Identification of Heracleum sosnowskyi-invaded land using earth remote sensing data

Abstract

H. sosnowskyi (Heracleum Sosnowskyi) is a plant widespread both in Lithuania and other States that causes abundant problems. The damage caused by the population of the said plant is many-sided: it menaces the biodiversity of the land, poses risk to human health, and causes considerable economic losses. In course of searching for effective and complex measures of struggle against this invasive plant, it is very important to identify places and areas of growing of H. sosnowskyi, to carry out the detailed investigation and monitoring of the analysis of its spread and to avoid leaving this process to chance. In the paper, the results of the research where identification of territories covered with H. sosnowskyi (land classification) was accomplished upon applying the Remote Sensing Methodology are presented. The technology of remote sensing offers a practical and economical means to study vegetation cover changes, especially over large areas. Two categories of land cover classification were used for this study: supervised (human-guided) or unsupervised (calculated by software). When the supervised method was applied, the average wavelength of the spectrum of H. sosnowskyi was calculated for classification of the RGB image and according to it, the unsupervised classification by the program was accomplished. The combination of both methods of classification performed in steps allowed to obtain better results than using one.