Multitemporal hyperspectral tree species classification in the Białowieża Forest World Heritage site

Abstract

Tree species composition maps derived from hyperspectral data have been found to be accurate but it is still \nunclear whether an optimal time window exists to acquire the images. Trees in temperate forests are subject \nto phenological changes that are species-specific and can have an impact on species recognition. Our study \nexamined the performance of a multitemporal hyperspectral dataset to classify tree species in the Polish part of \nthe Bialowie˙za Forest. We classified seven tree species including spruce (Picea abies (L.) H.Karst), pine (Pinus \nsylvestris L.), alder (Alnus glutinosa Gaertn.), oak (Quercus robur L.), birch (Betula pendula Roth), hornbeam \n(Carpinus betulus L.) and linden (Tilia cordata Mill.), using Support Vector Machines. We compared the results \nfor three data acquisitions—early and late summer (2–4 July and 24–27 August), and autumn (1–2 October) as \nwell as a classification based on an image stack containing all three acquisitions. Furthermore, the sizes (height \nand crown diameter) of misclassified and correctly classified trees of the same species were compared. The \nearly summer acquisition reached the highest accuracies with an Overall Accuracy (OA) of 83–94 per cent and \nKappa (κ) of 0.80–0.92. The classification based on the stacked multitemporal dataset resulted in slightly higher \naccuracies (84–94 per centOA and 0.81–0.92 κ). For some species, e.g. birch and oak, tree size differed notably for \ncorrectly and incorrectly classified trees.We conclude that implementing multitemporal hyperspectral data can \nimprove the classification result as compared with a single acquisition. However, the obtained accuracy of the \nmultitemporal image stack was in our case comparable to the best single-date classification and investing more \ntime in identifying regionally optimal acquisition windows may be worthwhile as long hyperspectral acquisitions \nare still sparse.