Forest Height Estimation Based on Sentinel-1 Interferometric Coherence and Meteorological Data

This work analyses the possibility of estimating forest tree height at high and low spatial resolution using Machine Learning (ML) models and multi-source Earth Observation (EO) data. The interferometric coherence along a digital elevation model and a land cover map is combined with meteorological data in a Random Forest model to estimate tree height in three different test sites. In the Pyrenees Mountains Northeastern Spain, in central Finland and the Northwest Territories of Canada. The results show how the combined information from these multiple sources complement each other to estimate the tree height with a relatively low error in an operational way, opening the possibility of further data fusion for improved results.