<?xml version="1.0" encoding="ISO-8859-1"?>
	<metadata ReferenceType="Conference Proceedings">
		<site>mtc-m16b.sid.inpe.br 802</site>
		<holdercode>{isadg {BR SPINPE} ibi 8JMKD3MGPCW/3DT298S}</holdercode>
		<author>Cintra, Rosangela Saher Correa,</author>
		<author>Silva, José Demísio Simões,</author>
		<affiliation>Instituto Nacional de Pesquisas Espaciais (INPE)</affiliation>
		<affiliation>Instituto Nacional de Pesquisas Espaciais (INPE)</affiliation>
		<title>Artificial Neural Network to estimate Integrated Water Vapor using satellite data from HSB sensor</title>
		<conferencename>International Conference on Southern Hemisphere Meteorology and Oceanography, 8 (ICSHMO).</conferencename>
		<editor>Vera, Carolina,</editor>
		<editor>Nobre, Carlos,</editor>
		<date>24-28 Apr. 2006</date>
		<publisheraddress>45 Beacon Hill Road, Boston, MA, USA</publisheraddress>
		<publisher>American Meteorological Society (AMS)</publisher>
		<conferencelocation>Foz do Iguaçu</conferencelocation>
		<keywords>integrated water vapor, satellite data, artificial neural network, brightness temperature, multilayer percepton.</keywords>
		<abstract>Artificial Neural Network (ANN)  is applied to estimate the Integrated Water Vapor (IWV) of atmosphere, using HSB (Humidy Sensor Brazil) channels data from AQUA satellite, and simulations of the brightness temperatures from RTTOV-7. The intention of HSB is to obtain information of the content of water vapor in the atmosphere, precipitation, and when it is together instruments, such as: AMSU-A (Advanced Microwave Sounding Unit-A) and AIRS (Atmospheric Infrared Sounder), also on board of the AQUA satellite, they allow to infer soundings of atmospheric profiles of temperature and moisture under conditions of clear and cloudy sky. The HSB is a sensor with the same characteristics of the sounder AMSU-B that is on board of the satellites of the series NOAA-KLM, then this method can applied with that data. This paper shows the ANN as a new method to estimate IWV, with supervised training of observations data from the RACCI/LBA experiment in Rondônia/Brazil, during period of September and October 2002.  The Total IWV is also compared against radiosonde data, where all of the results are in good agreement with RMS differences less than 4 mm and biases less than 1 mm. This method can also used to estimate the variability of distribution of water vapor in atmosphere through the on-line update training process. The total precipitable water in Kg/m2 is near to the integrated values of the profiles of absolute moisture of the radiosondes of the experiment RaCCI/LBA.. In Southern Hemisphere, there is a big disadvantage, because the space and temporary distribution of the observations is weak. This method allows the estimate of the IWV to connect straightly the temperature of brilliance with the quantity of water vapor (for a determined vertical profile of temperature). These observations are important in weather forecast, like observation of moisture field of initial conditions for the numerical models, through the Data Assimilation to obtain homogeneous fields of the analysis. Since the conventional observations for radiosonde offer quite limited space covering, particularly in the South America, then there is a method of estimate of water vapor in the atmosphere from satellite data, that it will improve the limitations of the meteorological observations of conventional stations.</abstract>
		<organization>American Meteorological Society (AMS)</organization>
		<type>Addressing gaps in SH observing systems</type>
		<secondarytype>PRE CI</secondarytype>
		<format>CD-ROM; On-line.</format>
		<size>360 KiB</size>
		<lastupdate>2006: cptec.inpe.br/walmeida/2003/ administrator</lastupdate>
		<metadatalastupdate>2018: cptec.inpe.br/walmeida/2003/ administrator {D 2006}</metadatalastupdate>
		<hostcollection>cptec.inpe.br/nobre/2005/ cptec.inpe.br/walmeida/2003/</hostcollection>
		<readpermission>allow from all</readpermission>