Rainfall estimation from satellite infrared imagery using artificial neural networks

Persistent Link:
http://hdl.handle.net/10150/191209
Title:
Rainfall estimation from satellite infrared imagery using artificial neural networks
Author:
Hsu, Kuo-lin,1961-
Issue Date:
1996
Publisher:
The University of Arizona.
Rights:
Copyright © is held by the author. Digital access to this material is made possible by the University Libraries, University of Arizona. Further transmission, reproduction or presentation (such as public display or performance) of protected items is prohibited except with permission of the author.
Abstract:
Infrared (IR) imagery collected by geostationary satellites provides useful information about the dirunal evolution of cloud systems. These JR images can be analyzed to indicate the location of clouds as well as the pattern of cloud top temperatures (Tbs). During the past several decades, a number of different approaches for estimation of rainfall rate (RR) from Tb have been explored and concluded that the Tb-RR relationship is (1) highly nonlinear, and (2) seasonally and regionally dependent. Therefore, to properly model the relationship, the model must be able to: (1) detect and identify a non-linear mapping of the Tb-RR relationship; (2) Incorporate information about various cloud properties extracted from IR image; (3) Use feedback obtained from RR observations to adaptively adjust to seasonal and regional variations; and (4) Effectively and efficiently process large amounts of satellite image data in real-time. In this study, a kind of artificial neural network (ANN), called Modified Counter Propagation Network (MCPN), that incorporates these features, has been developed. The model was calibrated using the data around the Japanese Islands provided by the Global Precipitation Climatology Project (GPCP) First Algorithm Intercompari son Project (AIP-I). Validation results over the Japanese Islands and Florida peninsula show that by providing limited ground-truth observation, the MCPN model is effective in monthly and hourly rainfall estimation. Comparison of results from MCPN model and GOES Precipitation Index (GPI) approach is also provided in the study.
Type:
Dissertation-Reproduction (electronic); text
Keywords:
Hydrology.; Rain and rainfall -- Measurement.; Precipitation forecasting.; Infrared imaging.; Neural networks (Computer science)
Degree Name:
Ph. D.
Degree Level:
doctoral
Degree Program:
Hydrology and Water Resources; Graduate College
Degree Grantor:
University of Arizona
Committee Chair:
Sorooshian, Soroosh

Full metadata record

DC FieldValue Language
dc.language.isoenen_US
dc.titleRainfall estimation from satellite infrared imagery using artificial neural networksen_US
dc.creatorHsu, Kuo-lin,1961-en_US
dc.contributor.authorHsu, Kuo-lin,1961-en_US
dc.date.issued1996en_US
dc.publisherThe University of Arizona.en_US
dc.rightsCopyright © is held by the author. Digital access to this material is made possible by the University Libraries, University of Arizona. Further transmission, reproduction or presentation (such as public display or performance) of protected items is prohibited except with permission of the author.en_US
dc.description.abstractInfrared (IR) imagery collected by geostationary satellites provides useful information about the dirunal evolution of cloud systems. These JR images can be analyzed to indicate the location of clouds as well as the pattern of cloud top temperatures (Tbs). During the past several decades, a number of different approaches for estimation of rainfall rate (RR) from Tb have been explored and concluded that the Tb-RR relationship is (1) highly nonlinear, and (2) seasonally and regionally dependent. Therefore, to properly model the relationship, the model must be able to: (1) detect and identify a non-linear mapping of the Tb-RR relationship; (2) Incorporate information about various cloud properties extracted from IR image; (3) Use feedback obtained from RR observations to adaptively adjust to seasonal and regional variations; and (4) Effectively and efficiently process large amounts of satellite image data in real-time. In this study, a kind of artificial neural network (ANN), called Modified Counter Propagation Network (MCPN), that incorporates these features, has been developed. The model was calibrated using the data around the Japanese Islands provided by the Global Precipitation Climatology Project (GPCP) First Algorithm Intercompari son Project (AIP-I). Validation results over the Japanese Islands and Florida peninsula show that by providing limited ground-truth observation, the MCPN model is effective in monthly and hourly rainfall estimation. Comparison of results from MCPN model and GOES Precipitation Index (GPI) approach is also provided in the study.en_US
dc.description.notehydrology collectionen_US
dc.typeDissertation-Reproduction (electronic)en_US
dc.typetexten_US
dc.subjectHydrology.en_US
dc.subjectRain and rainfall -- Measurement.en_US
dc.subjectPrecipitation forecasting.en_US
dc.subjectInfrared imaging.en_US
dc.subjectNeural networks (Computer science)en_US
thesis.degree.namePh. D.en_US
thesis.degree.leveldoctoralen_US
thesis.degree.disciplineHydrology and Water Resourcesen_US
thesis.degree.disciplineGraduate Collegeen_US
thesis.degree.grantorUniversity of Arizonaen_US
dc.contributor.chairSorooshian, Sorooshen_US
dc.contributor.committeememberShuttleworth, Jamesen_US
dc.contributor.committeememberDuckstein, Lucienen_US
dc.contributor.committeememberSzidarovszky, Ferencen_US
dc.identifier.oclc222035512en_US
All Items in UA Campus Repository are protected by copyright, with all rights reserved, unless otherwise indicated.