Open AccessShort term prediction of atmospheric temperature using neural networks
Author(s) -
Santanu Kumar Pal,
Jayanta Kumar Das,
Partho P. Sengupta,
Sharbari Banerjee
Publication year - 2002
Publication title -
mausam
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.243
H-Index - 12
ISSN - 0252-9416
DOI - 10.54302/mausam.v53i4.1662
Subject(s) - artificial neural network , backpropagation , term (time) , multilayer perceptron , perceptron , computer science , sample (material) , set (abstract data type) , layer (electronics) , artificial intelligence , algorithm , pattern recognition (psychology) , materials science , physics , thermodynamics , quantum mechanics , composite material , programming language
In this paper, a neural network based forecasting model for the maximum and the minimum temperature for the ground level is proposed. A backpropagation method of gradient-decent learning in multi-layer perceptron (MLP) type of neural network with only one hidden layer is considered. This network consists of 25 input nodes and two output nodes. The network is trained with a varying number of nodes in the hidden layer using a set of training sample and each of them is tested with a set of test sample. It accepts previous two consecutive days information (such as pressures, temperatures, relative humidities, etc.) as inputs for the estimation of the maximum and the minimum temperature as output. The network with 20 or less neurons in the hidden layer is found to be "optimum" and it produces an error within ±2° C for 80% of test cases.