A connectionist model for rainfall prediction

  • Authors:

  • Bimal Dutta;Angshuman Ray;Srimanta Pal;Dipak Chandra Patranabis

  • Affiliations:

  • Institute of Engineering and Management, Salt Lake Electronics Complex, Calcutta, India;Institute of Engineering and Management, Salt Lake Electronics Complex, Calcutta, India;Electronics and Communication Sciences Unit, Indian Statistical Institute, Calcutta, India;Department of Instrumentation and Electronics Engineering, Jadavpur University, Kolkata, India and Heritage Institute of Technology, Kolkata

  • Venue:
  • Neural, Parallel & Scientific Computations
  • Year:
  • 2009

Quantified Score

Hi-index 0.00

Visualization

Abstract

In this paper a neural network based method of local rainfall prediction is proposed. This method is developed based on past observations on various atmospheric parameters such as temperature, relative humidity, vapor presser, etc. We propose a neural network model whose architecture combines several multilayer perceptron networks (MLPs) to realize better performance after capturing the seasonality effect in the atmospheric data. We also demonstrate that the use of appropriate features can further improve the performance in prediction accuracy. These observations inspired us to use a feature selection MLP, FSMLP, (instead of MLP) which can select good features on-line while learning the prediction task. The FSMLP is used as a preprocessor to select good features. The combined use of FSMLP and SOFM-MLP results in a network system that uses only very few inputs but can produce good prediction.