Temperature forecasting using artificial neutral networks (ANN)

The objective of this paper is to develop an artificial neural network (ANN) model which can be used to predict weekly mean temperatures in Pantnagar, Uttarakhand, India. In order to determine the optimal network architecture, various network architectures were designed; different training algorithms were used; the number of neuron and hidden layer and transfer functions in the hidden layer/output layer were changed. Training of the network was performed by using Levenberg–Marquardt feed-forward back-propagation algorithms. Root mean square error and correlation coefficient statistics was used to measure the performance of the models. The results show that the ANN approach is a steadfast model for weekly temperature prediction.