Enhancement of satellite precipitation estimation via unsupervised dimensionality reduction

Majid Mahrooghy; Nicolas H. Younan; Valentine G. Anantharaj; James V. Aanstoos

doi:10.1109/TGRS.2012.2189406

Enhancement of satellite precipitation estimation via unsupervised dimensionality reduction

Majid Mahrooghy, Nicolas H. Younan, Valentine G. Anantharaj, James V. Aanstoos

Data Lifecycle Technologies

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

4 Scopus citations

Abstract

A methodology to enhance satellite precipitation estimation using unsupervised dimensionality reduction (UDR) techniques is developed. This enhanced technique is an extension to the precipitation estimation from remotely sensed imagery using an artificial neural network (PERSIANN) and cloud classification system (CCS) method (PERSIANN-CCS) enriched using wavelet features combined with dimensionality reduction. Cloud-top brightness temperature measurements from the Geostationary Operational Environmental Satellite (GOES)-12 are used for precipitation estimation at 4 km $\times$ 4 km spatial resolutions every 30 min. The study area in the continental U.S. covers parts of Louisiana, Arkansas, Kansas, Tennessee, Mississippi, and Alabama. Based on quantitative measures, root mean square error and Heidke skill score (HSS), the results show that the UDR techniques can improve the precipitation estimation accuracy. In addition, the independent component analysis is shown to have better performance than other UDR techniques; and in some cases, it achieves 10% improvement in the HSS.

Original language	English
Article number	6178796
Pages (from-to)	3931-3940
Number of pages	10
Journal	IEEE Transactions on Geoscience and Remote Sensing
Volume	50
Issue number	10 PART2
DOIs	https://doi.org/10.1109/TGRS.2012.2189406
State	Published - 2012

Funding

Manuscript received October 31, 2010; revised July 10, 2011 and January 6, 2012; accepted February 22, 2012. Date of publication April 4, 2012; date of current version September 21, 2012. This work was supported by the National Aeronautics and Space Administration Applied Sciences Program under Grant NNS06AA98B and the National Oceanic and Atmospheric Administration Office of Atmospheric Research under Grant NA07OAR4170517. The authors thank Dr. S. Sorooshian, Dr. K-L. Hsu, and the PERSIANN group at UC Irvine for providing the operational PERSIANN-CCS products and the helpful discussions about their methodology. V. Anantharaj is also supported by the Oak Ridge Leadership Computing Facility under the auspices of the Office of Advanced Scientific Computing Research, Office of Science, U.S. Department of Energy under Contract No. DE-AC05-00OR22725 and Contract No.DE-AC05-00OR22725 with UT-Battelle, LLC.

Funders	Funder number
National Oceanic and Atmospheric Administration Office of Atmospheric Research	NA07OAR4170517
Oak Ridge National Laboratory
U.S. Department of Energy	DE-AC05-00OR22725
National Aeronautics and Space Administration	NNS06AA98B
Office of Science
Advanced Scientific Computing Research

Keywords

Dimensionality reduction
Remote sensing
Satellite precipitation estimation (SPE)
Wavelets

Access to Document

10.1109/TGRS.2012.2189406

Cite this

@article{a829a620b9344712b0575f538251c46b,

title = "Enhancement of satellite precipitation estimation via unsupervised dimensionality reduction",

abstract = "A methodology to enhance satellite precipitation estimation using unsupervised dimensionality reduction (UDR) techniques is developed. This enhanced technique is an extension to the precipitation estimation from remotely sensed imagery using an artificial neural network (PERSIANN) and cloud classification system (CCS) method (PERSIANN-CCS) enriched using wavelet features combined with dimensionality reduction. Cloud-top brightness temperature measurements from the Geostationary Operational Environmental Satellite (GOES)-12 are used for precipitation estimation at 4 km $\times$ 4 km spatial resolutions every 30 min. The study area in the continental U.S. covers parts of Louisiana, Arkansas, Kansas, Tennessee, Mississippi, and Alabama. Based on quantitative measures, root mean square error and Heidke skill score (HSS), the results show that the UDR techniques can improve the precipitation estimation accuracy. In addition, the independent component analysis is shown to have better performance than other UDR techniques; and in some cases, it achieves 10% improvement in the HSS.",

keywords = "Dimensionality reduction, Remote sensing, Satellite precipitation estimation (SPE), Wavelets",

author = "Majid Mahrooghy and Younan, {Nicolas H.} and Anantharaj, {Valentine G.} and Aanstoos, {James V.}",

year = "2012",

doi = "10.1109/TGRS.2012.2189406",

language = "English",

volume = "50",

pages = "3931--3940",

journal = "IEEE Transactions on Geoscience and Remote Sensing",

issn = "0196-2892",

publisher = "Institute of Electrical and Electronics Engineers",

number = "10 PART2",

}

TY - JOUR

T1 - Enhancement of satellite precipitation estimation via unsupervised dimensionality reduction

AU - Mahrooghy, Majid

AU - Younan, Nicolas H.

AU - Anantharaj, Valentine G.

AU - Aanstoos, James V.

PY - 2012

Y1 - 2012

N2 - A methodology to enhance satellite precipitation estimation using unsupervised dimensionality reduction (UDR) techniques is developed. This enhanced technique is an extension to the precipitation estimation from remotely sensed imagery using an artificial neural network (PERSIANN) and cloud classification system (CCS) method (PERSIANN-CCS) enriched using wavelet features combined with dimensionality reduction. Cloud-top brightness temperature measurements from the Geostationary Operational Environmental Satellite (GOES)-12 are used for precipitation estimation at 4 km $\times$ 4 km spatial resolutions every 30 min. The study area in the continental U.S. covers parts of Louisiana, Arkansas, Kansas, Tennessee, Mississippi, and Alabama. Based on quantitative measures, root mean square error and Heidke skill score (HSS), the results show that the UDR techniques can improve the precipitation estimation accuracy. In addition, the independent component analysis is shown to have better performance than other UDR techniques; and in some cases, it achieves 10% improvement in the HSS.

AB - A methodology to enhance satellite precipitation estimation using unsupervised dimensionality reduction (UDR) techniques is developed. This enhanced technique is an extension to the precipitation estimation from remotely sensed imagery using an artificial neural network (PERSIANN) and cloud classification system (CCS) method (PERSIANN-CCS) enriched using wavelet features combined with dimensionality reduction. Cloud-top brightness temperature measurements from the Geostationary Operational Environmental Satellite (GOES)-12 are used for precipitation estimation at 4 km $\times$ 4 km spatial resolutions every 30 min. The study area in the continental U.S. covers parts of Louisiana, Arkansas, Kansas, Tennessee, Mississippi, and Alabama. Based on quantitative measures, root mean square error and Heidke skill score (HSS), the results show that the UDR techniques can improve the precipitation estimation accuracy. In addition, the independent component analysis is shown to have better performance than other UDR techniques; and in some cases, it achieves 10% improvement in the HSS.

KW - Dimensionality reduction

KW - Remote sensing

KW - Satellite precipitation estimation (SPE)

KW - Wavelets

UR - http://www.scopus.com/inward/record.url?scp=84867054372&partnerID=8YFLogxK

U2 - 10.1109/TGRS.2012.2189406

DO - 10.1109/TGRS.2012.2189406

M3 - Article

AN - SCOPUS:84867054372

SN - 0196-2892

VL - 50

SP - 3931

EP - 3940

JO - IEEE Transactions on Geoscience and Remote Sensing

JF - IEEE Transactions on Geoscience and Remote Sensing

IS - 10 PART2

M1 - 6178796

ER -

Enhancement of satellite precipitation estimation via unsupervised dimensionality reduction

Abstract

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this