Input pattern according to standard deviation of backpropagation neural network: Influence on accuracy of soil moisture retrieval

The accuracy of an Artificial Neural Network (ANN) depends on the representativeness of the data used to train it. Although it is known that an ANN will function well as long as the pattern of the input data is similar to the testing data, there has been no research on the effect of data "simil...

Full description

Bibliographic Details
Main Authors: Chai, S., Veenendaal, Bert, West, Geoff, Walker, J.
Format: Conference Paper
Published: 2008
Online Access:http://hdl.handle.net/20.500.11937/41405
_version_ 1848756136980774912
author Chai, S.
Veenendaal, Bert
West, Geoff
Walker, J.
author_facet Chai, S.
Veenendaal, Bert
West, Geoff
Walker, J.
author_sort Chai, S.
building Curtin Institutional Repository
collection Online Access
description The accuracy of an Artificial Neural Network (ANN) depends on the representativeness of the data used to train it. Although it is known that an ANN will function well as long as the pattern of the input data is similar to the testing data, there has been no research on the effect of data "similarity" on the accuracy of the network outputs. In this paper, an ANN model is used to retrieve soil moisture from the H- and V-polarized brightness temperature obtained. The research discussed in this paper is focused on the standard deviation of the data used for training and testing of the ANN. It is shown that similarity in standard deviation is a good indicator to choose representative training and testing data set. By doing this, the accuracy of retrieval increases from around 22% volume/volume (v/v) of Root Mean Square Error (RMSE) to around 2%(v/v). ©2008 IEEE.
first_indexed 2025-11-14T09:07:25Z
format Conference Paper
id curtin-20.500.11937-41405
institution Curtin University Malaysia
institution_category Local University
last_indexed 2025-11-14T09:07:25Z
publishDate 2008
recordtype eprints
repository_type Digital Repository
spelling curtin-20.500.11937-414052017-09-13T14:12:16Z Input pattern according to standard deviation of backpropagation neural network: Influence on accuracy of soil moisture retrieval Chai, S. Veenendaal, Bert West, Geoff Walker, J. The accuracy of an Artificial Neural Network (ANN) depends on the representativeness of the data used to train it. Although it is known that an ANN will function well as long as the pattern of the input data is similar to the testing data, there has been no research on the effect of data "similarity" on the accuracy of the network outputs. In this paper, an ANN model is used to retrieve soil moisture from the H- and V-polarized brightness temperature obtained. The research discussed in this paper is focused on the standard deviation of the data used for training and testing of the ANN. It is shown that similarity in standard deviation is a good indicator to choose representative training and testing data set. By doing this, the accuracy of retrieval increases from around 22% volume/volume (v/v) of Root Mean Square Error (RMSE) to around 2%(v/v). ©2008 IEEE. 2008 Conference Paper http://hdl.handle.net/20.500.11937/41405 10.1109/IGARSS.2008.4779087 restricted
spellingShingle Chai, S.
Veenendaal, Bert
West, Geoff
Walker, J.
Input pattern according to standard deviation of backpropagation neural network: Influence on accuracy of soil moisture retrieval
title Input pattern according to standard deviation of backpropagation neural network: Influence on accuracy of soil moisture retrieval
title_full Input pattern according to standard deviation of backpropagation neural network: Influence on accuracy of soil moisture retrieval
title_fullStr Input pattern according to standard deviation of backpropagation neural network: Influence on accuracy of soil moisture retrieval
title_full_unstemmed Input pattern according to standard deviation of backpropagation neural network: Influence on accuracy of soil moisture retrieval
title_short Input pattern according to standard deviation of backpropagation neural network: Influence on accuracy of soil moisture retrieval
title_sort input pattern according to standard deviation of backpropagation neural network: influence on accuracy of soil moisture retrieval
url http://hdl.handle.net/20.500.11937/41405