Salmon, BPOlivier, JCKleynhans, WWessels, Konrad JVan den Bergh, F2010-03-082010-03-082009-07Salmon, BP, Olivier, JC et al. 2009. Quest for automated land cover change detection using satellite time series data. IEEE International Geoscience and Remote Sensing Symposium (IGARSS), Cape Town, South Africa, 12-17 July 2009, pp 244-247978-1-4244-3395-7http://hdl.handle.net/10204/3978IEEE International Geoscience and Remote Sensing Symposium (IGARSS), Cape Town, South Africa, 12-17 July 2009This paper shows that a feedforward Multilayer Perceptron (MLP) operating over a temporal sliding window of multispectral time series MODerate-resolution Imaging Spectroradiometer (MODIS) satellite data is able to detect land cover change that was artificially introduced by concatenating time series belonging to different types of land cover. The method employs an iteratively retrained MLP that is a supervised method, and thus captures all local environmental patterns. Depending on the length of the temporal sliding window used in the short-term Fourier transform, an overall change detection accuracy of between 87.62% and 97.02% was achieved. It is shown that for this type of simulated land cover change, where land cover change was abrupt, a short-term FFT window of 18 months or less, using only the two NDVI spectral bands of MODIS data was sufficient to detect change reliably.enMLPFeedforward multilayer perceptronLand coverSatellites time seriesFeedforward neural networksMODIS dataMODerate-resolution imaging spectroradiometerRemote sensingGeosciencesConference PresentationSalmon, B., Olivier, J., Kleynhans, W., Wessels, K. J., & Van den Bergh, F. (2009). Quest for automated land cover change detection using satellite time series data. IEEE. http://hdl.handle.net/10204/3978Salmon, BP, JC Olivier, W Kleynhans, Konrad J Wessels, and F Van den Bergh. "Quest for automated land cover change detection using satellite time series data." (2009): http://hdl.handle.net/10204/3978Salmon B, Olivier J, Kleynhans W, Wessels KJ, Van den Bergh F, Quest for automated land cover change detection using satellite time series data; IEEE; 2009. http://hdl.handle.net/10204/3978 .TY - Conference Presentation AU - Salmon, BP AU - Olivier, JC AU - Kleynhans, W AU - Wessels, Konrad J AU - Van den Bergh, F AB - This paper shows that a feedforward Multilayer Perceptron (MLP) operating over a temporal sliding window of multispectral time series MODerate-resolution Imaging Spectroradiometer (MODIS) satellite data is able to detect land cover change that was artificially introduced by concatenating time series belonging to different types of land cover. The method employs an iteratively retrained MLP that is a supervised method, and thus captures all local environmental patterns. Depending on the length of the temporal sliding window used in the short-term Fourier transform, an overall change detection accuracy of between 87.62% and 97.02% was achieved. It is shown that for this type of simulated land cover change, where land cover change was abrupt, a short-term FFT window of 18 months or less, using only the two NDVI spectral bands of MODIS data was sufficient to detect change reliably. DA - 2009-07 DB - ResearchSpace DP - CSIR KW - MLP KW - Feedforward multilayer perceptron KW - Land cover KW - Satellites time series KW - Feedforward neural networks KW - MODIS data KW - MODerate-resolution imaging spectroradiometer KW - Remote sensing KW - Geosciences LK - https://researchspace.csir.co.za PY - 2009 SM - 978-1-4244-3395-7 T1 - Quest for automated land cover change detection using satellite time series data TI - Quest for automated land cover change detection using satellite time series data UR - http://hdl.handle.net/10204/3978 ER -