Responding to Large-Scale Forest Damage in an Alpine Environment with Remote Sensing, Machine Learning, and Web-GIS

Abstract

This paper reports a semi-automated workflow for detection and quantification of forest damage from windthrow in an Alpine region, in particular from the Vaia storm in October 2018. A web-GIS platform allows to select the damaged area by drawing polygons; several vegetation indices (VIs) are automatically calculated using remote sensing data (Sentinel-2A) and tested to identify the more suitable ones for quantifying forest damage using cross-validation with ground-truth data. Results show that the mean value of NDVI and NDMI decreased in the damaged areas, and have a strong negative correlation with severity. RGI has an opposite behavior in contrast with NDVI and NDMI, as it highlights the red component of the land surface. In all cases, variance of the VI increases after the event between 0.03 and 0.15. Understorey not damaged from the windthrow, if consisting of 40% or more of the total cover in the area, undermines significantly the sensibility of the VIs to detecting and predicting severity. Using aggregational statistics (average and standard deviation) of VIs over polygons as input to a machine learning algorithm, i.e., Random Forest, results in severity prediction with regression reaching a root mean square error (RMSE) of 9.96, on a severity scale of 0–100, using an ensemble of area averages and standard deviations of NDVI, NDMI, and RGI indices. The results show that combining more than one VI can significantly improve the estimation of severity, and web-GIS tools can support decisions with selected VIs. The reported results prove that Sentinel-2 imagery can be deployed and analysed via web-tools to estimate forest damage severity and that VIs can be used via machine learning for predicting severity of damage, with careful evaluation of the effect of understorey in each situation.

Natural Disturbances and Protection Forests: At the Cutting Edge of Remote Sensing Technologies for the Rapid Assessment of Protective Effects against Rockfall

“…These tools are a valid and well-established source of data for evaluating earth surface characteristics. Active sensors (e.g., laser scanner, radar) can provide useful 3D information on forest structures and are able to extract tree size and spatial arrangement [12], while passive sensors can be used to infer vegetation status and forest cover [13]. For example, active Synthetic Aperture Radar (SAR) sensors emit a polarized signal at wavelengths in the microwave range of the electromagnetic spectrum and record the backscattered intensity at different polarizations.…”

Inforsat: An Online Sentinel-2 Multi-Temporal Analysis Tool Set Using R Cran

“…All these solutions are key enabling technologies for Earth Observation. They have been applied by authors in the context of forest monitoring, in particular related to forest applications, like biomass estimation using different sensors (Pirotti et al, 2014), damage assessment from wind throw using ad-hoc indices from remote sensing data (Piragnolo et al, 2021) and comparing opendata sources to assess damaged areas (Laurin et al, 2020;Vaglio Laurin et al, 2016) or mapping wetlends with support of active remote sensing (LaRocque et al, 2020) or even to support spatialization of agricultural practices (Pagliacci et al, 2020).…”

Estimating VAIA Windstorm Damaged Forest Area in Italy Using Time Series Sentinel-2 Imagery and Continuous Change Detection Algorithms

“…Olmo et al [22] showed with a multitemporal analysis based on vegetation indices that, starting from April 2019, it was possible to observe a deviation of reflectance values for damaged and undamaged areas comparing to the years before the storm. Piragnolo et al [23] showed that the multitemporal analysis of vegetation indices calculated on the S2 imagery are useful to predict severity classes of damaged areas using aggregational statistics of VIs as input to random forest machine learning algorithm.…”

“…Many of these studies use dense Landsat or MODIS TS as input data [40,46], while, the use of S2 and CCDC algorithm to map forest areas damaged by windstorms is limited [37]. Many recent studies on VAIA windstorm underlined that S2 is adequate to detect windstorm since S2 program offers innovative features for forest remote sensing by combining high spatial resolution (i.e., 13 bands, from 0.443 to 2.190 µm with the visible (i.e., R, G, B,) and the near infrared bands at 10-m spatial resolution and four red-edge bands at 20-m spatial resolution), wide coverage and a quick revisit time (i.e., every 5 days after the launch of Sentinel-2B satellite in 2017) [15,18,22,23]. However, they considered only a small portion of the area hit by VAIA windstorm and no-ones provided an estimation of damaged area.…”