Landsat-8 OLI and Sentinel-2 MSI images from years 2015 and 2016, a 1:10,000 digital soil map and a large number of reference samples were used with a random forest machine learning implementation in GRASS GIS to construct a tree species map for the entire territory of Estonia (42,755 km2). Class probabilities for seven main tree species, an extra class for other species and probability of the forest cover not conforming to the forest definition were assigned for each pixel. Validation of dominant species distribution by area showed very strong correlation at county level both in state forests (R2 = 0.98) and in private forests (R2 = 0.93). Validation of tree species composition using harvester measurement data from 2,045 regeneration felling areas showed also very strong correlation (R2 = 0.75) with the measured values of the proportion of coniferous trees. There was some tendency to underestimate the proportion of more common species and overestimation was found for the species with smaller proportion in the mixture. The accuracy for the proportion of deciduous species that were present in a smaller number of reference observations was substantially smaller. Validation of the results by using data from 659 large sample plots from the database of the Estonian Network of Forest Research Plots and 3,002 small sample plots from the National Forest Inventory (NFI) data base confirmed the findings based on harvester data. The NFI data revealed also a decrease of estimation error with the increase of forest age. Cohen’s kappa index of agreement for main species for NFI sample plots with main species proportion equal to or greater than 75% decreased from 0.69 to 0.66 when observations with forests younger than 20 years were included in the comparison. Overall, the constructed map provides valuable data about tree species composition for the forests where no up to date inventory data are available or for the projects that require continuous cover of tree species data of known quality over the entire Estonia.

In 2007, three mature hemi-boreal stands were selected from Järvselja forest district, South-East Estonia to establish one-hectare-large test plots for the international inter-comparison experiment of radiation models (RAMI). All trees with a stem diameter at breast height greater than 4 cm were mapped and measured in the field. In summer 2019, the forests were inventoried again. Here we present a summary of changes that occurred in the forest structure – mainly growth and mortality. In the birch stand basal area G has increased from 23.3 m2 ha-1 to 28.2 m2 ha-1 in the upper layer and the number of trees N has decreased from 654 to 565 ha-1. In the upper layer of spruce stand G has increased from 30.9 m2 ha-1 to 35.4 m2 ha-1 and N has decreased from 774 to 724 ha-1 and N substantially decreased in the lower layers from 912 to 577 ha-1. In the pine stand G has increased from 28.3 m2 ha-1 to 29.1 m2 ha-1 and N decreased from 1116 to 971 ha-1. The three test stands can be used now for validating remote sensing data-based estimates of forest inventory variables at single tree level.

No abstract