Deep Learning by Long Short-Term Memory Model for Rainfall Prediction in Thailand

Wanna Wirojdanthai

Abstract


In this work, the long short-term memory (LSTM) technique in the deep learning neural network is applied to find the pattern in time series data. The LSTM model is applied to find the rainfall pattern in Thailand over 20 years. The results show that the LSTM model can predict the seasonal behavior in each year. Also, it can detect correctly the peaks in the rainy season and can capture the minimum rainfall in a summer period over six years of testing data. The average rainfall in rainy season is approximately 250 mm. The training process is done successfully without vanishing gradient problem. These results show the advantage of the LSTM model in time series forecasting for seasonal data.

Keywords-Recurrent neural network, LSTM, rainfall, time series


Full Text:

PDF

References


Hsu K.L., Gup H.V., Sorooshian S., “Artificial neural network modeling of rainfall-runoff process”, Water Resour Res, 1995, 31(10):2517-2530.

Jain S.K., Das D., Srivastava D.K. “Application of ANN for reservoir inflow prediction and operation”, J. Water Resour Plan Manage, 1999, ASCE, 125(5):263-271.

Coulibaly P., Anctil F., Bobee B., “Daily reservoir inflow forecasting using artificial neural networks with stopped training approach”, J. Hydrol, 2000, 230:244-257.

Waibel A., Hanazawa T., Hintin G., Shikano K., Lang K.J., Phoneme recognition using time delay neural networks, IEEE Trans ASSP, 1989, 37(3):328-339.

Wan E.A., “Time series prediction using a connectionist network with internal delay lines, Time series prediction: forecasting the future and understanding the past. Addition-Wesley, 1993, Reading: 195-217.

Coulibaly P., Anctil F., Bobee B., “Multivariate reservoir inflow forecasting using temporal neural networks”, J. Hydrol Eng ASCE, 2001, 6(5):367-376.

Peter A., Burgsteiner H., Maass W., “A learning rule for very simple universal approximators consisting of a single layer of perceptrons”, Neural Networks, 2008, 21(5): 786-795.

Schmidhuber J., “Deep Learning in Neural Networks: An Overview”, Neural Networks, 2015, 61: 85–117.

Hochreiter S., Schmidhuber J., “Long short-term memory”, Neural Computation, 1997, 9(8): 1735-1780.

Gers F., Schmidhuber J., Cummins F., “Learning to Forget:Continual Prediction with LSTM”, Neural Computation, 2000, 12:2451-2471.

Diederik P. K., Jimmy B. Adam, “A method for stochastic optimization”, The 3rd International Conference for Learning Representations, San Diego, 2015.


Refbacks

  • There are currently no refbacks.