Canopy height mapping in the Western Himalayas, Pakistan: A deep learning approach using GEDI and Sentinel-2 fusion

The western Himalayas in Pakistan, characterized by a diverse range of conifer species at higher elevations, represent a critical biodiversity hotspot and habitat for numerous species. Accurate spatial assessments of canopy height are essential for improving estimates of aboveground biomass, carbon sequestration, and associated forest ecosystem services in this region. In this study, we estimated canopy heights in the western Himalayas in Pakistan using a U-Net CNN approach, fusing data from the Global Ecosystem Dynamics Investigation Mission (GEDI) with multi-band Sentinel-2 (S2) imagery. We produced a canopy height map at a 10 m resolution for 2020. To ensure accurate measurements across various canopy height groups, we implemented a stratified training approach that optimized the representation of GEDI data throughout the training, validation, and testing phases. We trained multiple models using varying thresholds and assigned different weights to taller trees to improve accuracy between different canopy height groups in the study region. Our best model achieved a Root Mean Square Error (RMSE) of 7.52 m and a Mean Absolute Error (MAE) of 5.71 m in the test set, significantly outperforming existing global canopy height models in this topographically complex region. We further validate our predictions against field inventory plots, achieving a coefficient of determination (R 2 ) of 0.49 for plots containing at least 15 trees. The resulting tree canopy height map, designated as the Western Himalaya Canopy Height Map (WHiCH Map), is publicly available. • A U-Net deep learning model maps canopy height in the Western Himalayas at 10 m resolution. • Sentinel-2 and GEDI fusion improves canopy height prediction in complex terrain. • A stratified training approach enhances accuracy across diverse canopy height groups. • Our model achieves RMSE of 7.52 m, outperforming state-of-the-art global models. • The Western Himalaya Canopy Height (WHiCH) Map, representing tree canopy height, is publicly available.

Authors

Institutions

Publication Details

Journal
International Journal of Applied Earth Observation and Geoinformation
Published
2026-01-06
DOI
https://doi.org/10.1016/j.jag.2025.105030
Primary Topic
Remote Sensing and LiDAR Applications
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Canopy height mapping in the Western Himalayas, Pakistan: A deep learning approach using GEDI and Sentinel-2 fusion

Nathan Jacobs, Subash Khanal, Alex Levering, Hammad Gilani et al.
International Journal of Applied Earth Observation and Geoinformation
Remote Sensing and LiDAR Applications
article

Canopy height mapping in the Western Himalayas, Pakistan: A deep learning approach using GEDI and Sentinel-2 fusion

Nathan Jacobs, Subash Khanal, Alex Levering, Hammad Gilani, Srikumar Sastry, Aayush Dhakal, Adeel Ahmad
article en

Abstract

The western Himalayas in Pakistan, characterized by a diverse range of conifer species at higher elevations, represent a critical biodiversity hotspot and habitat for numerous species. Accurate spatial assessments of canopy height are essential for improving estimates of aboveground biomass, carbon sequestration, and associated forest ecosystem services in this region. In this study, we estimated canopy heights in the western Himalayas in Pakistan using a U-Net CNN approach, fusing data from the Global Ecosystem Dynamics Investigation Mission (GEDI) with multi-band Sentinel-2 (S2) imagery. We produced a canopy height map at a 10 m resolution for 2020. To ensure accurate measurements across various canopy height groups, we implemented a stratified training approach that optimized the representation of GEDI data throughout the training, validation, and testing phases. We trained multiple models using varying thresholds and assigned different weights to taller trees to improve accuracy between different canopy height groups in the study region. Our best model achieved a Root Mean Square Error (RMSE) of 7.52 m and a Mean Absolute Error (MAE) of 5.71 m in the test set, significantly outperforming existing global canopy height models in this topographically complex region. We further validate our predictions against field inventory plots, achieving a coefficient of determination (R 2 ) of 0.49 for plots containing at least 15 trees. The resulting tree canopy height map, designated as the Western Himalaya Canopy Height Map (WHiCH Map), is publicly available. • A U-Net deep learning model maps canopy height in the Western Himalayas at 10 m resolution. • Sentinel-2 and GEDI fusion improves canopy height prediction in complex terrain. • A stratified training approach enhances accuracy across diverse canopy height groups. • Our model achieves RMSE of 7.52 m, outperforming state-of-the-art global models. • The Western Himalaya Canopy Height (WHiCH) Map, representing tree canopy height, is publicly available.

International Journal of Applied Earth Observation and GeoinformationVol. 146
University of the Punjab (PK), Washington University in St. Louis (US), Taylor Geospatial Institute, Vrije Universiteit Amsterdam (NL), National University of Sciences and Technology (PK)
Life in Land
Openalex Percentile: Top 96%
Remote Sensing and LiDAR Applications
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.