Precipitation data fusion using vector space transformation and artificial neural networks

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

doi:10.1016/j.patrec.2009.12.033

Precipitation data fusion using vector space transformation and artificial neural networks

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

Research output: Contribution to journal › Article › peer-review

16 Scopus citations

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.

Original language	English
Pages (from-to)	1184-1200
Number of pages	17
Journal	Pattern Recognition Letters
Volume	31
Issue number	10
DOIs	https://doi.org/10.1016/j.patrec.2009.12.033
State	Published - Jul 15 2010
Externally published	Yes

Funding

This research is sponsored by the NASA Applied Sciences Program via NNS06AA98B. The authors thank Dr. Billy Olsen and his colleagues at the NWS ABRFC for all their help and for providing the reference dataset. Our thanks also go to Dr. Yangrong Ling for acquiring and pre-processing the HRPP products used in this study.

Funders	Funder number
National Aeronautics and Space Administration	NNS06AA98B

Keywords

Artificial neural networks
Convergence
Data merging
Optimization
Pattern recognition

Access to Document

10.1016/j.patrec.2009.12.033

Cite this

@article{4c42cb79aa0541e2ad21669d295e50a7,

title = "Precipitation data fusion using vector space transformation and artificial neural networks",

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.",

keywords = "Artificial neural networks, Convergence, Data merging, Optimization, Pattern recognition",

author = "Turlapaty, {Anish C.} and Anantharaj, {Valentine G.} and Younan, {Nicolas H.} and {Joseph Turk}, F.",

year = "2010",

month = jul,

day = "15",

doi = "10.1016/j.patrec.2009.12.033",

language = "English",

volume = "31",

pages = "1184--1200",

journal = "Pattern Recognition Letters",

issn = "0167-8655",

publisher = "Elsevier",

number = "10",

}

TY - JOUR

T1 - Precipitation data fusion using vector space transformation and artificial neural networks

AU - Turlapaty, Anish C.

AU - Anantharaj, Valentine G.

AU - Younan, Nicolas H.

AU - Joseph Turk, F.

PY - 2010/7/15

Y1 - 2010/7/15

N2 - 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.

AB - 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.

KW - Artificial neural networks

KW - Convergence

KW - Data merging

KW - Optimization

KW - Pattern recognition

UR - http://www.scopus.com/inward/record.url?scp=77953128489&partnerID=8YFLogxK

U2 - 10.1016/j.patrec.2009.12.033

DO - 10.1016/j.patrec.2009.12.033

M3 - Article

AN - SCOPUS:77953128489

SN - 0167-8655

VL - 31

SP - 1184

EP - 1200

JO - Pattern Recognition Letters

JF - Pattern Recognition Letters

IS - 10

ER -

Precipitation data fusion using vector space transformation and artificial neural networks

Abstract

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this