Development of an Optimal Neural Network for Avalanche Forecast in Himalayan Region

- This paper deals with the application of a well-known data mining technique, multi-layer back-propagation neural network, for forecasting of an avalanche in Himalayan region. Metrological and snow data for Himalayan region has been used for training the neural network. EasyNN-plus 6.0g, neural network software for Microsoft windows, is used for the development of an optimal neural networkPUSHPDEV. The system tries to model the decision making process of a pragmatic expert. PUSHPDEV can forecast whether an avalanche will trigger on a particular day from November to April. The network accepts eighteen inputs and produces an output whose value is zero or one, zero for no avalanche and one for avalanche on that day.

• Type: Conference
• Year: 2006
• Where: DMIN
• Authors: Rashpal Kaur, Mahesh Bansal, Atul Parti, V. Rihani
• Keywords: Avalanche, DMIN 2006, DMIN 2007, Himalayan Region, Neural Network