A linear merging methodology for high-resolution precipitation products using spatiotemporal regression

Anish C. Turlapaty; Nicolas H. Younan; Valentine G. Anantharaj

doi:10.1080/01431161.2012.703345

A linear merging methodology for high-resolution precipitation products using spatiotemporal regression

Anish C. Turlapaty, Nicolas H. Younan, Valentine G. Anantharaj

Data Lifecycle Technologies

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

2 Scopus citations

Abstract

Currently, the only viable option for a global precipitation product is the merger of several precipitation products from different modalities. In this article, we develop a linear merging methodology based on spatiotemporal regression. Four highresolution precipitation products (HRPPs), obtained through methods including the Climate Prediction Center's Morphing (CMORPH), Geostationary Operational Environmental Satellite-Based Auto-Estimator (GOES-AE), GOES-Based Hydro-Estimator (GOES-HE) and Self-Calibrating Multivariate Precipitation Retrieval (SCAMPR) algorithms, are used in this study. The merged data are evaluated against the Arkansas Red Basin River Forecast Center's (ABRFC's) ground-based rainfall product. The evaluation is performed using the Heidke skill score (HSS) for four seasons, from summer 2007 to spring 2008, and for two different rainfall detection thresholds. It is shown that the merged data outperform all the other products in seven out of eight cases. A key innovation of this machine learning method is that only 6% of the validation data are used for the initial training. The sensitivity of the algorithm to location, distribution of training data, selection of input data sets and seasons is also analysed and presented.

Original language	English
Pages (from-to)	7844-7867
Number of pages	24
Journal	International Journal of Remote Sensing
Volume	33
Issue number	24
DOIs	https://doi.org/10.1080/01431161.2012.703345
State	Published - Dec 20 2012

Funding

This research was sponsored by NASA Applied Sciences Program under Grant NNS06AA98B and the NOAA Office of Atmospheric Research via Grant NA07OAR4170517. Valentine 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, US Department of Energy, under Contract No. DE-AC05-00OR22725 and Contract No. DE-AC05-00OR22725 with UT-Battelle, LLC. Accordingly, the US Government retains a non-exclusive, royalty-free license to publish or reproduce the published form of this contribution, or allow others to do so, for US Government purposes. Our thanks also go to Dr Yangrong Ling for acquiring and preprocessing the HRPP products used in this study.

Funders	Funder number
NOAA Office of Atmospheric Research	NA07OAR4170517
Oak Ridge National Laboratory
US Department of Energy
National Aeronautics and Space Administration	NNS06AA98B
Office of Science
Advanced Scientific Computing Research

Access to Document

10.1080/01431161.2012.703345

Cite this

@article{94baea1c698246a3b9a94ca28e0cac07,

title = "A linear merging methodology for high-resolution precipitation products using spatiotemporal regression",

abstract = "Currently, the only viable option for a global precipitation product is the merger of several precipitation products from different modalities. In this article, we develop a linear merging methodology based on spatiotemporal regression. Four highresolution precipitation products (HRPPs), obtained through methods including the Climate Prediction Center's Morphing (CMORPH), Geostationary Operational Environmental Satellite-Based Auto-Estimator (GOES-AE), GOES-Based Hydro-Estimator (GOES-HE) and Self-Calibrating Multivariate Precipitation Retrieval (SCAMPR) algorithms, are used in this study. The merged data are evaluated against the Arkansas Red Basin River Forecast Center's (ABRFC's) ground-based rainfall product. The evaluation is performed using the Heidke skill score (HSS) for four seasons, from summer 2007 to spring 2008, and for two different rainfall detection thresholds. It is shown that the merged data outperform all the other products in seven out of eight cases. A key innovation of this machine learning method is that only 6% of the validation data are used for the initial training. The sensitivity of the algorithm to location, distribution of training data, selection of input data sets and seasons is also analysed and presented.",

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

year = "2012",

month = dec,

day = "20",

doi = "10.1080/01431161.2012.703345",

language = "English",

volume = "33",

pages = "7844--7867",

journal = "International Journal of Remote Sensing",

issn = "0143-1161",

publisher = "Taylor and Francis Group",

number = "24",

}

TY - JOUR

T1 - A linear merging methodology for high-resolution precipitation products using spatiotemporal regression

AU - Turlapaty, Anish C.

AU - Younan, Nicolas H.

AU - Anantharaj, Valentine G.

PY - 2012/12/20

Y1 - 2012/12/20

N2 - Currently, the only viable option for a global precipitation product is the merger of several precipitation products from different modalities. In this article, we develop a linear merging methodology based on spatiotemporal regression. Four highresolution precipitation products (HRPPs), obtained through methods including the Climate Prediction Center's Morphing (CMORPH), Geostationary Operational Environmental Satellite-Based Auto-Estimator (GOES-AE), GOES-Based Hydro-Estimator (GOES-HE) and Self-Calibrating Multivariate Precipitation Retrieval (SCAMPR) algorithms, are used in this study. The merged data are evaluated against the Arkansas Red Basin River Forecast Center's (ABRFC's) ground-based rainfall product. The evaluation is performed using the Heidke skill score (HSS) for four seasons, from summer 2007 to spring 2008, and for two different rainfall detection thresholds. It is shown that the merged data outperform all the other products in seven out of eight cases. A key innovation of this machine learning method is that only 6% of the validation data are used for the initial training. The sensitivity of the algorithm to location, distribution of training data, selection of input data sets and seasons is also analysed and presented.

AB - Currently, the only viable option for a global precipitation product is the merger of several precipitation products from different modalities. In this article, we develop a linear merging methodology based on spatiotemporal regression. Four highresolution precipitation products (HRPPs), obtained through methods including the Climate Prediction Center's Morphing (CMORPH), Geostationary Operational Environmental Satellite-Based Auto-Estimator (GOES-AE), GOES-Based Hydro-Estimator (GOES-HE) and Self-Calibrating Multivariate Precipitation Retrieval (SCAMPR) algorithms, are used in this study. The merged data are evaluated against the Arkansas Red Basin River Forecast Center's (ABRFC's) ground-based rainfall product. The evaluation is performed using the Heidke skill score (HSS) for four seasons, from summer 2007 to spring 2008, and for two different rainfall detection thresholds. It is shown that the merged data outperform all the other products in seven out of eight cases. A key innovation of this machine learning method is that only 6% of the validation data are used for the initial training. The sensitivity of the algorithm to location, distribution of training data, selection of input data sets and seasons is also analysed and presented.

UR - http://www.scopus.com/inward/record.url?scp=85010509977&partnerID=8YFLogxK

U2 - 10.1080/01431161.2012.703345

DO - 10.1080/01431161.2012.703345

M3 - Article

AN - SCOPUS:85010509977

SN - 0143-1161

VL - 33

SP - 7844

EP - 7867

JO - International Journal of Remote Sensing

JF - International Journal of Remote Sensing

IS - 24

ER -

A linear merging methodology for high-resolution precipitation products using spatiotemporal regression

Abstract

Funding

Access to Document

Other files and links

Fingerprint

Cite this