Comparison of neural network configurations in the long-range forecast of southwest monsoon rainfall over India

被引：26

作者：

Chakraverty, Snehashish

Gupta, Pallavi

机构：

[1] B.P.P.P. Division, Central Building Research Institute

来源：

NEURAL COMPUTING & APPLICATIONS | 2008年 / 17卷 / 02期

关键词：

rainfall; neural network; south-west monsoon; forecast;

D O I：

10.1007/s00521-007-0093-y

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 [模式识别与智能系统]; 0812 [计算机科学与技术]; 0835 [软件工程]; 1405 [智能科学与技术];

摘要：

The accurate long-range forecast of southwest rainfall can have manifold benefits for the country, from disaster mitigation and town planning to crop planning and power generation. In this paper, the rainfall has been modeled using artificial neural network (ANN) with different network configurations. Performance of these networks are compared with some results found in the literature. The networks have also been tested for the data outside the range of the trained data and compared with known results. The present network is found to be better in term of predictions than the previous results by others. Southwest monsoon rainfall over India for 6 years in advance has been predicted.

引用

页码：187 / 192

页数：6