摘要
Land cover changes (LCC) are an important component of Global Change. LCC can be described not only by its occurrence, but also by the land cover replacement, causal agent and change duration or recuperation. Nowadays, remote sensing offers the opportunity to assemble reliable time series, however this fails to make a characterization of LCC since the series represents dynamics due to the combination of several processes occurring simultaneously. In this article we proposed an approach to the study of LCC using wavelet transform (WT) and MODIS vegetation time series. Through this work we have demonstrated the capacity of this tool in order to recognize and characterize four different LLC documented in scientific publications, presenting the results divided in frequency scales as interannual, seasonal and rapid changes. The information decomposed in frequency allows the interpretation of each involved process without the interference of others. The uses of WT in an image time series give us the possibility of joining temporal and spatial dimension in a single raster. Layers generated with WT might be used to pattern recognition in LCC and to improve an image classification.
Land cover changes (LCC) are an important component of Global Change. LCC can be described not only by its occurrence, but also by the land cover replacement, causal agent and change duration or recuperation. Nowadays, remote sensing offers the opportunity to assemble reliable time series, however this fails to make a characterization of LCC since the series represents dynamics due to the combination of several processes occurring simultaneously. In this article we proposed an approach to the study of LCC using wavelet transform (WT) and MODIS vegetation time series. Through this work we have demonstrated the capacity of this tool in order to recognize and characterize four different LLC documented in scientific publications, presenting the results divided in frequency scales as interannual, seasonal and rapid changes. The information decomposed in frequency allows the interpretation of each involved process without the interference of others. The uses of WT in an image time series give us the possibility of joining temporal and spatial dimension in a single raster. Layers generated with WT might be used to pattern recognition in LCC and to improve an image classification.
