Assessing Cyclonic Wave Heights In The Arabian Sea Using Deep Learning Models.
Main Article Content
Abstract
Ocean wave heights in the Arabian Sea during tropical cyclones (TC) are predicted using deep learning models based on long short-term memory (LSTM) and bidirectional short-term memory (BLSTM) networks. The models utilize different lead times. Combining the BLSTM model with the traditional numerical wave models can provide a more accurate and computationally efficient forecast method for large wave height data. Two grids, G1 (71.5°E, 22.0°N) and G2 (67.1°E, 22.6°N), have been selected for the Arabian Sea (AS). Based on these grids, the model estimated significant wave heights are constructed, and the cyclones TAUKTAE (15 May–19 May 2021) and BIPARJOY (06 June–15 June 2023) went through. Deep learning models are used to estimate significant wave heights under severe situations, and the accuracy is compared using root mean square error (RMSE). Time series for grid G1 are examined from 1983 to 2021, whereas shorter time series for grid G2 are examined from 2013 to 2023. With the goal of achieving the least amount of error, the LSTM and BLSTM models are evaluated using various hidden units and epoch settings after being trained with 80% data. Less error was produced by the larger time-series for the training set, whether or not the TC conditions were included. The shorter time-series including the cyclonic data produced higher error for the 20% testing set. Additional forecasts with varying lead periods or delays were made, which increased inaccuracy. This has to do with the model's diminishing power as the forecast horizon gets longer.
Article Details
References
Akhil CP, Deka PC (2017) Application of Machine Learning Techniques in Wave Height Forecasting in Marine Environment-A Review. IJIRESET 6(5).http://www.ijirset.com/volume-6-issue-5.html
Ali M, Prasad R (2019) Significant wave height forecasting via an extreme learning machine model integrated with improved complete ensemble empirical mode decomposition. Renewable and Sustainable Energy Reviews 104:281-295. https://doi.org/10.1016/j.rser.2019.01.014
Bethel BJ, Sun W, Dong C, Wang D (2022) Forecasting hurricane-forced significant wave heights using a long short-term memory network in the Caribbean Sea. Ocean Science 18:419–436. https://doi.org/10.5194/os-18-419-2022
Biswas S, Sinha M (2021) Performances of deep learning models for Indian Ocean wind speed prediction. Modeling Earth Systems and Environment 7(2):809-831.https://doi.org/10.1007/s40808-020-00974-9
Deo MC, Jha A, Chaphekar AS, Ravikant K (2001) Neural networks for wave forecasting. Ocean Engineering 28:889-898.https://doi.org/10.1016/S0029-8018(00)00027-5
Deo M, Naidu CS (1999) Real time wave forecasting using neural networks. Ocean Engineering 26:191-203. https://doi.org/10.1016/S0029-8018(97)10025-7
Filik UB, Filik T (2017) Wind Speed Prediction Using Artificial Neural Networks Based on Multiple Local Measurements in Eskisehir. Energy Procedia 107:264-269.
doi: 10.1016/j.egypro.2016.12.147
Gopinatha DI, Dwarakishb S (2015) Wave prediction using neural networks at New Mangalore Port along west coast of India. Aquatic Procedia 4:143–150.doi: 10.1016/j.aqpro.2015.02.020
Graves A, Mohamed AR, Hinton G (2013) Speech recognition with deep recurrent neural networks. IEEE international conference on acoustics, speech and signal processing, pp 6645-6649. DOI: 10.1109/ICASSP.2013.6638947
Greff K, Srivastava RK, Koutnik J, Steunebrink BR, Schmidhuber J (2017) LSTM: A Search Space Odyssey.arXiv:1503.04069v2 [cs.NE]
Hochreiter S, Schmidhuber J (1997) LONG SHORT-TERM MEMORY. Neural Computation 9(8):1735-1780.https://doi.org/10.1162/neco.1997.9.8.1735
Kim J, Moon N (2019)BiLSTM model based on multivariate time series data in multiple field for forecasting trading area. Journal of Ambient Intelligence and Humanized Computing.https://doi.org/10.1007/s12652-019-01398-9
Kumar VS, Mandal S, Kumar SA (2003) Estimation of wind speed and wave height during cyclones. Ocean Engineering 30:2239-2253.doi:10.1016/S0029-8018(03)00076-3
Liu Y, Sun W, Durlofsky LJ (2019) A Deep-Learning-Based Geological Parameterization for History Matching Complex Models. Mathematical Geoscience 51:725-766. https://doi.org/10.1007/s11004-019-09794-9
Makarynskyy O, Pires-Silva AA, Makarynska D, Ventura-Soares C (2005) Artificial neural networks in wave predictions at the west coast of Portugal. Computers and Geosciences 31:415-424. https://doi.org/10.1016/j.cageo.2004.10.005
M Alif Rizal Yonanta, Didit A, Nugrahinggil S (2018) Wind Wave Prediction by using Autoregressive Integrated Moving Average model : Case Study in Jakarta Bay. International Journal on ICT 4(2):33-42. doi:10.21108/indojc.2018.42.300
Namini SS, Tavakoli N, Namin AS (2018) A Comparison of ARIMA and LSTM in Forecasting Time Series. 17th IEEE International Conference on Machine Learning and Applications (ICMLA), Orlando, FL, pp. 1394-1401.doi: 10.1109/ICMLA.2018.00227
Ni C, Ma X, Wang J (2019) Integrated deep learning model for predicting electrical power generation from wave energy converter. Proceedings of the 25th International conference on Automation and Computing, Lancaster University. DOI:10.23919/IConAC.2019.8895237
Oh J, Suh KD (2018) Real-time forecasting of wave heights using EOF – wavelet – neural network hybrid model. Ocean engineering 150:48-59.
https://doi.org/10.1016/j.oceaneng.2017.12.044
Patel M, Patel A, Ghosh R (2018) Precipitation Nowcasting: Leveraging bidirectional LSTM and 1D CNN.arXiv:1810.10485 (cs)
Petitjeana P, Ingladac J, Gancarskia P (2014) Assessing the quality of temporal high-resolution classifications with low-resolution satellite image time series. International Journal of Remote Sensing. 35(7)2:693–2712.http://dx.doi.org/10.1080/01431161.2014.883092
Reddy DS, Prasad PRC (2018) Prediction of vegetation dynamics using NDVI time series data and LSTM. Modeling Earth Systems and Environment 4:409-419.https://doi.org/10.1007/s40808-018-0431-3
Samanta B, Bandopadhyay S, Ganguli R (2006) Comparative Evaluation of Neural Network Learning Algorithms for Ore Grade Estimation. Mathematical Geology 38(2). DOI: 10.1007/s11004-005-9010-z
Sanil KV, Amrutha MM (2017) Characteristics of high monsoon wind-waves observed at multiple stations in the eastern Arabian Sea. Ocean Science Discussions.https://doi.org/10.5194/os-2017-84
Scott C Jamesa, YushanZhangb, FearghalO’Donnchac (2017) A Machine Learning Framework to Forecast Wave Conditions. arXiv:1709.08725v1
Siami-Namini S, Tavakoli N, NaminAS(2019) The Performance of LSTM and BiLSTM in Forecasting Time Series. IEEE International Conference on Big Data, pp. 3285-3292. doi:10.1109/BigData47090.2019.9005997
Singh OP, Khan TMA, Sazedur Rahman Md (2001)Has the frequency of intense tropical cyclones increased in the north Indian Ocean? Current Science 80(4):575–580. doi: 10.1016/j.neunet.2005.06.042
Srinivasan R, Abhigna P, Jerrita S, Rajendra V (2016) Analysis of recurrent neural networks for prediction of wave height using wind data. International Conference on Emerging Trend in Engineering Research at Vels University, Chennai.
SWAMP Group: Allender JH, Barnett TP, Bertotti L, Bruinsma J, Cardone VJ, Cavaleri L, Ephraums J, Golding B, Greenwood A, Guddal J, G¨unther H, Hasselmann K, Hasselmann S, Joseph P, Kawai S, Komen GJ, Lawson L, Linn´e H, Long RB, Lybanon M, Maeland E, Rosenthal W, Toba Y, Uji T, de Voogt WJP (1985) Sea wave modeling project (SWAMP), An intercomparison study of wind wave predictions models, part 1: Principal results and conclusions. Ocean Wave Modeling, Plenum, pp. 256.
Tolman H (1991)A third-generation model for wind waves on slowly varying, unsteady, and inhomogeneous depths and currents. Journal of Physical Oceanography 21(6):782-797.
Wu T, Cao Y, Wu Z et al (2019) Deep learning for inversion of significant wave height based on actual sea surface backscattering coefficient model. Multimedia Tools and Applications.https://doi.org/10.1007/s11042-019-07967-6
Yulitaa IN, Fananya MI, Arymuthya AM (2017) Bi-directional Long Short-Term Memory using Quantized data of Deep Belief Networks for Sleep Stage Classification.Procedia Computer Science 116:530-538.https://doi.org/10.1016/j.procs.2017.10.042
Zhang L, Oey L (2019)An observational analysis of ocean surface waves in tropical cyclones in the western North Pacific Ocean. Journal of Geophysical Research: Oceans 124:184-195.https://doi.org/10.1029/2018JC014517
Zhuxin O ,Yaoting G , Xuefeng Z , Xiangyu Wu, Dianjun Z(2024) Significant Wave Height Forecasting Based on EMD-TimesNet Networks., J. Mar. Sci. Eng. 12(4), 536. https://doi.org/10.3390/jmse12040536