Precipitation data fusion using vector space transformation and artificial neural networks

  • Authors:

  • Anish C. Turlapaty;Valentine G. Anantharaj;Nicolas H. Younan;F. Joseph Turk

  • Affiliations:

  • Department of Electrical and Computer Engineering, Mississippi State University, MS 39762, United States and Geosystems Research Institute, Mississippi State University, MS 39762, United States;Geosystems Research Institute, Mississippi State University, MS 39762, United States;Department of Electrical and Computer Engineering, Mississippi State University, MS 39762, United States and Geosystems Research Institute, Mississippi State University, MS 39762, United States;Naval Research Laboratory, Marine Meteorology Division, Monterey, CA 93943, United States

  • Venue:
  • Pattern Recognition Letters
  • Year:
  • 2010

Quantified Score

Hi-index 0.10

Visualization

Abstract

We have developed a new methodology to fuse several precipitation datasets, available from different estimation techniques. The method is based on artificial neural networks and vector space transformation function. The final merged product is statistically superior to any of the individual datasets over a seasonal period. The results have been tested against ground-based measurements of rainfall over a study area. This method is shown to have average success rates of 85% in the summer, 68% in the fall, 77% in the spring, and 55% in the winter.