A machine learning algorithm for mapping small reservoirs using Sentinel-2 satellite imagery in Google Earth Engine

This report outlines an advanced methodology for mapping small reservoirs in Northern Ghana, utilizing Sentinel-2 satellite imagery and Google Earth Engine. Aimed at enhancing mapping accuracy by reducing cloud contamination, the method filters image collections, applies optimal cloud masks, and com...

Descripción completa

Detalles Bibliográficos
Autores principales: Siabi, Ebenezer K., Akpoti, Komlavi, Zwart, Sander J.
Formato: Informe técnico
Lenguaje:Inglés
Publicado: International Water Management Institute (IWMI). CGIAR Initiative on Aquatic Foods 2023
Materias:
Acceso en línea:https://hdl.handle.net/10568/139360
_version_ 1855539123358531584
author Siabi, Ebenezer K.
Akpoti, Komlavi
Zwart, Sander J.
author_browse Akpoti, Komlavi
Siabi, Ebenezer K.
Zwart, Sander J.
author_facet Siabi, Ebenezer K.
Akpoti, Komlavi
Zwart, Sander J.
author_sort Siabi, Ebenezer K.
collection Repository of Agricultural Research Outputs (CGSpace)
description This report outlines an advanced methodology for mapping small reservoirs in Northern Ghana, utilizing Sentinel-2 satellite imagery and Google Earth Engine. Aimed at enhancing mapping accuracy by reducing cloud contamination, the method filters image collections, applies optimal cloud masks, and composes cloudless images. The methodology also included the calculation of spectral indices such as the Normalized Difference Vegetation Index (NDVI) and the Modified Normalized Difference Water Index (MNDWI) to improve classification accuracy, while a Random Forest algorithm classifies water and non-water features based on training samples from satellite imagery. The algorithm, leveraging specific spectral bands and MNDWI, demonstrates high accuracy, with results validated against a test dataset. The process concludes with image cleaning and permanent water masking, exporting the data in raster format for analysis. This methodology supports effective water resource management and the CGIAR Initiative on Aquatic Foods’ goals for food security and sustainable aquaculture in Northern Ghana.
format Informe técnico
id CGSpace139360
institution CGIAR Consortium
language Inglés
publishDate 2023
publishDateRange 2023
publishDateSort 2023
publisher International Water Management Institute (IWMI). CGIAR Initiative on Aquatic Foods
publisherStr International Water Management Institute (IWMI). CGIAR Initiative on Aquatic Foods
record_format dspace
spelling CGSpace1393602025-11-07T09:03:02Z A machine learning algorithm for mapping small reservoirs using Sentinel-2 satellite imagery in Google Earth Engine Siabi, Ebenezer K. Akpoti, Komlavi Zwart, Sander J. reservoirs mapping machine learning satellite imagery This report outlines an advanced methodology for mapping small reservoirs in Northern Ghana, utilizing Sentinel-2 satellite imagery and Google Earth Engine. Aimed at enhancing mapping accuracy by reducing cloud contamination, the method filters image collections, applies optimal cloud masks, and composes cloudless images. The methodology also included the calculation of spectral indices such as the Normalized Difference Vegetation Index (NDVI) and the Modified Normalized Difference Water Index (MNDWI) to improve classification accuracy, while a Random Forest algorithm classifies water and non-water features based on training samples from satellite imagery. The algorithm, leveraging specific spectral bands and MNDWI, demonstrates high accuracy, with results validated against a test dataset. The process concludes with image cleaning and permanent water masking, exporting the data in raster format for analysis. This methodology supports effective water resource management and the CGIAR Initiative on Aquatic Foods’ goals for food security and sustainable aquaculture in Northern Ghana. 2023-12-01 2024-02-14T12:12:04Z 2024-02-14T12:12:04Z Report https://hdl.handle.net/10568/139360 en Open Access application/pdf International Water Management Institute (IWMI). CGIAR Initiative on Aquatic Foods Siabi, Ebenezer K.; Akpoti, Komlavi; Zwart, Sander J. 2023. A machine learning algorithm for mapping small reservoirs using Sentinel-2 satellite imagery in Google Earth Engine. Colombo, Sri Lanka: International Water Management Institute (IWMI). CGIAR Initiative on Aquatic Foods. 13p.
spellingShingle reservoirs
mapping
machine learning
satellite imagery
Siabi, Ebenezer K.
Akpoti, Komlavi
Zwart, Sander J.
A machine learning algorithm for mapping small reservoirs using Sentinel-2 satellite imagery in Google Earth Engine
title A machine learning algorithm for mapping small reservoirs using Sentinel-2 satellite imagery in Google Earth Engine
title_full A machine learning algorithm for mapping small reservoirs using Sentinel-2 satellite imagery in Google Earth Engine
title_fullStr A machine learning algorithm for mapping small reservoirs using Sentinel-2 satellite imagery in Google Earth Engine
title_full_unstemmed A machine learning algorithm for mapping small reservoirs using Sentinel-2 satellite imagery in Google Earth Engine
title_short A machine learning algorithm for mapping small reservoirs using Sentinel-2 satellite imagery in Google Earth Engine
title_sort machine learning algorithm for mapping small reservoirs using sentinel 2 satellite imagery in google earth engine
topic reservoirs
mapping
machine learning
satellite imagery
url https://hdl.handle.net/10568/139360
work_keys_str_mv AT siabiebenezerk amachinelearningalgorithmformappingsmallreservoirsusingsentinel2satelliteimageryingoogleearthengine
AT akpotikomlavi amachinelearningalgorithmformappingsmallreservoirsusingsentinel2satelliteimageryingoogleearthengine
AT zwartsanderj amachinelearningalgorithmformappingsmallreservoirsusingsentinel2satelliteimageryingoogleearthengine
AT siabiebenezerk machinelearningalgorithmformappingsmallreservoirsusingsentinel2satelliteimageryingoogleearthengine
AT akpotikomlavi machinelearningalgorithmformappingsmallreservoirsusingsentinel2satelliteimageryingoogleearthengine
AT zwartsanderj machinelearningalgorithmformappingsmallreservoirsusingsentinel2satelliteimageryingoogleearthengine