 pp, 1973.

Nauss T and Kokhanovsky A.A: Discriminating raining from non-raining clouds at mid-latitudes using multispectral satellite data. -Atmospheric Chemistry and Physics, 6: 5031–5036, 2006.

T. Boudghene Stambouli, A. Ouamri, M. Keche, Textured Images Classification Using Nearest Feature Line Method Added with Kurtosis and Skewness, (2008) International Review on Computers and Software (IRECOS), 3. (6), pp. 593 - 596.

Weszka J.S, Dyer C.R, Rosenfeld A; “A Comparative Studyof Texture Measures for Terrain Classification”, IEEE Trans.on Systems, Man. & Cybernetics, Vol. SMC-6, April 1976.

Laws K.I., “Rapid Texture Identification”, SPIE, Vol.238, pp. 376-380, 1980.

Wu Chung-Ming, Chen Yung-Chang: “Statistical FeatureMatrix for Texture Analysis”, CVGIP: Graphical Models and Image Processing, Vol. 54, No 5, pp. 407-419, Sept. 1992.

Cocquerez J.P. et Philipp S. ; "Analyse d'images : filtrage et segmentation" ; Masson, Paris, 1995.

Mandelbrot B.B: The Fractal Geometry of Nature , SanFrancisco, CA, Freeman, 1982.

Tremblay A: The stratiform and convective components of surface precipitation. J Atmos Sci 62:1513–1528, 2005.

Baraldi A, Parmiggiani F : An Investigation of the textural characteristics associated with gray level cooccurence matrix statistical parameters. IEEE Trans Geosci Remote Sens 33:293–304, 1999.

Sali E and Wolfson H: "Texture classification in aerial photographs and satellite data", International Journal of Remote Sensing, vol. 13, n° 18 ; 3395-3408 pp, 1992.

Kayitakire F, Giot P and Defourny P : "Discrimination automatique de peuplements forestiers à partir d’orthophotos numériques couleur : un cas d’étude en Belgique" ; Journal canadien de télédétection ; vol. 28 ; n° 5 ; 629-640 pp, 2002.

Rosenberger C : "Mise en oeuvre d’un système adaptatif de segmentation d’images", Thèse de l’université de Rennes 1, 1999.

Curic .M, and Janc .D, “Analysis of predicted and observed accumulated convective precipitation in the area with frequent split storms”, Hydrol. Earth Syst. Sci., 2011, 15, 3651–3658.

Lazri M, Ameur S, Brucker J. M, Testud J, Hamadache B, Hameg S, Ouallouche F and Mohia Y: Identification of raining clouds using a method based on optical and microphysical cloud properties from Meteosat second generation daytime and nighttime data, Appl Water Sci, DOI 10.1007/s13201-013-0079-0, 2013.

Lazri M, Ameur Z, Ameur S, Mohia Y, Brucker J M, Testud J: Rainfall estimation over a Mediterranean region using a method based on various spectral parameters of SEVIRIMSG. J. Adv. Space Res. http://dx.doi.org/10.1016/j.asr.2013.07.036 , 2013.

Lazri M, Ameur S, Brucker J M, Testud J, Hamadache B, Hameg S, Ouallouche F, Mohia Y : Identification of raining clouds using a method based on optical and microphysical cloud properties from Meteosat second generation daytime and nighttime data, Appl Water Sci, DOI 10.1007/s13201-013-0079-0, 2013.

Freeman J.A., Skapura D.M.: Neural Networks: Algorithms, Applications, and Programming Techniques. Addison-Wesley, 401 pp, 1991.

Skapura D.M: "Building Neural Networks", ACM Press, Addision-Wesly Publishing Company, pp. 31-32, 1995

Hsu K, Gupta HV, Sorooshian S: Artificial neural network modelling of the rainfall runoff process. Water Resour Res 31 (10):2517–2530.

Galushkin AI : Neural networks theory. Springer, Berlin, pp 368–375, ISBN 978-3-540-48124-9, 1997.

Zahran, B.M., Classification of brain tumor using neural network, (2014) International Review on Computers and Software (IRECOS), 9 (4), pp. 673-67.

Singh, A.K., Shukla, V.P., Biradar, S.R., Tiwari, S., Curvelet based multiclass image classification under complex background using neural network, (2014) International Review on Computers and Software (IRECOS), 9 (3), pp. 577-584.


Refbacks

  • There are currently no refbacks.



Please send any question about this web site to info@praiseworthyprize.com
Copyright © 2005-2019 Praise Worthy Prize