Scholarly record
USING SENTINEL 2 TIME SERIES FOR FOREST TREE SPECIES CLASSIFICATION. CASE STUDY: NE OF ROMANIA
Abstract
Forest tree species monitoring is important for forest management, habitat and biodiversity assessment, as well as carbon cycle estimation. Forest ecosystems provide important services to society, and sustainable management and adapted policies are essential to maintain their ecological and socio-economic functions. For implementing a good sustainable forest management it?s important to know about tree species distribution. To characterize forest was used during the time, field inventories who can provide timely and accurate estimates of forest resources, but this method is time-consuming. Remote sensing is a tool who can provide good results, can increase the area of analyses and enables the production of high-resolution forest maps, also give precious information about the distribution of forest resources. The main purpose of the paper is to classify the type of forest tree species using satellite images Sentinel 2 applying supervised classification. The analyses were carried out in an area located in NE of Romania with coordinates 47°19?08?N and 26°52?13?E, characterized by continental climate (hot dry summers and cold winters).The plateau characteristics, with extensive structural plateaus, derives from the geological composition formed by oolitic sandstone and limestone, with the maximum altitude of 450 m. Within the Valea Oii catchment, only Todiresti commune (4381 ha) has forest area, the total forest surface is 1450 ha (deciduous forest has 30.58 %, coniferous forest has 0.57 % and mixed forest has 0.87 %) and the total agricultural surface is 2500 ha. Sentinel 2 satellite images has an important potential for the improving the classification of the forest tree species because of multispectral bands with high spatial resolution. For this purpose, 15 satellite images Sentinel 2 were used, taking into account the spring, summer and autumn season of the forest tree species. These images were acquired over two year, from April to November 2018-2019, monitoring the changes into the forest, but also evaluating the tree species. Field data were then compared with remote sensing data in the form of vegetation indices, but also with Random Forest (RF) classification. Vegetation indices for the analysis were: Normalized Differentiation Vegetation Index (NDVI), Improved Vegetation Index (EVI2) and Leaf Area Index (LAI).
Publication Impact Profile
Publication details
References12
Lu M., Chen B., Liao X., Yue T., Yue H., Ren S., Li X, Nie Z., Xu B., Forest Types Classification Based on Multi-Source Data Fusion, Remote Sensing, 9, 1153, 2017.
Moser B., Temperli C., Schneiter G., and Wohlgemuth T., Potential shift in tree species composition after interaction of fire and drought in the Central Alps, European Journal of Forest Research, vol. 129, no. 4, pp. 625–633, 02 2010.
Persson M., Lindberg E., Reese H., Tree Species Classification with Multi-Temporal Sentinel-2 Data, Remote Sensing, 10, 1794, 2018
Ghosh A., Fassnacht F. E., Joshi P. K., Kochb B., A framework for mapping tree species combining hyperspectral and LiDAR data: Role of selected classifiers and sensor across three spatial scales. Int. J. Appl. Earth Obs. Geoinf., 26, 49–63, 2014
Ballanti L., Blesius L., Hines E., Kruse B., Tree species classification using hyperspectral imagery: A comparison of two classifiers. Remote Sensing, 8, 445, 2016.
Fassnacht F.E., Latifi H., Sterénczak K., Modzelewska A., Lefsky M., Waser L.T., Straub C., Ghosh A., Review of studies on tree species classification from remotely sensed data. Remote Sensing Environment, 186, pp 64–87, 2016.
Sheeren D., Fauvel, M., Josipovic V., Lopes M., Planque C., Willm J., Dejoux J.-F., Tree Species Classification in Temperate Forests Using Formosat-2 Satellite Image Time Series. Remote Sensing, 8,734, 2016.
Mellor, A. Haywood, S. Jones, P. Wilkes, Forest classification using random forest with multisource remote sensing and ancillary GIS data, 16th Australasian Remote Sensing and Photogrammetry Conference Proceedings, 2014.
Drusch M., Del Bello U., Carlier S., Colin O., Fernandez V., Gascon F., Hoersch B., Isola C., Laberinti P., Martimort, P. et al., Sentinel-2: ESA’s Optical High-Resolution Mission for GMES Operational Services. Remote Sensing Environment,120, pp 25–36, 2012.
Knorn J., Kuemmerle T., Volkerc R., Keeton W. S., Gancz V., Biri I. A., Svoboda M., Griffinths P., Hagatis A., Hostert A., Continued loss of temperate old-growth forests in the Romanian Carpathians despite an increasing protected area network, Environmental Conservation 40(2): 182–193, 2012
Nicu I. C., Hydrogeomorphic Risk Analysis Affecting Chalcolithic Archaeological Sites from Valea Oii Watershed, Northeastern Romania, Germany, pp 35-38, 2016.
Breiman L., Random Forest, Machine Learning, vol. 45, Issue 1, pp 5-32, 2001.
View or Download full articleAccess options
SWS access login
Login as SWS Scientific CommitteeLogin as SWS Scientific PartnerLogin as SWS AuthorAuthors and approved SWS contributors will read and export their own linked papers after identity matching by SWS profile, email and SGEM GlobalID.
For librarian assistance: [email protected]
Purchase Instant Access
- Article can be downloaded after successful payment.
- Article may be used according to SWS library access terms.
- Article cannot be redistributed.
