Mapping fallow lands, the forgotten land cover class

We proposed a new methodology based on NDVI time series autocorrelation values and machine learning algorithms to assess fallowing temporal patterns across rainfed agricultural areas that was tested in mainland Spain. We found that approximately half of rainfed agricultural areas were regularly cultivated (RC) and distributed mainly in the north- western Spain whereas lands with crop-fallow rotation patterns every two (CF-2) and three years (CF-3) were distributed across northeast, center and south of Spain. You can see the spatial distribution in the map viewer below.  Results were published in Recuero et al., 2019.

Posted in Artificial intelligence, Field data, Maps, Products, Remote sensing data, Satellite, Scientific findings, Soil conservation, Sustainable agriculture, Time series.

Leave a Reply

Your email address will not be published. Required fields are marked *