Geoscience Reference
In-Depth Information
Fig. 1:
Three-layer backpropogation neural network.
In the processing steps of ANN for the temperature retrieval, the AMSU-
A 1d data consists of channels with a weighting function peaking below 10
hPa, i.e.
,
channels 1-12,15 and local satellite zenith angle has been considered
in the retrieval of the temperature profile. (i.e.
n
= 14). The local satellite zenith
angle has been included in the input nodes, and as a result it is not necessary to
adjust the measured brightness temperatures to the nadir direction. For the
hidden layer, a large range of neurons has been tried but the best performance
has been achieved in the range of 35 to 55 neurons. The best performance is
obtained by setting 45 neurons in the hidden layer. Similarly, the output layer
of the network contains 12 variables.
The ANN algorithm is developed here to retrieve the atmospheric
temperature profiles using AMSU-A observation at fixed pressure levels from
1000 to 100 hPa. For this purpose, the AMSU-A 1d data are matched with the
collocated NCEP analysis over the region 60° E to 90° E in longitude and from
02° N to 32° N in latitude. In the building of retrieval database, the NCEP
analysis is selected instead of radiosonde observation for the following reasons.
First, in the NCEP analysis, the grid values are adjusted for quality-controlled
radiosondes, therefore the radiosondes over the Indian regions have their
presence in NCEP analysis; second, unavailability of radiosondes over the
oceanic region and third, the importance of having a statistically robust set for
the training of the ANN, which requires a large number of profiles, much more
easily obtainable with GFS than with RAOBS (RAwinsonde Observation).
However, pairings in which either the NCEP data or satellite data from any
channel were missing were eliminated from the data sets.
Search WWH ::
Custom Search