Modeling Forest Canopy Cover: A Synergistic Use of Sentinel-2, Aerial Photogrammetry Data, and Machine Learning

Remote Sensing

卷:14

Verena C. Griess¹  Seyed Mohammad Moein Sadeghi²  Stelian Alexandru Borz²  Ali Asghar Darvishsefat³  Vahid Nasiri³  Hossein Arefi⁴ 

[1] Department of Environmental System Sciences, Institute of Terrestrial Ecosystems, ETH Zürich, 8092 Zurich, Switzerland;

[2] Department of Forest Engineering, Forest Management Planning and Terrestrial Measurements, Faculty of Silviculture and Forest Engineering, Transilvania University of Brasov, 500123 Brasov, Romania;

[3] Department of Forestry and Forest Economics, Faculty of Natural Resources, University of Tehran, Karaj 1417643184, Iran;

[4] Department of Technology, Mainz University of Applied Sciences, 55128 Mainz, Germany;

关键词: Sentinel-2;    UAV;    vegetation index;    forest canopy cover;    machine learning;    Hyrcanian forest;   

DOI  :  10.3390/rs14061453

来源: DOAJ

【 摘 要 】

Forest canopy cover (FCC) is an important ecological parameter of forest ecosystems, and is correlated with forest characteristics, including plant growth, regeneration, biodiversity, light regimes, and hydrological properties. Here, we present an approach of combining Sentinel-2 data, high-resolution aerial images, and machine learning (ML) algorithms to model FCC in the Hyrcanian mixed temperate forest, Northern Iran. Sentinel-2 multispectral bands and vegetation indices were used as variables for modeling and mapping FCC based on UAV ground truth to a wider spatial extent. Random forest (RF), support-vector machine (SVM), elastic net (ENET), and extreme gradient boosting (XGBoost) were the ML algorithms used to learn and generalize on the remotely sensed variables. Evaluation of variable importance indicated that vegetation indices including NDVI, NDVI-A, NDRE, and NDI45 were the dominant predictors in most of the models. Model accuracy estimation results showed that among the tested models, RF (R² = 0.67, RMSE = 18.87%, MAE = 15.35%) and ENET (R² = 0.63, RMSE = 20.04%, MAE = 16.44%) showed the best and the worst performance, respectively. In conclusion, it was possible to prove the suitability of integrating UAV-obtained RGB images, Sentinel-2 data, and ML models for the estimation of FCC, intended for precise and fast mapping at landscape-level scale.

【 授权许可】

Unknown