Extreme Learning Machine versus Multilayer perceptron for rainfall estimation from MSG Data

The application of artificial neural networks (ANN) in several fields has shown considerable success for classification or regression. Learning algorithms such as artificial neural networks must constantly readjust during the learning phase. This requires a relatively long learning time compared to the size and dimension of the data used. Contrary to these considerations, a new neural network, such as Extreme Learning Machine (ELM) has recently been implemented. The ELM does not care much about the size of the neural network, the hidden layer parameters are randomly generated and remain constant instead of being adjusted during training. In this paper, we will present a comparison between two neural networks, namely ELM and MLP (Multilayer perceptron) implemented for the precipitation estimation from meteorological satellite data. The architecture chosen for the two neural networks consists of an input layer (7 neurons), a hidden layer (8 neurons) and an output layer (7 neurons). The MLP has undergone standard training as soon as the ELM is trained according to the characteristics mentioned above. The results show that MLP prevails over ELM. However, the time cost during learning is too high for MLP compared to ELM.