Abstract
The early detection of track and intensity of cyclones reduces the impacts of destruction, and hence this paper proposes a model to determine the intensity of tropical cyclones from satellite images. The proposed system employs radial features and angular features to depict the characteristics of the tropical cyclone. Here the convolutional neural network (CNN) is employed in investigating the similarities between the actual recorded image and the image of the target cyclone, thereby extracting the optimal features of a tropical cyclone. The cyclone image considered as a target is the query image and bi-directional long short-term memory-based nomadic people optimisation (Bi-LSTM based NPO) algorithm predicts the intensity of the tropical cyclone. The prediction accuracy is enhanced by employing the proposed model. This paper utilised tropical cyclones for an image to intensity regression dataset (TCIR dataset). The experimental analysis is conducted to deliberate the estimation of tropical cyclone intensity. Finally, the comparative analysis is carried out for the proposed approach and other existing approaches to determine the error value rate of the proposed model.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Baki H, Chinta S, Balaji C and Srinivasan B 2021 A sensitivity study of WRF model microphysics and cumulus parameterisation schemes for the simulation of tropical cyclones using GPM radar data; J. Earth Syst. Sci. 130(4) 1–30.
Chandrasekar R, Sahu R K and Balaji C 2022 Assimilation of multi-channel radiances in mesoscale models with an ensemble technique to improve track forecasts of tropical cyclones; J. Earth Syst. Sci. 131(2) 1–20.
Chen B, Chen B F and Lin H T 2018 Rotation-blended CNNs on a new open dataset for tropical cyclone image-to-intensity regression; In: Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp. 90–99.
Combinido J S, Mendoza J R and 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), IEEE, pp. 1474–1480.
Devaraj J, Ganesan S, Elavarasan R M and Subramaniam U 2021 A novel deep learning based model for tropical intensity estimation and post-disaster management of hurricanes; Appl. Sci. 11(9) 4129.
Dong S, Wu W, He K and Mou X 2020 Rolling bearing performance degradation assessment based on improved convolutional neural network with anti-interference; Measurement 151 107219.
Elsberry R L 2014 Advances in research and forecasting of tropical cyclones from 1963–2013; Asia-Pacific J. Atmos. Sci. 50(1) 3–16.
Hallam S, Guishard M, Josey S A, Hyder P and Hirschi J 2021 Increasing tropical cyclone intensity and potential intensity in the subtropical Atlantic around Bermuda from an ocean heat content perspective 1955–2019; Environ. Res. Lett. 16(3) 034052.
Higa M, Tanahara S, Adachi Y, Ishiki N, Nakama S, Yamada H, Ito K, Kitamoto A and Miyata R 2021 Domain knowledge integration into deep learning for typhoon intensity classification; Sci. Rep. 11(1) 1–10.
Kanase R D, Deshpande M S, Krishna R P M and Mukhopadhyay P 2020 Evaluation of convective parameterisation schemes in simulation of tropical cyclones by climate forecast system model: Version 2; J. Earth Syst. Sci. 129(1) 1–18.
Kumar A, Gandhi C P, Zhou Y, Kumar R and Xiang J 2020 Improved deep convolution neural network (CNN) for the identification of defects in the centrifugal pump using acoustic images; Appl. Acoust. 167 107399.
Lee J, Im J, Cha D H, Park H and Sim S 2019 Tropical cyclone intensity estimation using multi-dimensional convolutional neural networks from geostationary satellite data; Remote Sens. 12(1) 108.
Lee Y J, Hall D, Liu Q, Liao W W and Huang M C 2021 Interpretable tropical cyclone intensity estimation using Dvorak-inspired machine learning techniques; Eng. Appl. Artificial Intelligence 101 104233.
Liu M, Lu Y, Long S, Bai J and Lian W 2021 An attention-based CNN-BiLSTM Hybrid Neural Network Enhanced with Features of Discrete Wavelet Transformation for Fetal Acidosis Classification; Expert Systems with Applications, https://doi.org/10.1016/j.eswa.2021.115714.
Liu S, Lin W, Portabella M and Wang Z 2022 Characterisation of tropical cyclone intensity using the HY-2B scatterometer wind data; Remote Sens. 14(4) 1035.
McNeely T, Dalmasso N and Wood K M 2020 Structural forecasting for tropical cyclone intensity prediction: Providing insight with deep learning; arXiv preprint arXiv, https://doi.org/10.48550/arXiv.2010.05783.
Nerrise F 2021 Predictive agent-based modeling of natural disasters using machine learning; In: Proceedings of the AAAI Conference on Artificial Intelligence 35(18) 15,976–15,977.
Prattipati Sanjeeva R and Saurabh D 2021 Cyclone prediction using machine learning; PhD diss., Discipline of Astronomy, Astrophysics and Space Engineering, IIT Indore.
Salih S Q and Alsewari A A 2020 A new algorithm for normal and large-scale optimisation problems: Nomadic people optimiser; Neural Comput. Appl. 32(14) 10,359–10,386.
Shahid F, Zameer A and Muneeb M 2020 Predictions for COVID-19 with deep learning models of LSTM, GRU and Bi-LSTM; Chaos, Solitons Fract. 140 110212.
Tan J, Chen S and Wang J 2021 Western north Pacific tropical cyclone track forecasts by a machine learning model; Stoch. Environ. Res. Risk Assess. 35(4) 1–14.
Tan J, Yang Q, Hu J, Huang Q and Chen S 2022 Tropical cyclone intensity estimation using Himawari-8 satellite cloud products and deep learning; Remote Sens. 14(4) 812.
Varalakshmi P, Vasumathi N and Venkatesan R 2021 Tropical cyclone prediction based on multi-model fusion across Indian coastal region; Progr. Oceanogr. 193 102557.
Varotsos C A, Krapivin V F and Soldatov V Y 2019 Monitoring and forecasting of tropical cyclones: A new information-modeling tool to reduce the risk; Int. J. Disaster Risk Reduction 36 101088.
Wang X, Wang W and Yan B 2020 Tropical cyclone intensity change prediction based on surrounding environmental conditions with deep learning; Water 12(10) 2685.
Xu W, Balaguru K, August A, Lalo N, Hodas N, DeMaria M and Judi D 2021 Deep learning experiments for tropical cyclone intensity forecasts; Wea. Forecasting 36(4) 1453–1470.
Zhang C J, Wang X J, Ma L M and Lu X Q 2021 Tropical cyclone intensity classification and estimation using infrared satellite images with deep learning; IEEE J. Selected Topics Appl. Earth Observ. Remote Sens. 14 2070–2086.
Zhang Z, Yang X, Shi L, Wang B, Du Z, Zhang F and Liu R 2022 A neural network framework for fine-grained tropical cyclone intensity prediction; Knowledge-Based Systems 241 108195.
Author information
Authors and Affiliations
Contributions
S Akila Rajini: Visualisation, conceptualisation, systematic descriptions, interpretations, writing and preparing the manuscript; G Tamilpavai: Investigation, systematic descriptions, simulation of data, investigation, simulation of data, validation, reviewing and editing.
Corresponding author
Additional information
Communicated by P A Francis
Rights and permissions
About this article
Cite this article
Rajini, S.A., Tamilpavai, G. Nomadic people optimisation based Bi-LSTM for detection and tracking of tropical cyclone. J Earth Syst Sci 132, 19 (2023). https://doi.org/10.1007/s12040-022-02028-3
Received:
Revised:
Accepted:
Published:
DOI: https://doi.org/10.1007/s12040-022-02028-3