Identification of forests on post-agricultural land
Identification of forests on post-agricultural land on a national scale on the basis of archival and modern satellite data and detection of weakened stands on the basis of satellite spectral indicators
Funded by: Dyrekcja Generalna Lasów Państwowych (DGLP)
The subject of project is to perform the research on the identification of forests on former farmland based on available satellite datasets in Poland. It is a continuation of a pilot project that ended in 2020.
The forest cover in the 1960s was developed by the expert manual interpretation based on the satellite images of the CORONA program. In case of mapping forests extent in later periods, a modern classification method with the use of machine learning algorithms was applied, using not only static classifiers, but also deep learning. The obtained results confirmed the high accuracy of the classification models. Based on the digital maps of forest cover and forest changes, the identification of forests on post-agricultural or other non-forest land was performed. A spatio-temporal analysis allowed to determine not only the location and area of post-agricultural forests, but also to indicate in which period of time they were established.
The CORONA images proofed to the especially valuable for the detection of the forest on post-agricultural land. Among the analysed data, the Landsat MSS images showed to have the lowest usefulness in forest mapping. The Landsat 5 and 7 data series from 1990 and 2000 were comparable in quality. The Sentinel-2 data, due to their high spatial, spectral and temporal resolution as well as a wide swath, are particularly valuable for forest and forest change mapping, and monitoring the forest condition at local, regional and national scale.