Prediction of Sea Surface Current Velocity and Direction Using LSTM

Labuan Bajo is considered to have an important role as a transportation route for traders and tourists. Therefore, it is necessary to have a further understanding of the condition of the waters in Labuan Bajo, one of them is sea currents. The purpose of this research is to predict sea surface flow velocity and direction using LSTM. There are many prediction methods, one of them is Long short-term memory (LSTM). The fundamental of LSTM is to process information from the previous memory by going through three gates, that is forget gate, input gate, and output gate so the output will be the input in the next process. Based on trials with several parameters namely Hidden Layer, Learning Rate, Batch Size, and Learning rate drop period, it achieved the smallest MAPE values of U and V components of 14.15% and 8.43% with 50 hidden layers, 32 Batch size and 150 Learn rate drop.

[1]  Gábor Petneházi,et al.  Recurrent Neural Networks for Time Series Forecasting , 2018, ArXiv.

[2]  Elis Indrayanti,et al.  Pola Arus Permukaan Di Perairan Pulau Tidung, Kepulauan Seribu, Provinsi DKI Jakarta Pada Musim Peralihan (Maret-Mei) , 2016 .

[3]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[4]  Taghi M. Khoshgoftaar,et al.  Deep learning applications and challenges in big data analytics , 2015, Journal of Big Data.

[5]  Reza Pulungan,et al.  Prediction by a Hybrid of Wavelet Transform and Long-Short-Term-Memory Neural Network , 2017 .

[6]  Burak Aydog˘an,et al.  Current velocity forecasting in straits with artificial neural networks, a case study: Strait of Istanbul , 2010 .

[7]  Vijaya Kamble,et al.  Comparison of Predictive Algorithms: Backpropagation, SVM, LSTM and Kalman Filter for Stock Market , 2019, 2019 Amity International Conference on Artificial Intelligence (AICAI).

[8]  I. Ridwansyah,et al.  Long short term memory (LSTM) recurrent neural network (RNN) for discharge level prediction and forecast in Cimandiri river, Indonesia , 2019, IOP Conference Series: Earth and Environmental Science.

[9]  Mahendran Shitan,et al.  Forecasting with univariate time series models : a case of export demand for Peninsular Malaysia’s moulding and chipboard. , 2010 .

[10]  Mauro Castelli,et al.  The effect of batch size on the generalizability of the convolutional neural networks on a histopathology dataset , 2020, ICT Express.

[11]  Yohanes Suyanto,et al.  Bidirectional Long Short Term Memory Method and Word2vec Extraction Approach for Hate Speech Detection , 2020, IJCCS (Indonesian Journal of Computing and Cybernetics Systems).

[12]  Navin Kumar Manaswi,et al.  Deep Learning with Applications Using Python , 2018, Apress.

[13]  Sebastian Ruder,et al.  An overview of gradient descent optimization algorithms , 2016, Vestnik komp'iuternykh i informatsionnykh tekhnologii.

[14]  Xianfeng Tang,et al.  Revisiting Spatial-Temporal Similarity: A Deep Learning Framework for Traffic Prediction , 2018, AAAI.

[15]  I. Kimirei,et al.  Seasonal and spatial variation of surface current in the Pemba Channel, Tanzania , 2019, PloS one.

[16]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[17]  Chawki Djeddi,et al.  Stock Market Value Prediction using Deep Learning , 2020 .

[18]  Li Wei,et al.  Prediction of Sea Surface Temperature in the South China Sea by Artificial Neural Networks , 2020, IEEE Geoscience and Remote Sensing Letters.

[19]  M. Ye,et al.  Developing a Long Short-Term Memory (LSTM) based model for predicting water table depth in agricultural areas , 2018, Journal of Hydrology.

[20]  Akbar Siami Namin,et al.  Forecasting Economics and Financial Time Series: ARIMA vs. LSTM , 2018, ArXiv.

[21]  Arnita,et al.  Long Short-Term Memory Algorithm for Rainfall Prediction Based on El-Nino and IOD Data , 2021 .

[22]  Iwan Syarif,et al.  LSTM With Adam Optimization-Powered High Accuracy Preeclampsia Classification , 2019, 2019 International Electronics Symposium (IES).

[23]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[24]  Dian Candra Rini Novitasari,et al.  Prediksi Kecepatan Arus Laut dengan Menggunkan Metode Backpropagation (Studi Kasus: Labuhan Bajo) , 2020 .

[25]  C. Lewis.  Industrial and business forecasting methods : a practical guide to exponential smoothing and curve fitting , 1982 .

[26]  Yang Zhang,et al.  Effective Adam-Optimized LSTM Neural Network for Electricity Price Forecasting , 2018, 2018 IEEE 9th International Conference on Software Engineering and Service Science (ICSESS).

[27]  Adnan Sözen,et al.  Comparative analysis and forecasting of COVID-19 cases in various European countries with ARIMA, NARNN and LSTM approaches , 2020, Chaos, Solitons & Fractals.

[28]  Shahaboddin Shamshirband,et al.  Comparative Analysis of Recurrent Neural Network Architectures for Reservoir Inflow Forecasting , 2020, Water.

[29]  J. Scott Armstrong,et al.  On the Selection of Error Measures for Comparisons Among Forecasting Methods , 2005 .

[30]  H. Surbakti,et al.  Analisis Data Arus Di Perairan Muara Sungai Banyuasin Provinsi Sumatera Selatan , 2016 .