Files and links (1)
Published VersionCC BY V4.0, Open Access
Journal article
Improving forest loss mapping in Nepal using LandTrendr time-series and machine learning
Remote Sensing Applications: Society and Environment, Vol.41, pp.1-22
2026
Abstract
Understanding forest disturbances is essential for effective conservation strategies. Given Nepal's complex geography and forest ecology, change detection using Remote Sensing remains challenging, with limited time-series studies. This study introduces an enhanced LandTrendr (LT) workflow to improve forest loss mapping using medium-resolution imagery and machine learning. The approach includes: a) a Vision Transformers model (LiteForest-ViT) for semi-automated forest cover mask using Landsat 5, b) masking terrain shadows, c) ensemble of 7 spectral indices: NBR (Normalized Burn Ratio), NDVI (Normalized Difference Vegetation Index), TCA (Tasseled Cap Angle), TCB (Tasseled Cap Brightness), TCG (Tasseled Cap Greenness), EVI (Enhanced Vegetation Index), TCW (Tasseled Cap Wetness) with 6 LT-derived metrics for Random Forest (RF) and eXtreme Gradient Boosting (XGBoost) classification, d) expert-weighted district-level model selection tailored to regional heterogeneity, e) integration of multiple platforms for seamless processing, and f) MODIS-derived snow uncertainty loss estimation. The study spans (1995–2024) across Karnali, Bagmati, and Darchula. Results indicate RF edged XGBoost in the High Mountains and Himalayas, while XGBoost did better in the Siwalik and Middle Mountains. NBR was the most influential index regardless of model classifier and region. The algorithm achieved 0.90 overall accuracy, 0.74 kappa statistics, and 0.93 F1-score, exceeding GFC (Global Forest Change) and REDD + AI (CTrees) benchmarks. Overall, 7870 ha of forest loss were detected, where ∼165 ha accounted for snow-impacted uncertain loss. While loss has decreased, continued disturbance underscores the significance of our findings to support REDD+ (Reducing Emissions from Deforestation and Forest Degradation) in the region.
Details
- Title
- Improving forest loss mapping in Nepal using LandTrendr time-series and machine learning
- Authors
- Sakar Dhakal - Tribhuvan UniversityKamal Raj Aryal - University of the Sunshine CoastUttam Babu Shrestha - Global Institute for Interdisciplinary Studies (Nepal)Hari Adhikari (Corresponding Author) - University of Helsinki
- Publication details
- Remote Sensing Applications: Society and Environment, Vol.41, pp.1-22
- Publisher
- Elsevier BV
- Date published
- 2026
- DOI
- 10.1016/j.rsase.2025.101864
- ISSN
- 2352-9385
- Copyright note
- © 2026 The Authors. Published by Elsevier B.V. This is an open access article under the CC BY license (http://creativecommons.org/licenses/by/4.0/).
- Data Availability
- All the datasets used are publicly available. All the preprocessing and analysis were done using openly available environments such as Google Colab, LT-GEE, geemap, and Visual Studio Code, except ArcGIS. The code repository for newly integrated workflows will be made publicly available after publication.
- Grant note
- This research was funded by the Forest Research and Training Center (FRTC), Karnali province, Government of Nepal.
- Organisation Unit
- School of Science, Technology and Engineering
- Language
- English
- Record Identifier
- 991214173402621
- Output Type
- Journal article
Metrics
1 Record Views
InCites Highlights
These are selected metrics from InCites Benchmarking & Analytics tool, related to this output
- Collaboration types
- Domestic collaboration
- International collaboration
- Web Of Science research areas
- Environmental Sciences
- Remote Sensing
UN Sustainable Development Goals (SDGs)
This output has contributed to the advancement of the following goals:
Source: InCites