The use of regression tree method for Sentinel-2 satellite data to mapping percent tree cover in different forest types

Cilek A., Berberoglu S., Donmez C., Sahingoz M.

ENVIRONMENTAL SCIENCE AND POLLUTION RESEARCH, cilt.29, sa.16, ss.23665-23676, 2022 (SCI-Expanded) identifier identifier identifier

  • Yayın Türü: Makale / Tam Makale
  • Cilt numarası: 29 Sayı: 16
  • Basım Tarihi: 2022
  • Doi Numarası: 10.1007/s11356-021-17333-5
  • Dergi Adı: ENVIRONMENTAL SCIENCE AND POLLUTION RESEARCH
  • Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus, IBZ Online, ABI/INFORM, Aerospace Database, Aqualine, Aquatic Science & Fisheries Abstracts (ASFA), BIOSIS, CAB Abstracts, EMBASE, Environment Index, Geobase, MEDLINE, Pollution Abstracts, Veterinary Science Database, Civil Engineering Abstracts
  • Sayfa Sayıları: ss.23665-23676
  • Anahtar Kelimeler: Percent tree cover, Sentinel-2, Regression tree, Mediterranean and terrestrial transition environments, CARBON EMISSIONS, CANOPY COVER, DEFORESTATION, SURFACES, AREA
  • Çukurova Üniversitesi Adresli: Evet

Özet

Quantifying forest systems is of importance for ecological services and economic benefits in ecosystem models. This study aims to map the percent tree cover (PTC) of various forest stands in the Buyuk Menderes Basin, located in the western part of Turkey with different characteristics in the Mediterranean and Terrestrial transition regions Sentinel-2 data with 10-m spatial resolution. In recent years, some researches have been carried out in different fields to show the capabilities and potential of Sentinel-2 satellite sensors. However, the limited number of PTC researches conducted with Sentinel-2 images reveals the importance of this study. This study aimed to demonstrate reliable PTC data in landscape planning or ecosystem modeling by introducing an advanced approach with high spatial, spectral, and temporal resolution and more cost-effective. In this study, a regression tree algorithm, one of the popular machine learning techniques for ecological modeling, was used to estimate the tree cover's dependent variable based on high-resolution monthly metrics' spectral signatures. Six frames of TripleSat images were used as training data in the regression tree. Monthly Sentinel-2 bands and produced metrics including NDVI, LAI, fCOVER, MSAVI2, and MCARI were almost the first time used as predictor variables. Stepwise linear regression (SLR) was applied to select these predictor bands in the regression tree and a correlation coefficient of 0.83 was obtained. Result PTC maps were produced and the results were evaluated based on coniferous and broadleaf. The results were tested using high spatial resolution TripleSat images and higher model accuracy was determined in both forest types. The high correlation is due to the Sentinel 2 satellite's band characteristics and the metrics are directly related to the tree cover. As a result, the high-accuracy availability of the Sentinel2 satellite is seen to map the PTC on a regional scale, including complex forest types between the Mediterranean and terrestrial transition climates.