Canopy Tree Height Estimation Using Quantile Regression: Modeling and Evaluating Uncertainty in Remote Sensing

TL;DR

This paper introduces a method using quantile regression to improve tree height estimation from satellite data by providing uncertainty quantification, enhancing ecological monitoring accuracy.

Contribution

It adapts existing models with minor modifications to produce calibrated uncertainty estimates, addressing a key limitation of point predictions in remote sensing.

Findings

Quantile regression improves uncertainty estimation in tree height models.

Model confidence decreases in complex terrain and heterogeneous vegetation.

The approach is compatible with existing satellite-based tree height models.

Abstract

Accurate tree height estimation is vital for ecological monitoring and biomass assessment. We apply quantile regression to existing tree height estimation models based on satellite data to incorporate uncertainty quantification. Most current approaches for tree height estimation rely on point predictions, which limits their applicability in risk-sensitive scenarios. In this work, we show that, with minor modifications of a given prediction head, existing models can be adapted to provide statistically calibrated uncertainty estimates via quantile regression. Furthermore, we demonstrate how our results correlate with known challenges in remote sensing (e.g., terrain complexity, vegetation heterogeneity), indicating that the model is less confident in more challenging conditions.