VibrantSR: Sub-Meter Canopy Height Models from Sentinel-2 Using Generative Flow Matching

TL;DR

VibrantSR is a generative super-resolution framework that estimates high-resolution canopy height models from Sentinel-2 satellite imagery, enabling consistent, large-scale forest monitoring and carbon accounting.

Contribution

It introduces a novel generative super-resolution method for canopy height estimation from Sentinel-2 data, outperforming existing satellite benchmarks and enabling scalable forest monitoring.

Findings

Achieves 4.39 m MAE for canopy heights >= 2 m

Outperforms Meta, LANDFIRE, and ETH satellite benchmarks

Enables operational forest monitoring at continental scales

Abstract

We present VibrantSR (Vibrant Super-Resolution), a generative super-resolution framework for estimating 0.5 meter canopy height models (CHMs) from 10 meter Sentinel-2 imagery. Unlike approaches based on aerial imagery that are constrained by infrequent and irregular acquisition schedules, VibrantSR leverages globally available Sentinel-2 seasonal composites, enabling consistent monitoring at a seasonal-to-annual cadence. Evaluated across 22 EPA Level 3 eco-regions in the western United States using spatially disjoint validation splits, VibrantSR achieves a Mean Absolute Error of 4.39 meters for canopy heights >= 2 m, outperforming Meta (4.83 m), LANDFIRE (5.96 m), and ETH (7.05 m) satellite-based benchmarks. While aerial-based VibrantVS (2.71 m MAE) retains an accuracy advantage, VibrantSR enables operational forest monitoring and carbon accounting at continental scales without reliance on costly and temporally infrequent aerial acquisitions.