Country-wide Retrieval of Forest Structure From Optical and SAR Satellite Imagery With Deep Ensembles

TL;DR

This paper introduces a deep ensemble-based method to accurately map forest structure variables across Norway at 10-meter resolution using Sentinel satellite data, providing reliable uncertainty estimates for informed forest management.

Contribution

It is the first to apply Bayesian deep learning for dense, multi-variable forest structure prediction with uncertainty quantification from satellite imagery at country scale.

Findings

Normalized mean absolute errors between 11% and 15%.

Model generalizes well to unseen regions.

Provides Norway-wide forest structure maps.

Abstract

Monitoring and managing Earth's forests in an informed manner is an important requirement for addressing challenges like biodiversity loss and climate change. While traditional in situ or aerial campaigns for forest assessments provide accurate data for analysis at regional level, scaling them to entire countries and beyond with high temporal resolution is hardly possible. In this work, we propose a method based on deep ensembles that densely estimates forest structure variables at country-scale with 10-meter resolution, using freely available satellite imagery as input. Our method jointly transforms Sentinel-2 optical images and Sentinel-1 synthetic-aperture radar images into maps of five different forest structure variables: 95th height percentile, mean height, density, Gini coefficient, and fractional cover. We train and test our model on reference data from 41 airborne laser scanning missions across Norway and demonstrate that it is able to generalize to unseen test regions, achieving normalized mean absolute errors between 11% and 15%, depending on the variable. Our work is also the first to propose a variant of so-called Bayesian deep learning to densely predict multiple forest structure variables with well-calibrated uncertainty estimates from satellite imagery. The uncertainty information increases the trustworthiness of the model and its suitability for downstream tasks that require reliable confidence estimates as a basis for decision making. We present an extensive set of experiments to validate the accuracy of the predicted maps as well as the quality of the predicted uncertainties. To demonstrate scalability, we provide Norway-wide maps for the five forest structure variables.