In-season crop-type mapping in Kenya using Sentinel-2 imagery

In-season crop type mapping is essential to agriculture management applications, including yield estimates, crop planting acreage statistics, food market predictions, and land use change analysis that support relevant decision-making, pushing economic development in certain agricultural export natio...

Descripción completa

Detalles Bibliográficos
Autores principales: Li, Hui, Guo, Zhe, Di, Liping, Guo, Liying, Zhang, Chen, Lin, Li
Formato: Conference Paper
Lenguaje:Inglés
Publicado: Institute of Electrical and Electronics Engineers 2024
Materias:
Acceso en línea:https://hdl.handle.net/10568/159465
_version_ 1855531151926493184
author Li, Hui
Guo, Zhe
Di, Liping
Guo, Liying
Zhang, Chen
Lin, Li
author_browse Di, Liping
Guo, Liying
Guo, Zhe
Li, Hui
Lin, Li
Zhang, Chen
author_facet Li, Hui
Guo, Zhe
Di, Liping
Guo, Liying
Zhang, Chen
Lin, Li
author_sort Li, Hui
collection Repository of Agricultural Research Outputs (CGSpace)
description In-season crop type mapping is essential to agriculture management applications, including yield estimates, crop planting acreage statistics, food market predictions, and land use change analysis that support relevant decision-making, pushing economic development in certain agricultural export nations like Keny. This study employed a supervised machine learning method to produce three Kenya counties’ in-season crop-type maps in September 2023. We used surveyed growing crop ground truth data at the end of August 2023 and European Space Agency (ESA) WorldCover data serving as training labels, including nine crop types (Maize, Coffee, Grassland, Tea, Sugarcane, Exotic tree, Legumes, Vegetable, Native tree). The 15-day composite Sentinel-2 time series data was generated, incorporating training labels to assemble into training samples. They engaged in training a random forest classifier, conducting crop-type classifying in Nandi, Vihiga, and Kisumu Counties of Kenya. Moreover, the majority filter served to refine the classification. The validation results confirmed that grassland, sugarcane, tree, and tea possess high classification accuracy (0.80−0.91), and coffee and maize showcase low accuracy (0.67 0.73) due to the massive mix pixels. This study attempted to produce in-season crop-type maps in an African nation with fragmented crop fields.
format Conference Paper
id CGSpace159465
institution CGIAR Consortium
language Inglés
publishDate 2024
publishDateRange 2024
publishDateSort 2024
publisher Institute of Electrical and Electronics Engineers
publisherStr Institute of Electrical and Electronics Engineers
record_format dspace
spelling CGSpace1594652025-03-13T16:04:16Z In-season crop-type mapping in Kenya using Sentinel-2 imagery Li, Hui Guo, Zhe Di, Liping Guo, Liying Zhang, Chen Lin, Li crops modelling agriculture markets machine learning yields In-season crop type mapping is essential to agriculture management applications, including yield estimates, crop planting acreage statistics, food market predictions, and land use change analysis that support relevant decision-making, pushing economic development in certain agricultural export nations like Keny. This study employed a supervised machine learning method to produce three Kenya counties’ in-season crop-type maps in September 2023. We used surveyed growing crop ground truth data at the end of August 2023 and European Space Agency (ESA) WorldCover data serving as training labels, including nine crop types (Maize, Coffee, Grassland, Tea, Sugarcane, Exotic tree, Legumes, Vegetable, Native tree). The 15-day composite Sentinel-2 time series data was generated, incorporating training labels to assemble into training samples. They engaged in training a random forest classifier, conducting crop-type classifying in Nandi, Vihiga, and Kisumu Counties of Kenya. Moreover, the majority filter served to refine the classification. The validation results confirmed that grassland, sugarcane, tree, and tea possess high classification accuracy (0.80−0.91), and coffee and maize showcase low accuracy (0.67 0.73) due to the massive mix pixels. This study attempted to produce in-season crop-type maps in an African nation with fragmented crop fields. 2024-09-04 2024-11-08T19:42:02Z 2024-11-08T19:42:02Z Conference Paper https://hdl.handle.net/10568/159465 en Limited Access Institute of Electrical and Electronics Engineers Li, Hui; Guo, Zhe; Di, Liping; Guo, Liying; Zhang, Chen; and Lin, Li. 2024. In-season crop-type mapping in Kenya using Sentinel-2 imagery. 12th International Conference on Agro-Geoinformatics (Agro-Geoinformatics). Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/Agro-Geoinformatics262780.2024.10660971
spellingShingle crops
modelling
agriculture
markets
machine learning
yields
Li, Hui
Guo, Zhe
Di, Liping
Guo, Liying
Zhang, Chen
Lin, Li
In-season crop-type mapping in Kenya using Sentinel-2 imagery
title In-season crop-type mapping in Kenya using Sentinel-2 imagery
title_full In-season crop-type mapping in Kenya using Sentinel-2 imagery
title_fullStr In-season crop-type mapping in Kenya using Sentinel-2 imagery
title_full_unstemmed In-season crop-type mapping in Kenya using Sentinel-2 imagery
title_short In-season crop-type mapping in Kenya using Sentinel-2 imagery
title_sort in season crop type mapping in kenya using sentinel 2 imagery
topic crops
modelling
agriculture
markets
machine learning
yields
url https://hdl.handle.net/10568/159465
work_keys_str_mv AT lihui inseasoncroptypemappinginkenyausingsentinel2imagery
AT guozhe inseasoncroptypemappinginkenyausingsentinel2imagery
AT diliping inseasoncroptypemappinginkenyausingsentinel2imagery
AT guoliying inseasoncroptypemappinginkenyausingsentinel2imagery
AT zhangchen inseasoncroptypemappinginkenyausingsentinel2imagery
AT linli inseasoncroptypemappinginkenyausingsentinel2imagery