Neural network method to solve inverse problems for canopy radiative transfer models

Authors:
A. N. Kravchenko
Affiliations:
Space Research Institute, National Academy of Sciences of Ukraine and National Space Agency of Ukraine, Kyiv, Ukraine
Venue:
Cybernetics and Systems Analysis
Year:
2009

Citing 5
Cited 1

Quantitative Remote Sensing of Land Surfaces

Quantitative Remote Sensing of Land Surfaces
Inverse Problem Theory and Methods for Model Parameter Estimation

Inverse Problem Theory and Methods for Model Parameter Estimation
Pattern Recognition and Machine Learning (Information Science and Statistics)

Pattern Recognition and Machine Learning (Information Science and Statistics)
Data Assimilation: The Ensemble Kalman Filter

Data Assimilation: The Ensemble Kalman Filter
Water resource quality monitoring using heterogeneous data and high-performance computations

Cybernetics and Systems Analysis

Solving inverse problems by decomposition, classification and simple modeling

Information Sciences: an International Journal

Quantified Score

Hi-index	0.00

Visualization

Abstract

Vegetation parameter retrieval is considered as the inverse of modeling canopy radiative transfer. To solve this problem, a new computationally efficient method based on mixture density networks (MDNs) is proposed to estimate the errors of retrieved parameters for each given set of reflectances. The properties of neural networks of traditional architecture and MDNs are considered. The method is tested using a simple model and the PROSPECT leaf radiative transfer model and is validated against real data.