Airborne laser scanning for the identification of boreal forest site types

Boreal forests site types are used to assess the growth potential of the forests and therefore provide important inventory information. A new approach is proposed here for the site quality assessment of mature forests using airborne laser scanner (ALS) data and the k-NN classifier. Both the echo z-value and the intensity value percentiles of different echo types of ALS data were used in the analysis. The data comprised 274 forest stands of varying sizes belonging to five forest site types varying from very fertile to poor forests in the Koli National Park, Finland. The best overall classification accuracy of all the forest site types achieved was 58.0 %, and for a single class 73%. It is concluded that this ALS-based data analysis technique is applicable to the detection of boreal forests site types in large-scale forest inventories.