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.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
F. Kogan, R. Stark, A. Gitelson, et al., “Derivation of pasture biomass in Mongolia from AVHRR-based vegetation health indices,” Int. J. Remote Sens., 25, No. 14, 2889–2896 (2004).
A. Richardson, S. Duigan, and G. Berlyn, “An evaluation of noninvasive methods to estimate foliar chlorophyll content,” New Phytologist, 153, No. 1, 185–194 (2002).
N. N. Kussul’, N. I. Il’in, S. V. Skakun, and A. N. Lavrenyuk, “Estimating the state of vegetation and predicting the productivity of winter crops in Ukraine using satellite data,” in: Intern. Book Series Decision Making and Business Intelligence, Strategies and Techniques, No. 3 (2008), pp. 103–109.
N. N. Kussul’, A. Yu. Shelestov, S. V. Skakun, and A. N. Kravchenko, Intelligent Computations in Processing Earth Observation Data [in Russian], Naukova Dumka, Kyiv (2007).
A. N. Kravchenko, N. N. Kussul’, E. A. Lupyan, et al., “Water resource quality monitoring using heterogeneous data and high-performance computations,” Cybern. Syst. Analysis, 44, No. 4, 616–624 (2008).
G. Evensen, Data Assimilation: The Ensemble Kalman Filter, Springer, Berlin (2006).
N. Kussul, A. Shelestov, S. Skakun, and O. Kravchenko, “Data assimilation technique for flood monitoring and prediction,” Int. J. Inform. Theory Appl., 15, No. 1, 76–84 (2008).
S. Liang, Quantitative Remote Sensing of Land Surfaces, Wiley, New York (2004).
F. Baret and S. Buis, “Estimating canopy characteristics from remote sensing observations: review of methods and associated problems,” in: S. Liang (ed.), Advances in Land Remote Sensing, Springer, Dordrecht (2008), pp. 173–201.
S. Jacquemoud and F. Baret, “PROSPECT: A model of leaf optical properties spectra,” Remote Sens. of Env., 34, No. 2, 75–91 (1990).
J. B. Feret, C. François, G. P. Asner, et al., “PROSPECT-4 and 5: Advances in the leaf optical properties model separating photosynthetic pigments,” Remote Sens. of Env., 112, No. 6, 3030–3043 (2008).
T. Dawson, P. Curran, and S. Plummer, “LIBERTY — modelling the effects of leaf biochemical concentration on reflectance spectra,” Remote Sens. of Env., 65, No. 1, 50–60 (1998).
W. Verhoef, “Light scattering by leaf layers with application to canopy reflectance modeling: the SAIL model,” Remote Sens. of Env., 16, No. 2, 125–141 (1984).
C. Bacour, F. Baret, D. Béal, M. Weiss, and K. Pavageau, “Neural network estimation of LAI, fAPAR, fCover and LAIxCab, from top of canopy MERIS reflectance data: Principles and validation,” Remote Sens. of Env., 105, No. 4, 313–325 (2006).
E. F. Vermote, N. Z. El Saleous, and C. O. Justice, “Atmospheric correction of MODIS data in the visible to middle infrared: First results,” Remote Sens. of Env., 83, No. 1, 97–111 (2002).
M. Verstraete and B. Pinty, “Designing optimal spectral indexes for remote sensing applications,” IEEE Trans. Geosci. Remote Sens., 34, No. 5, 1254–1265 (1996).
T. N. Carlson and D. A. Ripley, “On the relation between NDVI, fractional vegetation cover, and leaf area index,” Remote Sens. of Env., 62, No. 3, 241–252 (1998).
F. Baret and G. Guyot, “Potentials and limits of vegetation indexes for LAI and APAR assessment,” Remote Sens. of Env., 35, No. 2, 161–173 (1991).
B. C. Gao, “NDWI — a normalized difference water index for remote sensing of vegetation liquid water from space,” Remote Sens. of Env., 58, No. 3, 257–266 (1996).
P. Ceccato, N. Gobron, S. Flasse, et al., “Designing a spectral index to estimate vegetation water content from remote sensing data. Part 1. Theoretical approach,” Remote Sens. of Env., 82, No. 2, 188–197 (2002).
A. Tarantola, Inverse Problem Theory and Methods for Model Parameter Estimation, SIAM, Philadelphia (2005).
M. Weiss, F. Baret, R. Myneni, et al., “Investigation of a model inversion technique for the estimation of crop characteristics from spectral and directional reflectance data,” Agronomie, 20, No. 1, 3–22 (2000).
Y. Knyazikhin, J. V. Martonchik, R. B. Myneni, et al., “Synergistic algorithm for estimating vegetation canopy leaf area index and fraction of absorbed photosynthetically active radiation from MODIS and MISR data,” J. Geophys. Res., 103, 32257–32274 (1998).
B. Combal, F. Baret, M. Weiss, et al., “Retrieval of canopy biophysical variables from bidirectional reflectance using prior information to solve the ill-posed inverse problem,” Remote Sens. of Env., 84, No. 1, 1–15 (2002).
Z. Qingyuan, X. Xiangming, B. Braswell, et al., “Estimating light absorption by chlorophyll, leaf and canopy in a deciduous broadleaf forest using MODIS data and a radiative transfer model,” Remote Sens. of Env., 99, No. 3, 357–371 (2005).
C. Bishop, Pattern Recognition and Machine Learning, Springer, New York (2006).
Author information
Authors and Affiliations
Corresponding author
Additional information
The paper is supported by the joint project of the Science and Technology Center in Ukraine (STCU) and National Academy of Sciences of Ukraine (NASU), “Grid Technologies for Multi-Source Data Integration” (No. 4928).
Translated from Kibernetika i Sistemnyi Analiz, No. 3, pp. 159–172, May–June 2009. Original article submitted January 29, 2009.
Rights and permissions
About this article
Cite this article
Kravchenko, A.N. Neural network method to solve inverse problems for canopy radiative transfer models. Cybern Syst Anal 45, 477–488 (2009). https://doi.org/10.1007/s10559-009-9106-4
Received:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10559-009-9106-4