Tree Height Estimation using Machine Learning and 3D Tomographic SAR - a case study in Northern Europe

Joseph Gallego Mejia; Grace Colverd; Laura Schade; Karol  Gonçalves; Jumpei Takami

doi:10.22541/essoar.173456557.74467579/v1

Back

Tree Height Estimation using Machine Learning and 3D Tomographic SAR - a case study in Northern Europe

Preprint

Open access

Tree Height Estimation using Machine Learning and 3D Tomographic SAR - a case study in Northern Europe

Joseph Gallego Mejia, Grace Colverd, Laura Schade, Karol Gonçalves and Jumpei Takami

ESS Open Archive

18 Dec 2024

DOI: https://doi.org/10.22541/essoar.173456557.74467579/v1

Files and links (1)

url

https://doi.org/10.22541/essoar.173456557.74467579/v1View

Preprint (Author's original) Open

Abstract

Tree height estimation is crucial for accurate biomass estimation and forest monitoring. Synthetic Aperture Radar (SAR) offers two products useful for tree height estimation: SLC (Single Look Complex) images and derived tomographic cubes. In this work, we present machine learning methods to predict forest height in two ways, directly from SLC images and from tomographic cubes, providing valuable context to the upcoming European Space Agency’s Biomass Satellite mission.

Metrics

10 Record Views

Details

Title: Tree Height Estimation using Machine Learning and 3D Tomographic SAR - a case study in Northern Europe
Creators: Joseph Gallego Mejia - Drexel University, Computer Science
Grace Colverd - University of Cambridge
Laura Schade
Karol Gonçalves - University of Lisbon
Jumpei Takami - United Nations Office for Outer Space Affairs
Publication Details: ESS Open Archive
Resource Type: Preprint
Language: English
Academic Unit: Computer Science
Other Identifier: 991022116573904721

Tree Height Estimation using Machine Learning and 3D Tomographic SAR - a case study in Northern Europe

Files and links (1)

Abstract

Metrics

Details

Drexel University Social media