Performances of deep learning models for Indian Ocean wind speed prediction
- PDF / 9,876,719 Bytes
- 23 Pages / 595.276 x 790.866 pts Page_size
- 28 Downloads / 171 Views
ORIGINAL ARTICLE
Performances of deep learning models for Indian Ocean wind speed prediction Susmita Biswas1 · Mourani Sinha2 Received: 15 June 2020 / Accepted: 9 September 2020 © Springer Nature Switzerland AG 2020
Abstract A wind speed forecasting technique, using deep learning architectures based on long short-term memory (LSTM) model and bidirectional long short-term memory (BiLSTM) model is presented in this work. The coastal belts of the Indian peninsula are vulnerable to natural disasters like storm surges and inundations due to cyclones each year. The wind speed is a major parameter for analyzing extreme weather events. Prediction using numerical models is not efficient enough due to the irregular patterns in the data and, thus, deep neural network models involving many layers have been tested. The shallow feed-forward model has also been considered along with deep learning models to estimate future values from past data. The present work employs a comparison study of different models to forecast wind speed time series at two locations in the Bay of Bengal and the Arabian Sea, respectively, having different dynamics and randomness. For training the models, daily wind speed data are considered for the period 2006–2017 and an independent validation set is chosen comprising 2018 wind speed data to check the accuracy. To evaluate forecast efficiency among different network models fitted to given time series, mean square error (MSE) and root mean square error (RMSE) have been computed. Multiple experiments are conducted with different hidden unit values and epoch values to obtain the minimum error. Regression equations generated may be used for forecasting future time series. The BiLSTM model connecting hidden states of opposite directions proved to be most efficient for the wind speed forecasting in different regions. Keywords Machine learning · Deep learning · Bidirectional LSTM model · Wind speed · Indian Ocean · Prediction
Introduction Neural network models can be recurrent having loops or feed-forward that do not form a cycle. A network with a single hidden layer is called shallow whereas with two or more hidden layers is deep. Deep learning is a subset of the machine learning research. Machine learning is a branch of computational intelligence that creates algorithms that automatically enhance themselves with experience. A good performance of the machine learning model depends on having a good representation of the input data available. Deep learning models with the ability to redefine complex data * Mourani Sinha [email protected] 1
Department of Computer Science and Engineering, Techno India University, Saltlake, Kolkata, West Bengal 700091, India
Department of Mathematics, Techno India University, Saltlake, Kolkata, West Bengal 700091, India
2
from high-input data can dominate other sophisticated traditional machine learning methods (Mousavia et al. 2018). Deep learning models have obtained sophisticated results in some problems associated with classification and pattern recognition. These
Data Loading...
