Publication Abstracts
Aires 2004
Aires, F., 2004: Neural network uncertainty assessment using Bayesian statistics with application to remote sensing: 1. Network weights. J. Geophys. Res., 109, D10303, doi:10.1029/2003JD004173.
Neural network techniques have proved successful for many inversion problems in remote sensing; however, uncertainty estimates are rarely provided. This study has three parts. In this first article, we present an approach to evaluate uncertainties (i.e., error bars and the correlation structure of these errors) of the neural network parameters, the so-called "synaptic weights", based on a Bayesian technique. In contrast to more traditional approaches based on "point estimation" of the neural network weights (i.e., only one set of weights is determined by the learning process), we assess uncertainties on such estimates to monitor the quality of the neural network model. Uncertainties of the network parameters are used in the following two papers to estimate uncertainties of the network output (companion paper 2) and of the network Jacobians (companion paper 3). These new theoretical developments are illustrated by applying them to the problem of retrieving surface skin temperature, microwave surface emissivities and integrated water vapor content from a combined analysis of microwave and infrared observations over land.
- Get PDF (300 kB)
- PDF documents require the free Adobe Reader or compatible viewing software to be viewed.
- Go to journal article webpage
Export citation: [ BibTeX ] [ RIS ]
BibTeX Citation
@article{ai03100m, author={Aires, F.}, title={Neural network uncertainty assessment using Bayesian statistics with application to remote sensing: 1. Network weights}, year={2004}, journal={Journal of Geophysical Research}, volume={109}, pages={D10303}, doi={10.1029/2003JD004173}, }
[ Close ]
RIS Citation
TY - JOUR ID - ai03100m AU - Aires, F. PY - 2004 TI - Neural network uncertainty assessment using Bayesian statistics with application to remote sensing: 1. Network weights JA - J. Geophys. Res. JO - Journal of Geophysical Research VL - 109 SP - D10303 DO - 10.1029/2003JD004173 ER -
[ Close ]