Use of Sentinel-2 Data to Improve Multivariate Tree Species Composition in a Forest Resource Inventory

Abstract

Aerial-photo interpreted inventories of forest resources, including tree species composition, are valuable in forest resource management, but are expensive to create and can be relatively inaccurate. Because of differences among tree species in their spectral properties and seasonal phenologies, it might be possible to improve such forest resource inventory information (FRI) by using it in concert with multispectral satellite information from multiple time periods. We used Sentinel-2 information from nine spectral bands and 12 dates within a two-year period to model multivariate percent tree species composition in >51,000 forest stands in the FRI of south-central Ontario, Canada. Accuracy of random forest (RF) and convolutional neural network (CNN) predictions were tested using species-specific basal area information from 155 0.25-ha field plots. Additionally, we created models using the Sentinel-2 information in concert with the field data and compared the accuracy of these models and the FRI-based models by use of basal areas from a second (13.7-ha) field data set. Based on average R2 values across species in the two field data sets, the Sentinel-FRI models outperformed the FRI, showing 1.5- and 1.7-fold improvements relative to the FRI for RF and 2.1- and 2.2-fold improvements for CNN (mean R2: 0.141–0.169 (FRI); 0.217–0.295 (RF); 0.307–0.352 (CNN)). Models created with the field data performed even better: improvements relative to the FRI were 2.1-fold for RF and 2.8-fold for CNN (mean R2: 0.169 (FRI); 0.356 (RF); 0.469 (CNN)). As predicted, R2 values between FRI- and field-trained predictions were higher than R2 values with the FRI. Of the 21 tree species evaluated, 8 relatively rare species had poor models in all cases. Our multivariate approach allowed us to use more FRI stands in model creation than if we had been restricted to stands dominated by single species and allowed us to map species abundances at higher resolution. It might be possible to improve models further by use of tree stem maps and incorporation of the effects of canopy disturbances.

Forest Semantic Segmentation Based on Deep Learning Using Sentinel-2 Images

“…Isaienkov et al (2021) presented a basic U-Net model for deforestation detection in the forest-steppe zone using Sentinel-2 imagery. Malcolm et al (2021) used Sentinel-2 imagery to model multivariate tree species composition in a forest stand in south-central Ontario, Canada. The accuracy of random forest (RF) and CNN estimates was tested using species-specific based area information.…”

Mapping with height and spectral remote sensing implies that environment and forest structure jointly constrain tree community composition in temperate coniferous forests of eastern Washington, United States

“…Challenges in tree species mapping highlight not only technical vegetation mapping difficulties but also fundamental uncertainties in factors controlling tree community patterns in managed and unmanaged landscapes. Recent regional and national tree community composition mapping efforts in USA and elsewhere may rely on spectral indices and seasonal dynamics in imagery from MODIS (e.g., Isaacson et al, 2012;Wilson et al, 2012;Zhang et al, 2018), Landsat (e.g., Ohmann et al, 2011;Adams et al, 2020), and Sentinel-2 (Hoscilo and Lewandowska, 2019;Malcolm et al, 2021) multispectral imagery. However, due to the fact that many forested areas contain multiple tree species that vary in occurrence and abundance at fine spatial scales, there is a need for finerscale remote sensing that can capture variation in forest composition and structure.…”