This paper discusses the usability of non-parametric knn (k-nearest neighbour) method to detect changes in forest areas from satellite images. Spot Xi images acquired 1999, main forest characteristics from field measured sample plots and data of conventional stand-wise forest inventory from the year 1988 were used to estimate the grids of following forest characteristics: mean age of main forest storey, diameter, basal area, height, volume per 1 ha, as well as the percentages of coniferous, soft and hard deciduous tree species. The differences of grids, created using stand-wise forest attributes from the 1988 inventory and estimated using the k-nearest neighbour methods were experimented to detect changes in the forest. 68.7-75.5% of areas, classified as the potential felling areas, were detected to be clear cut areas or young stands less than 15 years according to the data of stand-wise inventory of year 2003. Different settings for the methods investigated are evaluated, too.

Precision of the forest inventory still is one of the most important problems in the forestry nowadays. The aim of this research was to estimate the results of the combined forest inventory (CFI), using high spatial resolution aerial images in the planned areas of clear-cuts, comparing the results with the calipering and production files of harvesters. Testing of algorithms showed considerable difference in results between the CFI, forest inventory data and harvester production data. CFI results and production data had a close correlation with R2 =0.83. Comparing CFI calculated growing stock with production data, the average relative error amounted to 10.7%, which means the possibility for integration of these results into the forest inventory system. Comparing to CFI, there is a weak correlation between forest inventory and production data with R2 =0.34. The results indicate that LiDAR CFI technology can be used in the forecasting of the forest management, offering precise information about potential amount and economic value of assortments.

The most obvious application of satellite images in forestry areas and generating forests maps with particular emphasis on identifying temporarily non-forested areas and mapping forest clear-cuts. The aim of this paper was to investigate the influence of attributes describing forest clear-cut patch size, patch shape, and habitat conditions on classification results and map forest clear-cuts in Latvian and Estonian boundary area. The satellite images used were medium spatial resolution Landsat Thematic Mapper satellite images made in plain snow cover conditions in late winter. The boundary area was represented by Aluksne region in Latvia and by Voru County in Estonia. Clear -cut areas as changed areas in forests were discerned from non-changed areas with image differencing method that has proved itself as one of the most often used methods in land use and land cover change detection.