Publication Type:

Conference Paper

Source:

2018 International Conference on Communication and Signal Processing (ICCSP), IEEE, Adhiparasakthi Engineering College,Chennai, India, p.0666 – 0670 (2018)

ISBN:

9781538635216

URL:

https://ieeexplore.ieee.org/abstract/document/8523829

Keywords:

Biological system modeling, climatological variables, climatology, Computer architecture, convnet, Convolution, Data models, data-driven model, Deep learning, deep learning models, feedforward neural nets, learning (artificial intelligence), LSTM, mean square error methods, Neural networks, Neurons, precipitation, Predictive models, Rain, rainfall precipitation, Rainfall Prediction, rainfall prediction model, RMSE, Time series, time series data

Abstract:

Rainfall is one of the major source of freshwater for all the organism around the world. Rainfall prediction model provides the information regarding various climatological variables on the amount of rainfall. In recent days, Deep Learning enabled the self-learning data labels which allows to create a data-driven model for a time series dataset. It allows to make the anomaly/change detection from the time series data and also predicts the future event's data with respect to the events occurred in the past. This paper deals with obtaining models of the rainfall precipitation by using Deep Learning Architectures (LSTM and ConvNet) and determining the better architecture with RMSE of LSTM as 2.55 and RMSE of ConvNet as 2.44 claiming that for any time series dataset, Deep Learning models will be effective and efficient for the modellers.

Cite this Research Publication

S. Aswin, Dr. Geetha Srikanth, and Vinayakumar, R., “Deep Learning Models for the Prediction of Rainfall”, in 2018 International Conference on Communication and Signal Processing (ICCSP), Adhiparasakthi Engineering College,Chennai, India, 2018, pp. 0666 – 0670.