Estimation of physical variables from multichannel remotely sensed imagery using a neural network: Application to rainfall estimation

Kuo Lin Hsu, Hoshin Vijai Gupta, Xiaogang Gao, Soroosh Sorooshian

Research output: Contribution to journalArticle

134 Citations (Scopus)

Abstract

Satellite-based remotely sensed data have the potential to provide hydrologically relevant information about spatially and temporally varying physical variables. A methodology for estimating such variables from multichannel remotely sensed data is presented; the approach is based on a modified counterpropagation neural network (MCPN) and is both effective and efficient at building complex nonlinear input-output function mappings from large amounts of data. An application to high-resolution estimation of the spatial and temporal variation of surface rainfall using geostationary satellite infrared and visible imagery is presented. Test results also indicate that spatially and temporally sparse ground-based observations can be assimilated via an adaptive implementation of the MCPN method, thereby allowing on-line improvement of the estimates.

Original languageEnglish (US)
Pages (from-to)1605-1618
Number of pages14
JournalWater Resources Research
Volume35
Issue number5
DOIs
StatePublished - 1999

Fingerprint

neural networks
Rain
imagery
Neural networks
rain
Geostationary satellites
rainfall
temporal variation
spatial variation
geostationary satellite
Satellites
Infrared radiation
methodology
testing
method
test

ASJC Scopus subject areas

  • Aquatic Science
  • Environmental Science(all)
  • Environmental Chemistry
  • Water Science and Technology

Cite this

Estimation of physical variables from multichannel remotely sensed imagery using a neural network : Application to rainfall estimation. / Hsu, Kuo Lin; Gupta, Hoshin Vijai; Gao, Xiaogang; Sorooshian, Soroosh.

In: Water Resources Research, Vol. 35, No. 5, 1999, p. 1605-1618.

Research output: Contribution to journalArticle

@article{458ddf15bbf344049b1e79109d62ebdd,
title = "Estimation of physical variables from multichannel remotely sensed imagery using a neural network: Application to rainfall estimation",
abstract = "Satellite-based remotely sensed data have the potential to provide hydrologically relevant information about spatially and temporally varying physical variables. A methodology for estimating such variables from multichannel remotely sensed data is presented; the approach is based on a modified counterpropagation neural network (MCPN) and is both effective and efficient at building complex nonlinear input-output function mappings from large amounts of data. An application to high-resolution estimation of the spatial and temporal variation of surface rainfall using geostationary satellite infrared and visible imagery is presented. Test results also indicate that spatially and temporally sparse ground-based observations can be assimilated via an adaptive implementation of the MCPN method, thereby allowing on-line improvement of the estimates.",
author = "Hsu, {Kuo Lin} and Gupta, {Hoshin Vijai} and Xiaogang Gao and Soroosh Sorooshian",
year = "1999",
doi = "10.1029/1999WR900032",
language = "English (US)",
volume = "35",
pages = "1605--1618",
journal = "Water Resources Research",
issn = "0043-1397",
publisher = "American Geophysical Union",
number = "5",

}

TY - JOUR

T1 - Estimation of physical variables from multichannel remotely sensed imagery using a neural network

T2 - Application to rainfall estimation

AU - Hsu, Kuo Lin

AU - Gupta, Hoshin Vijai

AU - Gao, Xiaogang

AU - Sorooshian, Soroosh

PY - 1999

Y1 - 1999

N2 - Satellite-based remotely sensed data have the potential to provide hydrologically relevant information about spatially and temporally varying physical variables. A methodology for estimating such variables from multichannel remotely sensed data is presented; the approach is based on a modified counterpropagation neural network (MCPN) and is both effective and efficient at building complex nonlinear input-output function mappings from large amounts of data. An application to high-resolution estimation of the spatial and temporal variation of surface rainfall using geostationary satellite infrared and visible imagery is presented. Test results also indicate that spatially and temporally sparse ground-based observations can be assimilated via an adaptive implementation of the MCPN method, thereby allowing on-line improvement of the estimates.

AB - Satellite-based remotely sensed data have the potential to provide hydrologically relevant information about spatially and temporally varying physical variables. A methodology for estimating such variables from multichannel remotely sensed data is presented; the approach is based on a modified counterpropagation neural network (MCPN) and is both effective and efficient at building complex nonlinear input-output function mappings from large amounts of data. An application to high-resolution estimation of the spatial and temporal variation of surface rainfall using geostationary satellite infrared and visible imagery is presented. Test results also indicate that spatially and temporally sparse ground-based observations can be assimilated via an adaptive implementation of the MCPN method, thereby allowing on-line improvement of the estimates.

UR - http://www.scopus.com/inward/record.url?scp=0032917913&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0032917913&partnerID=8YFLogxK

U2 - 10.1029/1999WR900032

DO - 10.1029/1999WR900032

M3 - Article

AN - SCOPUS:0032917913

VL - 35

SP - 1605

EP - 1618

JO - Water Resources Research

JF - Water Resources Research

SN - 0043-1397

IS - 5

ER -