Multitemporal Sentinel-1 and Sentinel-2 Images for Characterization and Discrimination of Young Forest Stands Under Regeneration in Norway

• Published in: IEEE journal of selected topics in applied earth observations and remote sensing Vol. 14; pp. 5049 - 5063
• Main Authors: Akbari, Vahid, Solberg, Svein, Puliti, Stefano
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 2021; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Backscatter; Classification; Coherence; Comparative analysis; Comparative studies; Correlation analysis; Cross correlation; Data; Detection; Discrimination; Forest management; Forest resources; Forest stands under regeneration; Forestry; Optical sensors; precommercial thinning (PCT); Radar; radar backscattering coefficient; random forest (RF) classification; Regeneration; Regeneration (biological); Remote sensing; repeat-pass interferometric coherence magnitude; Sentinel-1 (S-1); Sentinel-2 (S-2); Small mammals; spectral bands; Synthetic aperture radar; synthetic aperture radar (SAR); Vegetation; Norway
• ISSN: 1939-1404; 2151-1535; 2151-1535
• DOI: 10.1109/JSTARS.2021.3073101

There is a need for mapping of forest areas with young stands under regeneration in Norway, as a basis for conducting tending, or precommercial thinning (PCT), whenever necessary. The main objective of this article is to show the potential of multitemporal Sentinel-1 (S-1) and Sentinel-2 (S-2) data for characterization and detection of forest stands under regeneration. We identify the most powerful radar and optical features for discrimination of forest stands under regeneration versus other forest stands. A number of optical and radar features derived from multitemporal S-1 and S-2 data were used for the class separability and cross-correlation analysis. The analysis was performed on forest resource maps consisting of the forest development classes and age in two study sites from south-eastern Norway. Important features were used to train the classical random forest (RF) classification algorithm. A comparative study of performance of the algorithm was used in three cases: I) using only S-1 features, II) using only S-2 optical bands, and III) using combination of S-1 and S-2 features. RF classification results pointed to increased class discrimination when using S-1 and S-2 data in relation to S-1 or S-2 data only. The study shows that forest stands under regeneration in the height interval for PCT can be detected with a detection rate of 91% and F-1 score of 73.2% in case III as most accurate, while tree density and broadleaf fraction could be estimated with coefficient of determination (<inline-formula><tex-math notation="LaTeX">\text {R}^2</tex-math></inline-formula>) of about 0.70 and 0.80, respectively.