Skip to main content

Advertisement

SpringerLink
Log in

Automatic system for radar echoes filtering based on textural features and artificial intelligence

  • Original Paper
  • Published:
Meteorology and Atmospheric Physics Aims and scope Submit manuscript

Abstract

Among the very popular Artificial Intelligence (AI) techniques, Artificial Neural Network (ANN) and Support Vector Machine (SVM) have been retained to process Ground Echoes (GE) on meteorological radar images taken from Setif (Algeria) and Bordeaux (France) with different climates and topologies. To achieve this task, AI techniques were associated with textural approaches. We used Gray Level Co-occurrence Matrix (GLCM) and Completed Local Binary Pattern (CLBP); both methods were largely used in image analysis. The obtained results show the efficiency of texture to preserve precipitations forecast on both sites with the accuracy of 98% on Bordeaux and 95% on Setif despite the AI technique used. 98% of GE are suppressed with SVM, this rate is outperforming ANN skills. CLBP approach associated to SVM eliminates 98% of GE and preserves precipitations forecast on Bordeaux site better than on Setif’s, while it exhibits lower accuracy with ANN. SVM classifier is well adapted to the proposed application since the average filtering rate is 95–98% with texture and 92–93% with CLBP. These approaches allow removing Anomalous Propagations (APs) too with a better accuracy of 97.15% with texture and SVM. In fact, textural features associated to AI techniques are an efficient tool for incoherent radars to surpass spurious echoes.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11

Similar content being viewed by others

References

  • Azimi-Sadjadi MR, Liou RJ (1992) Fast learning process of multilayer neural networks using recursive least squares method. IEEE Trans Signal Process 40:446–450. doi:10.1109/78.124956

    Article  Google Scholar 

  • Bakhtiarizadeh MR, Moradi-Shahrbabak M, Ebrahimi M, Ebrahimie E (2014) Neural network and SVM classifiers accurately predict lipid binding proteins, irrespective of sequence homology. J Theor Biol 356:213–222. doi:10.1016/j.jtbi.2014.04.040

    Article  Google Scholar 

  • Bishop CM (1995) Neural networks for pattern recognition. Clarendon Press

  • Boutellaa E, Bengherabi M, Boulkenafet Z, Harizi F, Hadid A (2013) Face verification using local binary patterns generic histogram adaptation and Chi square based decision. In: 2013 4th European Workshop on Visual Information Processing (EUVIP). Presented at the 2013 4th European Workshop on Visual Information Processing (EUVIP), pp 142–147

  • Charalampidis D, Kasparis T, Jones WL (2002) Removal of nonprecipitation echoes in weather radar using multifractals and intensity. IEEE Trans Geosci Remote Sens 40:1121–1131. doi:10.1109/TGRS.2002.1010899

    Article  Google Scholar 

  • Cho Y-H, Lee GW, Kim K-E, Zawadzki I (2006) Identification and removal of ground echoes and anomalous propagation using the characteristics of radar echoes. J Atmospheric Ocean Technol 23:1206–1222. doi:10.1175/JTECH1913.1

    Article  Google Scholar 

  • Cortes C, Vapnik V (1995) Support-vector networks. Mach Learn 20:273–297. doi:10.1007/BF00994018

    Google Scholar 

  • Doviak RJ, Zrnic DS (1993) Doppler radar and weather observations. Courier Corporation

  • Grecu M, Krajewski WF (1999) Detection of anomalous propagation echoes in weather radar data using neural networks. IEEE Trans Geosci Remote Sens 37:287–296. doi:10.1109/36.739163

    Article  Google Scholar 

  • Guo Z, Zhang D, Zhang D (2010) A completed modeling of local binary pattern operator for texture classification. IEEE Trans Image Process 19:1657–1663. doi:10.1109/TIP.2010.2044957

    Article  Google Scholar 

  • Haddad B, Adane A, Mesnard F, Sauvageot H (2000) Modeling anomalous radar propagation using first-order two-state Markov chains. Atm Res 52:283–292. doi:10.1016/S0169-8095(99)00036-8

    Article  Google Scholar 

  • Haddad B, Adane A, Sauvageot H, Sadouki L, Naili R (2004) Identification and filtering of rainfall and ground radar echoes using textural features. Int J Remote Sens 25:4641–4656. doi:10.1080/01431160310001654455

    Article  Google Scholar 

  • Hamuzu K, Wakabayashi M (1991) Ground clutter rejection. In: Clukie IC, Collier CG (eds) In hydological applications of weather radar, pp 131–142

  • Han G, Zhao C (2008) A scene images classification method based on local binary patterns and nearest-neighbor classifier. In: Eighth International Conference on Intelligent Systems Design and Applications, 2008. ISDA’08. Presented at the Eighth International Conference on Intelligent Systems Design and Applications, 2008. ISDA’08, pp 100–104. doi:10.1109/ISDA.2008.19

  • Haralick RM (1979) Statistical and structural approaches to texture. Proc IEEE 67:786–804. doi:10.1109/PROC.1979.11328

    Article  Google Scholar 

  • Hedir M, Haddad B (2015) Ground echoes filtering using the completed local binary pattern and the support vector machine, in: Analysis of Multitemporal Remote Sensing Images (Multi-Temp), 2015 8th International Workshop on the. Presented at the Analysis of Multitemporal Remote Sensing Images (Multi-Temp), 2015 8th International Workshop on the, pp 1–4. doi:10.1109/Multi-Temp.2015.7245777

  • Islam T, Rico-Ramirez MA, Han D, Srivastava PK (2012) Artificial intelligence techniques for clutter identification with polarimetric radar signatures. Atm Res 109–110:95–113. doi:10.1016/j.atmosres.2012.02.007

    Article  Google Scholar 

  • Kaissassou S, Lenouo A, Tchawoua C, Lopez P, Gaye AT (2015) Climatology of radar anomalous propagation over West Africa. J. Atm Sol-Terr Phys 123:1–12. doi:10.1016/j.jastp.2014.11.009

    Article  Google Scholar 

  • Lakshmanan V, Hondl K, Stumpf G, Smith T (2003) Quality control of weather radar data using texture features and a neural network. Presented at the 5th International Conference on Advances in Pattern Recognition, IEEE, Kolkata

  • Magaldi AV, Mateu M, Bech J, Lorente J (2016) A long term (1999–2008) study of radar anomalous propagation conditions in the Western Mediterranean. Atmospheric Res. 169, Part A, 73–85. doi:10.1016/j.atmosres.2015.09.027

  • Mesnard F, Sauvageot H (2010) Climatology of anomalous propagation radar echoes in a coastal area. J Appl Meteorol Climatol 49:2285–2300. doi:10.1175/2010JAMC2440.1

    Article  Google Scholar 

  • Nanni L, Lumini A, Brahnam S (2012) Survey on LBP based texture descriptors for image classification. Expert Syst Appl 39:3634–3641. doi:10.1016/j.eswa.2011.09.054

    Article  Google Scholar 

  • Ojala T, Pietikainen M, Maenpaa T (2002) Multiresolution gray-scale and rotation invariant texture classification with local binary patterns. IEEE Trans Pattern Anal Mach Intell 24:971–987. doi:10.1109/TPAMI.2002.1017623

    Article  Google Scholar 

  • Pan S, Iplikci S, Warwick K, Aziz TZ (2012) Parkinson’s disease tremor classification: a comparison between support vector machines and neural networks. Expert Syst Appl 39:10764–10771. doi:10.1016/j.eswa.2012.02.189

    Article  Google Scholar 

  • Raaf O, Adane A (2014) Image-filtering and optimization of rainy cells. J Math Model Algorithms Oper Res 13:355–369. doi:10.1007/s10852-014-9252-1

    Article  Google Scholar 

  • Sadouki L, Haddad B (2013) Classification of radar echoes with a textural–fuzzy approach: an application for the removal of ground clutter observed in Sétif (Algeria) and Bordeaux (France) sites. Int J Remote Sens 34:7447–7463. doi:10.1080/01431161.2013.823522

    Article  Google Scholar 

  • Tashk A, Helfroush MS, Danyali H, Akbarzadeh-jahromi M (2015) Automatic detection of breast cancer mitotic cells based on the combination of textural, statistical and innovative mathematical features. Appl Math Model 39:6165–6182. doi:10.1016/j.apm.2015.01.051

    Article  Google Scholar 

  • Tebbi MA, Haddad B (2016) Artificial intelligence systems for rainy areas detection and convective cells’ delineation for the south shore of Mediterranean Sea during day and nighttime using MSG satellite images. Atm Res 178–179:380–392. doi:10.1016/j.atmosres.2016.04.013

    Article  Google Scholar 

  • Unser M (1986) Sum and difference histograms for texture classification. IEEE Trans. Pattern Anal Mach Intell PAMI-8, 118–125. doi:10.1109/TPAMI.1986.4767760

  • Wang P, Kao-Jixu Zhang Y, Jia H-Z (2012) Doppler weather radar clutter suppression based on texture feature. In: 2012 International Conference on Machine Learning and Cybernetics (ICMLC). Presented at the 2012 International Conference on Machine Learning and Cybernetics (ICMLC), pp 1339–1344. doi:10.1109/ICMLC.2012.6359559

Download references

Acknowledgements

The authors would like to thank all those who contributed to the radar data set used in this paper, notably the National Meteorology Office of Algeria for the Setif data and Météo-France for the Bordeaux images. We would also like to thank the reviewers for their valuable comments and suggestions.

Author information

Authors and Affiliations

  1. Faculty of Electronic and Informatics,Department of Telecommunications,Laboratory of Image Processing and Radiation, University of Science and Technology Houari Boumediene, PO Box 32, El Alia, Bab Ezzouar, 16111, Algiers, Algeria

    Mehdia Hedir & Boualem Haddad

Authors
  1. Mehdia Hedir
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Boualem Haddad
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Mehdia Hedir.

Additional information

Responsible Editor: C. Simmer.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Hedir, M., Haddad, B. Automatic system for radar echoes filtering based on textural features and artificial intelligence. Meteorol Atmos Phys 129, 555–572 (2017). https://doi.org/10.1007/s00703-016-0488-3

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00703-016-0488-3

Keywords

Search

Navigation