Accuracy and Consistency of Space-based Vegetation Height Maps for Forest Dynamics in Alpine Terrain

TL;DR

This study demonstrates that deep learning applied to Sentinel-2 satellite imagery can generate accurate, high-resolution vegetation height maps for Swiss forests, enabling more frequent monitoring of forest dynamics and change detection.

Contribution

The paper introduces a large-scale, annual vegetation height mapping approach using deep learning on Sentinel-2 data, improving temporal resolution for forest monitoring in Switzerland.

Findings

High correlation between model accuracy and terrain features.

Detection of small-scale changes as small as 250 m².

Successful identification of larger changes with an F1-score of 0.77.

Abstract

Monitoring and understanding forest dynamics is essential for environmental conservation and management. This is why the Swiss National Forest Inventory (NFI) provides countrywide vegetation height maps at a spatial resolution of 0.5 m. Its long update time of 6 years, however, limits the temporal analysis of forest dynamics. This can be improved by using spaceborne remote sensing and deep learning to generate large-scale vegetation height maps in a cost-effective way. In this paper, we present an in-depth analysis of these methods for operational application in Switzerland. We generate annual, countrywide vegetation height maps at a 10-meter ground sampling distance for the years 2017 to 2020 based on Sentinel-2 satellite imagery. In comparison to previous works, we conduct a large-scale and detailed stratified analysis against a precise Airborne Laser Scanning reference dataset. This stratified analysis reveals a close relationship between the model accuracy and the topology, especially slope and aspect. We assess the potential of deep learning-derived height maps for change detection and find that these maps can indicate changes as small as 250 $m^2$. Larger-scale changes caused by a winter storm are detected with an F1-score of 0.77. Our results demonstrate that vegetation height maps computed from satellite imagery with deep learning are a valuable, complementary, cost-effective source of evidence to increase the temporal resolution for national forest assessments.