Skip to main content
SpringerLink
Log in

Tropical cyclone intensity classification from infrared images of clouds over Bay of Bengal and Arabian Sea using machine learning classifiers

  • Original Paper
  • Published:
Arabian Journal of Geosciences Aims and scope Submit manuscript

Abstract

Tropical cyclones are natural phenomena occurring in coastal tropical regions that cause damage to life and property. Hence, a study of their evolution is necessary to prevent loss of life and property. In this paper, we present a cloud intensity classification technique for tropical cyclones based on feature extraction and pattern recognition, over the Bay of Bengal and Arabian Sea basins (latitudes 5° N–22° N and longitudes 52° E–100° E). Images of ten cyclones (2013 to 2018) are collected from the TC archive of Marine Meteorology Division of the US Naval Research Laboratory. A novel set of features is used for this purpose using some geometric properties of the cyclone structure. These features are fed to five machine learning classifiers: Naïve Bayes, Support Vector Machine, Logistic Model Tree, Random Tree and Random Forest. The Random Forest classifier used here for classification task outperforms other classifiers with an accuracy of 86.66%. It is also observed that the root mean square error of the Random Forest classifier maximum sustained wind speed is 9.84 knots. Results indicate that the proposed feature extraction technique and machine learning classifiers are feasible for the tropical cyclone intensity classification from infrared images.

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
Fig. 12
Fig. 13
Fig. 14

Similar content being viewed by others

References

  • Archive Bulletins (2013-2018) Indian Meteorological Department, Archive Bulletins DEMS-RSMC Tropical Cyclones, http://www.rsmcnewdelhi.imd.gov.in/index.php, Accessed 22 February 2021

  • Arora SK, Jha B (2016) Frequently Asked Questions [online]. Indian Meteorological Department. http://www.imdsikkim.gov.in/wxfaq.pdf. Accessed 24 February 2021

  • Bankert RL, Tag PM (2002) An automated method to estimate tropical cyclone intensity using SSM/I imagery. J Appl Meteorol 45:461–472

    Article  Google Scholar 

  • Barnes D, Manic M (2010) STRICR-FB, A novel size-translation-rotation-invariant character recognition method. In Proceedings of the 3rd International Conf. on Human System Interaction. Rzeszow:63–168. https://doi.org/10.1109/HSI.2010.5514573

  • Breiman L (1999) Random forests - random features. Technical Report 567, Statistics Department, University of California, Berkeley, https://statistics.berkeley.edu/tech-reports/567

  • Cardone VJ, Cox AT (2009) Tropical cyclone wind field forcing for surge models: critical issues and sensitivities. Nat Hazards 51:29–47

    Article  Google Scholar 

  • Chen Z, Yu X, Chen G, Zhou J (2018) Cyclone intensity estimation using multispectral imagery from the FY-4 satellite. In: Proceedings of the 2018 International Conference on Audio, Language and Image Processing (ICALIP), pp 46–51. https://doi.org/10.1109/ICALIP.2018.8455603

    Chapter  Google Scholar 

  • Chen G, Chen Z, Zhou F, Yu X, Zhang H, Zhu L (2019) A semisupervised deep learning framework for tropical cyclone intensity estimation. In: Proceedings of the 2019 10th International Workshop on the Analysis of Multitemporal Remote Sensing Images (MultiTemp). https://doi.org/10.1109/Multi-Temp.2019.8866970

    Chapter  Google Scholar 

  • Combinido JS, Mendoza JR, Aborot JA (2018) Convolutional neural network approach for estimating tropical cyclone intensity using satellite-based infrared images. In: Proceedings of the 2018 24th ICPR, pp 1474–1480. https://doi.org/10.1109/ICPR.2018.8545593

    Chapter  Google Scholar 

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

    Article  Google Scholar 

  • Drönner J, Korfhage N, Egli S, Mühling M, Thies B, Bendix J, Freisleben B, Seeger B (2018) Fast cloud segmentation using convolutional neural networks. Remote Sens 10:1–24

    Article  Google Scholar 

  • Dube SK, Rao AD, Sinha PC, Murty TS, Bahulayan N (1997) Storm surge in the Bay of Bengal and Arabian Sea: the problem and its Prediction. Mausam 48:283–304

    Article  Google Scholar 

  • Dube SK, Jain I, Rao AD, Murty TS (2009) Storm surge modeling for the Bay of Bengal and Arabian Sea. Nat Hazards 51:3–27

    Article  Google Scholar 

  • Dutta I, Banerjee S (2013) Elliptic Fourier descriptors in the study of cyclone cloud intensity patterns. International Journal of Image Processing 7:402–417

    Google Scholar 

  • Dvorak VF (1975) Tropical cyclone intensity analysis and forecasting from satellite imagery. Mon Weather Rev 103:420–430

    Article  Google Scholar 

  • Dvorak VF (1984) Tropical cyclone intensity analysis using satellite data. NOAA Technical Report NESDIS 11:1–47

    Google Scholar 

  • Eaton JW, Bateman D, Hauberg SA, Wehbring R (2016) GNU Octave version 4.2.0 manual: a high-level interactive language for numerical computations. http://www.gnu.org/software/octave/doc/interpreter. Accessed 22 February 2021

  • Fetanat G, Homaifar A, Knapp K (2013) Objective tropical cyclone intensity estimation using analogs of spatial features in satellite data. Weather Forecast 28:1446–1459

    Article  Google Scholar 

  • Frank WM, Ritchie EA (1999) Effects of environmental flow upon tropical cyclone structure. Mon Weather Rev 127:2044–2061

    Article  Google Scholar 

  • Frank E, Mark HA, Witten IH (2016) The WEKA workbench online appendix for data mining: practical machine learning tools and techniques. Morgan Kaufmann, San Francisco

    Google Scholar 

  • Griffin JS, Burpee RW, Marks FD, Franklin JL (1992) Real time airborne analysis of aircraft data supporting operational hurricane forecasting. Weather Forecast 7:480–490

    Article  Google Scholar 

  • Jaiswal N, Kishtawal CM (2013) Objective detection of center of tropical cyclone in remotely sensed infrared images. IEEE J-Stars 6:1031–1035

    Google Scholar 

  • Jin S, Wang S, Li X, Jiao L, Zhang JA, Shen D (2017) A salient region detection and pattern matching-based algorithm for center detection of a partially covered tropical cyclone in a SAR image. IEEE T Geosci Remote 55:280–291

    Article  Google Scholar 

  • Kar C, Banerjee S (2016) An approach towards automatic intensity detection of tropical cyclone by weight based unique feature vector. In: Proceedings of the IEEE International Conference on Computational Intelligence and Computing Research (ICCIC), pp 1–4. https://doi.org/10.1109/ICCIC.2016.7919616

    Chapter  Google Scholar 

  • Kar C, Banerjee S (2018) An image processing approach for intensity detection of tropical cyclone using feature vector analysis. International Journal of Image and Data Fusion 9:338–348

    Article  Google Scholar 

  • Kar C, Kumar A, Banerjee S (2019a) Tropical cyclone intensity detection by geometric features of cyclone images and multilayer perceptron. SN Applied Sciences 1:1099. https://doi.org/10.1007/s42452-019-1134-8

    Article  Google Scholar 

  • Kar C, Kumar A, Konar D, Banerjee S (2019b) Automatic region of interest detection of tropical cyclone image by center of gravity and distance metrics. In: Proceedings of the Fifth International Conference on Image Information Processing (ICIIP), pp 141–145. https://doi.org/10.1109/ICIIP47207.2019.8985860

    Chapter  Google Scholar 

  • Kim M, Park M, Im J, Park J, Lee M (2019) Machine learning approaches for detecting tropical cyclone formation using satellite data. Remote Sens 11:1–19

    Article  Google Scholar 

  • Kossin JP, Knaff JA, Berger HI, Herndon DC, Cram TA, Velden CS, Murnane RJ, Hawkins JD (2007) Estimating hurricane wind structure in the absence of aircraft reconnaissance. Weather Forecast 22:89–101

    Article  Google Scholar 

  • Kotal D, Bhattacharya SK (2020) Improvement of wind field forecasts for tropical cyclones over the North Indian Ocean. Tropical Cyclone Research and Review 9:53–66

    Article  Google Scholar 

  • Kulkarni A, Bankert A, Hadjimichael M (2010) Tropical cyclone intensity estimation using neural networks. In: Proceedings of the ASPRS Annual Conference, San Diego, California

    Google Scholar 

  • Landwehr N, Hall M, Frank E (2005) Logistic Model Trees. Mach Learn 59:161–205

    Article  Google Scholar 

  • Lee RST, Lin JNK (2001) An elastic contour matching model for tropical cyclone pattern recognition. IEEE T Syst Man Cy B. 31:413–417

    Article  Google Scholar 

  • Lee J, Im J, Cha DH, Park H, Sim S (2020) Tropical cyclone intensity estimation using multi-dimensional convolutional neural networks from geostationary satellite data. Remote Sens 12:2–24

    Google Scholar 

  • Liaw A, Wiener M (2002) Classification and regression by random forest. R News 2:18–22

    Google Scholar 

  • Liu Y, Racah E, Correa J, Khosrowshahi A, Lavers D, Kunkel K, Wehner M, Collins W (2016) Application of deep convolutional neural networks for detecting extreme weather in climate datasets. Int Conf Big Data:81–88

  • Matsuoka D, Nakano M, Sugiyama D et al (2018) Deep learning approach for detecting tropical cyclones and their precursors in the simulation by a cloud-resolving global nonhydrostatic atmospheric model. Progress in Earth and Planetary Science 5:1–16

    Article  Google Scholar 

  • Moon YS, Kim SP, Kim J (2012) Fast computation of rotation-invariant distances for image time-series data. In: Proceedings of the Convergence and Hybrid Information Technology, vol 7425, pp 516–524

    Chapter  Google Scholar 

  • National Oceanic and Atmospheric Administration (2021) Saffir-Simpson Hurricane Wind Scale https://www.nhc.noaa.gov/aboutsshws.php, Accessed 22 February 2021

  • NOAA (2021) https://www.ncdc.noaa.gov/data-access/model-data/model-datasets/numerical-weather-prediction, Accessed 22 February 2021

  • Numerical Weather Prediction Division (2021) IMD, http://nwp.imd.gov.in, Accessed 22 February 2021

  • Observing Systems Capability Analysis and Review Tool (2021) World Meteorological Organization https://www.wmo-sat.info/oscar/satellites/view/535, Accessed 22 February 2021

  • Olander TL, Velden CS, Turk MA (2002) Development of the advanced objective Dvorak technique (AODT)—Current progress and future directions. Preprints, 25th Conf. on Hurricanes and Tropical Meteorology, San Diego, CA

  • Olander TL, Velden CS (2007) The advanced Dvorak technique: continued development of an objective scheme to estimate tropical cyclone intensity using geostationary infrared satellite imagery. Weather Forecast 22:287–298

    Article  Google Scholar 

  • Olander TL, Velden CS (2019) The advanced Dvorak technique (ADT) for estimating tropical cyclone intensity: update and new capabilities. Weather Forecast 34:905–922

    Article  Google Scholar 

  • Onodera Y, Watanabe H, Taguchi A, Iijima N, Sone M, Mitsui H (1992) Translation and rotation-invariant pattern recognition method using neural network with back-propagation. In: Proceedings of the Singapore ICCS/ISITA, 2, pp 548–552

    Google Scholar 

  • Pal M (2005) Random forest classifier for remote sensing classification. Int J Remote Sens 26:217–222

    Article  Google Scholar 

  • Pao TL, Yeh JH (2008) Typhoon locating and reconstruction from the infra-red satellite cloud image. Journal of Multimedia 3:45–51

    Article  Google Scholar 

  • Park S, Im J, Jang E, Rhee J (2016) Drought assessment and monitoring through blending of multi-sensor indices using machine learning approaches for different climate regions. Agr Forest Meteorol 216:157–169

    Article  Google Scholar 

  • Pineros MF, Ritchie EA, Tyo JS (2008) Objective measures of tropical cyclone structure and intensity change from remotely sensed infrared data. IEEE T Geosci Remote 46:3574–3579

    Article  Google Scholar 

  • Pradhan R, Aygun RS, Maskey M, Ramachandran R, Cecil DJ (2018) Tropical cyclone intensity estimation using a deep convolutional neural network. IEEE Trans Image Process 27:692–702

    Article  Google Scholar 

  • Pu Z, Kalnay E (2019) Numerical weather prediction basics: models, numerical methods, and data assimilation. In: Handbook of Hydrometeorological Ensemble Forecasting. Springer, Berlin, pp 67–97

    Chapter  Google Scholar 

  • Richardson HJ, Hill DJ, Denesiuk DR, Fraser LH (2017) A comparison of geographic datasets and field measurements to model soil carbon using random forests and stepwise regressions (British Columbia, Canada). GISci Remote Sens 17:1–19

    Google Scholar 

  • Ritchie EA, Valliere-Kelley G, Piñeros MF, Tyo JS (2012) Tropical cyclone intensity estimation in the North Atlantic Basin using an improved deviation angle variance technique. Weather Forecast 27:1264–1277

    Article  Google Scholar 

  • Ritchie EA, Wood KM, Rodríguez-Herrera OG, Piñeros MF, Tyo JS (2014) Satellite-derived tropical cyclone intensity in the North Pacific Ocean using the deviation-angle variance technique. Weather Forecast 29:505–516

    Article  Google Scholar 

  • Roy C (2016) An informed system development approach to tropical cyclone track and intensity forecasting. Dissertation, Linkoping Studies in Science and Technology, Linkoping University.

  • Roy Chowdhury A, Chatterjee T, Banerjee S (2019) A Random Forest classifier-based approach in the detection of abnormalities in the retina. Med Biol Eng Comput 57:193–203

    Article  Google Scholar 

  • RSMC New Delhi (2019) Report on cyclonic disturbances over the north Indian ocean during 2018. http://rsmcnewdelhi.imd.gov.in/images/pdf/publications/annual-rsmc-report/rsmc-2018.pdf, Accessed 24 February 2021

  • Saffir HS (1973) Hurricane wind and storm surge. The Military Engineer 423:4–5

    Google Scholar 

  • Sakuragi T, Hoshino S, Kitabatake N (2014) Development and verification of a tropical cyclone intensity estimation method reflecting the variety of TRMM/TMI brightness temperature distribution, RSMC Tokyo - Typhoon Center. Tech Rep 16:1–15

    Google Scholar 

  • Simpson RH (1974) The Hurricane Disaster Potential Scale. Weatherwise 27:169–186

    Article  Google Scholar 

  • Takahashi HG (2011) Long-term changes in rainfall and tropical cyclone activity over South and Southeast Asia. Advances in Geosciences 30:17–22

    Article  Google Scholar 

  • TPC-21 Edition (2018) http://www.rsmcnewdelhi.imd.gov.in/images/pdf/publications/tcp-21/tcp-21-2018.pdf, Accessed 24 February 2021

  • Vapnik V (1998) The support vector method of function estimation. In: Suykens JAK, Vandewalle J (eds) Nonlinear modeling. Springer, Boston, pp 55–85

    Chapter  Google Scholar 

  • Velden C et al (2006) The Dvorak tropical cyclone intensity estimation technique: a satellite-based method that has endured for over 30 years. B Am Meteorol Soc 87:1195–1210

    Article  Google Scholar 

  • Wood VT (1994) A technique for detecting a tropical cyclone centre using a Doppler radar. J Atmos Ocean Tech 11:1207–1216

    Article  Google Scholar 

  • Yeh KS, Zhang X, Gopalakrishnan S, Aberson S, Rogers R, Marks F, Atlas R (2012) Performance of the experimental HWRF in the 2008 hurricane season. Nat hazards 63:1439–1449

    Article  Google Scholar 

  • Yip CL, Wong KY, Li PW (2006) Data complexity in tropical cyclone positioning and classification. In: Basu M, Ho TK (eds) Data complexity in pattern recognition. Advanced Information and Knowledge Processing. Springer, London, pp 249–270

    Google Scholar 

  • Yu X, Chen Z, Chen G, Zhang H, Zhou J (2019) A tensor network for tropical cyclone wind speed estimation. In: Proceedings of the 2019 IEEE International Geoscience and Remote Sensing Symposium, 10007─10010

    Google Scholar 

  • Yu X, Chen Z, Zhang H, Zheng Y (2020) A novel deep learning framework for tropical cyclone intensity estimation using FY-4 satellite imagery. In Proceedings of the 2020 the 4th International Conference on Innovation in Artificial Intelligence, 10─14

  • Zhang C, Wang X, Duanmu C (2010) Tropical cyclone cloud image segmentation by the B-Spline histogram with multi-scale transforms. Acta Meteorol Sin 24:78–94

    Google Scholar 

  • Zhang T, Lin W, Lin Y, Zhang M, Yu H, Cao K, Xue W (2019) Prediction of tropical cyclone genesis from mesoscale convective systems using machine learning. Weather Forecast 34:1035–1049

    Article  Google Scholar 

  • Zhao Y, Zhao C, Sun R, Wang Z (2016) A multiple linear regression model for tropical cyclone intensity estimation fromsatellite infrared images. Atmosphere 7:1–17

Download references

Acknowledgements

National Satellite Meteorological Center, Indian Meteorological Department for Archive Bulletins 2013-2018. Marine Meteorology Division of United State Naval Research Laboratory (http://www.nrlmry.navy.mil) for TC images as mentioned in Table 4.

Author information

Authors and Affiliations

  1. Department of Computer Science and Engineering, Sikkim Manipal Institute of Technology, Sikkim Manipal University, Gangtok, Sikkim, India

    Chinmoy Kar

  2. Department of Natural Science, Maulana Abul Kalam Azad University of Technology, Kolkata, India

    Sreeparna Banerjee

Authors
  1. Chinmoy Kar
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Sreeparna Banerjee
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Chinmoy Kar.

Ethics declarations

Conflict of interest

The authors declare that they have no competing interests.

Additional information

Responsible Editor: Biswajeet Pradhan

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Kar, C., Banerjee, S. Tropical cyclone intensity classification from infrared images of clouds over Bay of Bengal and Arabian Sea using machine learning classifiers. Arab J Geosci 14, 683 (2021). https://doi.org/10.1007/s12517-021-06997-5

Download citation

  • Received:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s12517-021-06997-5

Keywords

Search

Navigation