Tropical cyclone detection in South Pacifc and Atlantic coastal area using optical fow estimation and RESNET deep learning model

• Autorzy: Malothu, Nagu , Prasad, Varre Venkata Kanaka Durga Vara , Krishna, Battula Tirumala
• Języki publikacji: EN

Abstrakty

EN

Tropical cyclones (TC) are among the worst natural disasters, that cause massive damage to property and lives. The meteorologists track these natural phenomena using Satellite imagery. The spiral rain bands appear in a cyclic pattern with an eye as a center in the satellite image. Automatic identification of the cyclic pattern is a challenging task due to the clouds present around the structure. Conventional approaches use only image data to detect the cyclic structure using deep learning algorithms. The training and testing data consist of positive and negative samples of TC. But the cyclic structure’s texture pattern makes it difficult for the deep learning algorithms to extract useful features. This paper presents an automatic TC detection algorithm using optical flow estimation and deep learning algorithms to overcome this draw-back. The optical flow vectors are estimated using the Horn-Schunck estimator, the Liu-Shen estimator, and the Lagrange multiplier. The deep learning algorithms take the optical flow vectors as input during the training stage and extract the features to identify the cyclone’s circular pattern. The software used for experimental analysis is MATLAB 2021a. The proposed method increases the accuracy of detecting the cyclone pattern through optical flow vectors compared to using the pixel intensity values. By using proposed method 98% of accuracy will be achieved when compared with the existing methods.

Słowa kluczowe

PL

cyklon tropikalny; mnożnik Lagrange'a; estymator Horna-Schunka; estymator Liu-Shen; algorytm głębokiego uczenia

EN

tropical cyclone; Lagrange multiplier; Horn–Schunk estimator; Liu–Shen estimator; deep learning algorithm; conventional approaches

• Czasopismo: Acta Geophysica
• Rocznik: 2022
• Tom: Vol. 70, no 6
• Strony: 2855--2871
• Opis fizyczny: Bibliogr. 21 poz.

Twórcy

autor

Malothu, Nagu

• Department of ECE, JNTUK, Kakinada, AP, India,

autor

Prasad, Varre Venkata Kanaka Durga Vara

• Department of ECE, Gudlavalleru engineering college, Gudlavalleru, Krishna (Dt), AP, India,

autor

Krishna, Battula Tirumala

• Department of ECE, University College of Engineering, JNTUK, Kakinada, AP, India

Bibliografia

• 1. Bai CY, Chen BF, Lin HT (2020) Benchmarking tropical cyclone rapid intensification with satellite images and attention-based deep models. In: Joint European conference on machine learning and knowledge discovery in databases, pp 497–512. Springer
• 2. Chen B, Chen BF, Hsiao CM (2020) Cnn profiler on polar coordinate images for tropical cyclone structure analysis. arXiv preprint arXiv:2010.15158
• 3. Combinido JS, Mendoza JR, Aborot J (2018) A convolutional neural network approach for estimating tropical cyclone intensity using satellite-based infrared images. In: 2018 24th International conference on pattern recognition (ICPR), pp 1474–1480. IEEE
• 4. Del Portillo I, Cameron BG, Crawley EF (2019) A technical comparison of three low earth orbit satellite constellation systems to provide global broadband. Acta Astronautica 159:123–135
• 5. Drake J, Wiseman S (2018) Increasing incidence of dirofilaria immitis in dogs in usa with focus on the southeast region 2013–2016. Parasit vectors 11(1):1–7
• 6. Fudeyasu H, Hirose S, Yoshioka H, Kumazawa R, Yamasaki S (2014) A global view of the landfall characteristics of tropical cyclones. Trop Cyclone Res Rev 3(3):178–192
• 7. Geer AJ, Lonitz K, Weston P, Kazumori M, Okamoto K, Zhu Y, Liu EH, Collard A, Bell W, Migliorini S et al (2018) All-sky satellite data assimilation at operational weather forecasting centres. Q J R Meteorol Soc 144(713):1191–1217
• 8. Gualtieri L, Camargo SJ, Pascale S, Pons FM, Ekström G (2018) The persistent signature of tropical cyclones in ambient seismic noise. Earth Planet Sci Lett 484:287–294
• 9. Hsan TZ Sein MM (2019) Tropical cyclone determination using infrared satellite image. Dev Int J Trend Sci Res Dev 3:2464–2467
• 10. Hussain M, Chen D, Cheng A, Wei H, Stanley D (2013) Change detection from remotely sensed images: from pixel-based to object-based approaches. ISPRS J Photogram Remote Sens 80:91–106
• 11. Joyce RJ, Xie P (2011) Kalman filter-based cmorph. J Hydrometeorol 12(6):1547–1563
• 12. Kar C, Kumar A, Banerjee S (2019) Tropical cyclone intensity detection by geometric features of cyclone images and multilayer perceptron. SN Appl Sci 1(9):1–7
• 13. Kolstad EW (2021) Prediction and precursors of idai and 38 other tropical cyclones and storms in the mozambique channel. Q J R Meteorol Soc 147(734):45–57
• 14. Park MS, Kim M, Lee MI, Im J, Park S (2016) Detection of tropical cyclone genesis via quantitative satellite ocean surface wind pattern and intensity analyses using decision trees. Remote Sens Environ 183:205–214
• 15. Poompavai V, Ramalingam M (2013) Geospatial analysis for coastal risk assessment to cyclones. J Indian Soc Remote Sens 41(1):157–176
• 16. Pradhan R, Aygun RS, Maskey M, Ramachandran R, Cecil DJ (2017) Tropical cyclone intensity estimation using a deep convolutional neural network. IEEE Trans Image Process 27(2):692–702
• 17. Thompson MP, Norris FH, Hanacek B (1993) Age differences in the psychological consequences of hurricane hugo. Psychol Aging 8(4):606
• 18. Wang P, Wang P, Wang C, Yuan Y, Wang D (2020) A center location algorithm for tropical cyclone in satellite infrared images. IEEE J Select Top Appl Earth Observ Remote Sens 13:2161–2172
• 19. Weinkle J, Landsea C, Collins D, Musulin R, Crompton RP, Klotzbach PJ, Pielke R (2018) Normalized hurricane damage in the continental united states 1900–2017. Nat Sustain 1(12):808–813
• 20. Zhang C, Durgan SD, Lagomasino D (2019) Modeling risk of mangroves to tropical cyclones: a case study of hurricane irma. Estuarine Coastal Shelf Sci 224:108–116
• 21. Zhang CJ, Luo Q, Dai LJ, Ma LM, Lu XQ (2019) Intensity estimation of tropical cyclones using the relevance vector machine from infrared satellite image data. IEEE J Select Top Appl Earth Observ Remote Sens 12(3):763–773

Uwagi

PL

Opracowanie rekordu ze środków MEiN, umowa nr SONP/SP/546092/2022 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2022-2023).

Identyfikatory

DOI

10.1007/s11600-022-00849-w