Improved mapping of highland bamboo forests using Sentinel-2 time series and machine learning in Google Earth Engine

Recent advances in the application of spectral bands from satellite observations and machine learning algorithms (MLA) in the Google Earth Engine (GEE) cloud-computing platform have been demonstrated to enhance the accuracy of mapping forest resources. This study presents a novel method for mapping...

Full description

Saved in:
Bibliographic Details
Main Authors: Dagnew Yebeyen, Binyam Tesfaw Hailu, Worku Zewdie, Temesgen Abera, Gudeta W. Sileshi, Melaku Getachew, Sileshi Nemomissa
Format: Article
Language:English
Published: Taylor & Francis Group 2024-01-01
Series:Geocarto International
Subjects:
Online Access:https://www.tandfonline.com/doi/10.1080/10106049.2024.2364680
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846129163039145984
author Dagnew Yebeyen
Binyam Tesfaw Hailu
Worku Zewdie
Temesgen Abera
Gudeta W. Sileshi
Melaku Getachew
Sileshi Nemomissa
author_facet Dagnew Yebeyen
Binyam Tesfaw Hailu
Worku Zewdie
Temesgen Abera
Gudeta W. Sileshi
Melaku Getachew
Sileshi Nemomissa
author_sort Dagnew Yebeyen
collection DOAJ
description Recent advances in the application of spectral bands from satellite observations and machine learning algorithms (MLA) in the Google Earth Engine (GEE) cloud-computing platform have been demonstrated to enhance the accuracy of mapping forest resources. This study presents a novel method for mapping the natural distribution of highland bamboo (Oldeania alpina) using spectral bands and three machine learning algorithms, namely random forest, gradient tree boosting, and classification and regression tree. First, spectral bands, vegetation indices and textural features including contrast, entropy and inverse difference moment were derived from the Sentinel-2 elevation data. Second, observations were categorized as the dry season (December–February), short rainy season (March-May), main (long) rainy season (June-August), wet season (September–November) and annual composite. Third, the machine learning algorithms were tested using 1882 ground control points collected from field and high spatial resolution images. Finally, the best-performing machine learning algorithm was used to classify and map bamboo forests. The five land cover categories identified were bamboo stands, natural forest, other vegetation, non-vegetated areas and water bodies. The result shows that the random forest classifier is a robust algorithm with an overall accuracy of 94% considering all the annual composite’s spectral, vegetation and textural variables. The highland bamboo coverage (91 km2) in the Andracha district provided valuable insights. Bamboo stands were mostly distributed in the southern and southeastern parts of the district. Here, we show that image compositing and multiple input parameters using machine learning techniques can overcome challenges facing land cover classification, which can hinder accurate mapping of Afromontane forests. We conclude that the incorporation of vegetation indices and textural features in land cover classification increases accuracy of mapping natural highland bamboo coverage and distribution. The application of this new method is a promising prospect not only in Ethiopia but also in Afromontane forests elsewhere in Africa.
format Article
id doaj-art-4d0006fa9f814ab39d4b8d2ce4328db5
institution Kabale University
issn 1010-6049
1752-0762
language English
publishDate 2024-01-01
publisher Taylor & Francis Group
record_format Article
series Geocarto International
spelling doaj-art-4d0006fa9f814ab39d4b8d2ce4328db52024-12-10T08:23:09ZengTaylor & Francis GroupGeocarto International1010-60491752-07622024-01-0139110.1080/10106049.2024.2364680Improved mapping of highland bamboo forests using Sentinel-2 time series and machine learning in Google Earth EngineDagnew Yebeyen0Binyam Tesfaw Hailu1Worku Zewdie2Temesgen Abera3Gudeta W. Sileshi4Melaku Getachew5Sileshi Nemomissa6International Bamboo and Rattan Organization, East Africa Regional Office, Addis Ababa, EthiopiaSchool of Earth Science, Addis Ababa University, Addis Ababa, EthiopiaDepartment of Remote Sensing, Space Science and Geospatial Institute, Addis Ababa, EthiopiaDepartment of Geosciences and Geography, University of Helsinki, Helsinki, FinlandDepartment of Plant Biology and Biodiversity Management, Addis Ababa University, Addis Ababa, EthiopiaBiometry, GIS and Database Directorate, Ethiopian Environment and Forest Research Institute, Addis Ababa, EthiopiaDepartment of Plant Biology and Biodiversity Management, Addis Ababa University, Addis Ababa, EthiopiaRecent advances in the application of spectral bands from satellite observations and machine learning algorithms (MLA) in the Google Earth Engine (GEE) cloud-computing platform have been demonstrated to enhance the accuracy of mapping forest resources. This study presents a novel method for mapping the natural distribution of highland bamboo (Oldeania alpina) using spectral bands and three machine learning algorithms, namely random forest, gradient tree boosting, and classification and regression tree. First, spectral bands, vegetation indices and textural features including contrast, entropy and inverse difference moment were derived from the Sentinel-2 elevation data. Second, observations were categorized as the dry season (December–February), short rainy season (March-May), main (long) rainy season (June-August), wet season (September–November) and annual composite. Third, the machine learning algorithms were tested using 1882 ground control points collected from field and high spatial resolution images. Finally, the best-performing machine learning algorithm was used to classify and map bamboo forests. The five land cover categories identified were bamboo stands, natural forest, other vegetation, non-vegetated areas and water bodies. The result shows that the random forest classifier is a robust algorithm with an overall accuracy of 94% considering all the annual composite’s spectral, vegetation and textural variables. The highland bamboo coverage (91 km2) in the Andracha district provided valuable insights. Bamboo stands were mostly distributed in the southern and southeastern parts of the district. Here, we show that image compositing and multiple input parameters using machine learning techniques can overcome challenges facing land cover classification, which can hinder accurate mapping of Afromontane forests. We conclude that the incorporation of vegetation indices and textural features in land cover classification increases accuracy of mapping natural highland bamboo coverage and distribution. The application of this new method is a promising prospect not only in Ethiopia but also in Afromontane forests elsewhere in Africa.https://www.tandfonline.com/doi/10.1080/10106049.2024.2364680Afromontane forestscloud computingOldeania alpinaland cover classificationmachine learningremote sensing
spellingShingle Dagnew Yebeyen
Binyam Tesfaw Hailu
Worku Zewdie
Temesgen Abera
Gudeta W. Sileshi
Melaku Getachew
Sileshi Nemomissa
Improved mapping of highland bamboo forests using Sentinel-2 time series and machine learning in Google Earth Engine
Geocarto International
Afromontane forests
cloud computing
Oldeania alpina
land cover classification
machine learning
remote sensing
title Improved mapping of highland bamboo forests using Sentinel-2 time series and machine learning in Google Earth Engine
title_full Improved mapping of highland bamboo forests using Sentinel-2 time series and machine learning in Google Earth Engine
title_fullStr Improved mapping of highland bamboo forests using Sentinel-2 time series and machine learning in Google Earth Engine
title_full_unstemmed Improved mapping of highland bamboo forests using Sentinel-2 time series and machine learning in Google Earth Engine
title_short Improved mapping of highland bamboo forests using Sentinel-2 time series and machine learning in Google Earth Engine
title_sort improved mapping of highland bamboo forests using sentinel 2 time series and machine learning in google earth engine
topic Afromontane forests
cloud computing
Oldeania alpina
land cover classification
machine learning
remote sensing
url https://www.tandfonline.com/doi/10.1080/10106049.2024.2364680
work_keys_str_mv AT dagnewyebeyen improvedmappingofhighlandbambooforestsusingsentinel2timeseriesandmachinelearningingoogleearthengine
AT binyamtesfawhailu improvedmappingofhighlandbambooforestsusingsentinel2timeseriesandmachinelearningingoogleearthengine
AT workuzewdie improvedmappingofhighlandbambooforestsusingsentinel2timeseriesandmachinelearningingoogleearthengine
AT temesgenabera improvedmappingofhighlandbambooforestsusingsentinel2timeseriesandmachinelearningingoogleearthengine
AT gudetawsileshi improvedmappingofhighlandbambooforestsusingsentinel2timeseriesandmachinelearningingoogleearthengine
AT melakugetachew improvedmappingofhighlandbambooforestsusingsentinel2timeseriesandmachinelearningingoogleearthengine
AT sileshinemomissa improvedmappingofhighlandbambooforestsusingsentinel2timeseriesandmachinelearningingoogleearthengine