Your search found 2 records
1 Siabi, Ebenezer K.; Akpoti, Komlavi; Zwart, Sander J. 2023. Small reservoirs in the northern regions of Ghana and their vulnerability to drying. Colombo, Sri Lanka: International Water Management Institute (IWMI). CGIAR Initiative on Aquatic Foods. 37p.
(Location: IWMI HQ Call no: e-copy only Record No: H052651)
(3.60 MB)
This study investigates the dynamics and susceptibility to drying of small reservoirs in Northern Ghana, leveraging advanced machine learning and remote sensing techniques through Google Earth Engine. It aims to map these reservoirs, evaluate their extent, and analyze water availability during dry seasons, crucial for understanding water resource potential for aquaculture and supporting food security goals under the CGIAR Initiative on Aquatic Foods. Findings reveal a consistent decrease in the number and size of reservoirs from November to April, attributed to increasing dry conditions, with a notable rise in reservoir numbers peaking in November 2022. Small reservoirs (< 0.6 hectares) were found to be more numerous than medium and large ones, predominantly located in midstream areas. Approximately half of these reservoirs face a very high risk of drying, highlighting the urgent need for effective water management strategies. This research provides significant insights into the vulnerabilities of small reservoirs, guiding sustainable management practices to combat the impacts of climate change and environmental stressors on water and aquaculture resources in Northern Ghana.
2 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.
(Location: IWMI HQ Call no: e-copy only Record No: H052658)
(0.98 MB)
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.
Powered by DB/Text
WebPublisher, from