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.

As European Union member states – Latvia and Lithuania have changed their national height systems from Baltic Normal Height System 1977 to European Vertical Reference System realizations. Performing practical Global Navigation Satellite System (GNSS) measurements and obtained data mathematical processing, there is a possibility to calculate point height difference between GNSS data and data of 1st order levelling networks. The aim of the research is to gain insight for methodology development of geodetic point height testing using GNSS measurements. To achieve the goal following tasks are set: 1) perform GNSS measurements of first order levelling network in Latvia and Lithuania; 2) do data processing to get point ellipsoidal height and compare with the point normal height; 3) detect technically feasible accuracy of geoid model for precise height measurements with GNSS method within research area. Performing GNSS measurements at the same time in the territory of Latvia and Lithuania, the experience of mutual cross-border cooperation was accumulated. The results were adjusted with academic software package Bernese and were obtained point ellipsoidal and normal heights. The height measurement accuracy using GNSS method depends on geoid model accuracy and more precise results can be obtained increasing used geoid model accuracy to 1.5 to 2 cm.

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.

After height system replacement in Latvia, there is a transformation formula for point height difference theoretical value in any place of Latvia. Performing practical Global Navigation Satellite System (GNSS) measurements and obtained data mathematical processing, there is also a possibility to calculate point height difference, in this case – practical values. There were thirteen 1st class levelling network points selected in territory of Latvia and got the theoretical and practical values of them. As the result, it is possible to compare height differences between Baltic Normal Height System 1977 and Latvian Normal Height System 2000,5. The practical and theoretical values should coincide, but just 3 of selected geodetic points the height difference comparing practical and theoretical values is close to zero and point height difference of all measured points differs in 17 cm amplitudes indicating problems with transformation formula or need to improve geoid model.