Non-linear mixture modelling without end-members using an artificial neural network

G. M. Foody, R. M. Lucas, P. J. Curran, M. Honzak

Research output: Contribution to journalArticlepeer-review

148 Citations (SciVal)


Many methods of analysing remotely sensed data assume that pixels are pure, and so a failure to accommodate mixed pixels may result in signi® cant errors in data interpretation and analysis. The analysis of data containing a large proportion of mixed pixels may therefore bene® t from the decomposition of the pixels into their component parts. Methods for unmixing the composition of pixels have been used in a range of studies and have often increased the accuracy of the analyses. However, many of the methods assume linear mixing and require end-member spectra, but mixing is often non-linear and end-member spectra are di� cult to obtain. In thispaper,an alternative approach to unmixing thecomposition of image pixels, which makes no assumptions about the nature of the mixing and does not require end-member spectra, is presented. The method is based on an arti® cial neural network (ANN) and shown in a case study to provide accurate estimates of sub-pixel land cover composition. The results of this case study showed that accurate estimates of the proportional cover of a class and its areal extent may be made. It was also shown that there was a tendency for the accuracy of the unmixing to increase with the complexity of the network and the intensity of training. The results indicate the potential to derive accurate information from remotely sensed data sets dominated by mixed pixels.
Original languageEnglish
Pages (from-to)937-953
Number of pages17
JournalInternational Journal of Remote Sensing
Issue number4
Publication statusPublished - 25 Nov 2010
Externally publishedYes


Dive into the research topics of 'Non-linear mixture modelling without end-members using an artificial neural network'. Together they form a unique fingerprint.

Cite this