Landscape fragmentation in coffee agroecological subzones in central Kenya: A multiscale remote sensing approach
Smallholder agroecological subzones (AEsZs) produce an array of crops occupying large areas throughout Africa but remain largely unmapped. We explored multisource satellite datasets to produce a seamless land-use and land-cover (LULC) and fragmentation dataset for upper midland (UM1 to UM4) AEsZs in central Kenya. Specifically, the utility of PlanetScope, Sentinel 2, and Landsat 8 images for mapping coffee-based landscape were tested using a random forest (RF) classifier. Vegetation indices, texture variables, and wavelength bands from all satellite data were used as inputs in generating four RF models. A LULC baseline map was produced that was further analyzed using FRAGSTAT to generate landscape metrics for each AEsZs. Wavelength bands model from Sentinel 2 had the highest overall accuracy with shortwave near-infrared and green bands as the most important variables. In UM1 and UM2, coffee was the dominant cover type, whereas annual and other perennial crops dominated the landscape in UM3 and UM4. The patch density for coffee was five times higher in UM4 than in UM1. Since Sentinel 2 is freely available, the approach used in our study can be adopted to support land-use planning in smallholder agroecosystems.
Main Authors: | , , , , , , , , |
---|---|
Format: | article biblioteca |
Language: | eng |
Subjects: | F40 - Écologie végétale, U30 - Méthodes de recherche, paysage agricole, agroécosystème, cartographie de l'utilisation des terres, télédétection, apprentissage machine, Coffea arabica, http://aims.fao.org/aos/agrovoc/c_37277, http://aims.fao.org/aos/agrovoc/c_36669, http://aims.fao.org/aos/agrovoc/c_9000100, http://aims.fao.org/aos/agrovoc/c_6498, http://aims.fao.org/aos/agrovoc/c_49834, http://aims.fao.org/aos/agrovoc/c_1721, http://aims.fao.org/aos/agrovoc/c_4086, |
Online Access: | http://agritrop.cirad.fr/597442/ http://agritrop.cirad.fr/597442/1/Mos2.pdf |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
id |
dig-cirad-fr-597442 |
---|---|
record_format |
koha |
spelling |
dig-cirad-fr-5974422024-01-29T03:16:51Z http://agritrop.cirad.fr/597442/ http://agritrop.cirad.fr/597442/ Landscape fragmentation in coffee agroecological subzones in central Kenya: A multiscale remote sensing approach. Mosomtai Gladys, Odindi John, Abdel-Rahman Elfatih M., Babin Régis, Pinard Fabrice, Mutanga Onisimo, Tonnang Henri E.Z., David Guillaume, Landmann Tobias. 2020. Journal of Applied Remote Sensing, 14 (4):044513, 20 p.https://doi.org/10.1117/1.JRS.14.044513 <https://doi.org/10.1117/1.JRS.14.044513> Landscape fragmentation in coffee agroecological subzones in central Kenya: A multiscale remote sensing approach Mosomtai, Gladys Odindi, John Abdel-Rahman, Elfatih M. Babin, Régis Pinard, Fabrice Mutanga, Onisimo Tonnang, Henri E.Z. David, Guillaume Landmann, Tobias eng 2020 Journal of Applied Remote Sensing F40 - Écologie végétale U30 - Méthodes de recherche paysage agricole agroécosystème cartographie de l'utilisation des terres télédétection apprentissage machine Coffea arabica http://aims.fao.org/aos/agrovoc/c_37277 http://aims.fao.org/aos/agrovoc/c_36669 http://aims.fao.org/aos/agrovoc/c_9000100 http://aims.fao.org/aos/agrovoc/c_6498 http://aims.fao.org/aos/agrovoc/c_49834 http://aims.fao.org/aos/agrovoc/c_1721 Kenya http://aims.fao.org/aos/agrovoc/c_4086 Smallholder agroecological subzones (AEsZs) produce an array of crops occupying large areas throughout Africa but remain largely unmapped. We explored multisource satellite datasets to produce a seamless land-use and land-cover (LULC) and fragmentation dataset for upper midland (UM1 to UM4) AEsZs in central Kenya. Specifically, the utility of PlanetScope, Sentinel 2, and Landsat 8 images for mapping coffee-based landscape were tested using a random forest (RF) classifier. Vegetation indices, texture variables, and wavelength bands from all satellite data were used as inputs in generating four RF models. A LULC baseline map was produced that was further analyzed using FRAGSTAT to generate landscape metrics for each AEsZs. Wavelength bands model from Sentinel 2 had the highest overall accuracy with shortwave near-infrared and green bands as the most important variables. In UM1 and UM2, coffee was the dominant cover type, whereas annual and other perennial crops dominated the landscape in UM3 and UM4. The patch density for coffee was five times higher in UM4 than in UM1. Since Sentinel 2 is freely available, the approach used in our study can be adopted to support land-use planning in smallholder agroecosystems. article info:eu-repo/semantics/article Journal Article info:eu-repo/semantics/publishedVersion http://agritrop.cirad.fr/597442/1/Mos2.pdf text Cirad license info:eu-repo/semantics/restrictedAccess https://agritrop.cirad.fr/mention_legale.html https://doi.org/10.1117/1.JRS.14.044513 10.1117/1.JRS.14.044513 info:eu-repo/semantics/altIdentifier/doi/10.1117/1.JRS.14.044513 info:eu-repo/semantics/altIdentifier/purl/https://doi.org/10.1117/1.JRS.14.044513 |
institution |
CIRAD FR |
collection |
DSpace |
country |
Francia |
countrycode |
FR |
component |
Bibliográfico |
access |
En linea |
databasecode |
dig-cirad-fr |
tag |
biblioteca |
region |
Europa del Oeste |
libraryname |
Biblioteca del CIRAD Francia |
language |
eng |
topic |
F40 - Écologie végétale U30 - Méthodes de recherche paysage agricole agroécosystème cartographie de l'utilisation des terres télédétection apprentissage machine Coffea arabica http://aims.fao.org/aos/agrovoc/c_37277 http://aims.fao.org/aos/agrovoc/c_36669 http://aims.fao.org/aos/agrovoc/c_9000100 http://aims.fao.org/aos/agrovoc/c_6498 http://aims.fao.org/aos/agrovoc/c_49834 http://aims.fao.org/aos/agrovoc/c_1721 http://aims.fao.org/aos/agrovoc/c_4086 F40 - Écologie végétale U30 - Méthodes de recherche paysage agricole agroécosystème cartographie de l'utilisation des terres télédétection apprentissage machine Coffea arabica http://aims.fao.org/aos/agrovoc/c_37277 http://aims.fao.org/aos/agrovoc/c_36669 http://aims.fao.org/aos/agrovoc/c_9000100 http://aims.fao.org/aos/agrovoc/c_6498 http://aims.fao.org/aos/agrovoc/c_49834 http://aims.fao.org/aos/agrovoc/c_1721 http://aims.fao.org/aos/agrovoc/c_4086 |
spellingShingle |
F40 - Écologie végétale U30 - Méthodes de recherche paysage agricole agroécosystème cartographie de l'utilisation des terres télédétection apprentissage machine Coffea arabica http://aims.fao.org/aos/agrovoc/c_37277 http://aims.fao.org/aos/agrovoc/c_36669 http://aims.fao.org/aos/agrovoc/c_9000100 http://aims.fao.org/aos/agrovoc/c_6498 http://aims.fao.org/aos/agrovoc/c_49834 http://aims.fao.org/aos/agrovoc/c_1721 http://aims.fao.org/aos/agrovoc/c_4086 F40 - Écologie végétale U30 - Méthodes de recherche paysage agricole agroécosystème cartographie de l'utilisation des terres télédétection apprentissage machine Coffea arabica http://aims.fao.org/aos/agrovoc/c_37277 http://aims.fao.org/aos/agrovoc/c_36669 http://aims.fao.org/aos/agrovoc/c_9000100 http://aims.fao.org/aos/agrovoc/c_6498 http://aims.fao.org/aos/agrovoc/c_49834 http://aims.fao.org/aos/agrovoc/c_1721 http://aims.fao.org/aos/agrovoc/c_4086 Mosomtai, Gladys Odindi, John Abdel-Rahman, Elfatih M. Babin, Régis Pinard, Fabrice Mutanga, Onisimo Tonnang, Henri E.Z. David, Guillaume Landmann, Tobias Landscape fragmentation in coffee agroecological subzones in central Kenya: A multiscale remote sensing approach |
description |
Smallholder agroecological subzones (AEsZs) produce an array of crops occupying large areas throughout Africa but remain largely unmapped. We explored multisource satellite datasets to produce a seamless land-use and land-cover (LULC) and fragmentation dataset for upper midland (UM1 to UM4) AEsZs in central Kenya. Specifically, the utility of PlanetScope, Sentinel 2, and Landsat 8 images for mapping coffee-based landscape were tested using a random forest (RF) classifier. Vegetation indices, texture variables, and wavelength bands from all satellite data were used as inputs in generating four RF models. A LULC baseline map was produced that was further analyzed using FRAGSTAT to generate landscape metrics for each AEsZs. Wavelength bands model from Sentinel 2 had the highest overall accuracy with shortwave near-infrared and green bands as the most important variables. In UM1 and UM2, coffee was the dominant cover type, whereas annual and other perennial crops dominated the landscape in UM3 and UM4. The patch density for coffee was five times higher in UM4 than in UM1. Since Sentinel 2 is freely available, the approach used in our study can be adopted to support land-use planning in smallholder agroecosystems. |
format |
article |
topic_facet |
F40 - Écologie végétale U30 - Méthodes de recherche paysage agricole agroécosystème cartographie de l'utilisation des terres télédétection apprentissage machine Coffea arabica http://aims.fao.org/aos/agrovoc/c_37277 http://aims.fao.org/aos/agrovoc/c_36669 http://aims.fao.org/aos/agrovoc/c_9000100 http://aims.fao.org/aos/agrovoc/c_6498 http://aims.fao.org/aos/agrovoc/c_49834 http://aims.fao.org/aos/agrovoc/c_1721 http://aims.fao.org/aos/agrovoc/c_4086 |
author |
Mosomtai, Gladys Odindi, John Abdel-Rahman, Elfatih M. Babin, Régis Pinard, Fabrice Mutanga, Onisimo Tonnang, Henri E.Z. David, Guillaume Landmann, Tobias |
author_facet |
Mosomtai, Gladys Odindi, John Abdel-Rahman, Elfatih M. Babin, Régis Pinard, Fabrice Mutanga, Onisimo Tonnang, Henri E.Z. David, Guillaume Landmann, Tobias |
author_sort |
Mosomtai, Gladys |
title |
Landscape fragmentation in coffee agroecological subzones in central Kenya: A multiscale remote sensing approach |
title_short |
Landscape fragmentation in coffee agroecological subzones in central Kenya: A multiscale remote sensing approach |
title_full |
Landscape fragmentation in coffee agroecological subzones in central Kenya: A multiscale remote sensing approach |
title_fullStr |
Landscape fragmentation in coffee agroecological subzones in central Kenya: A multiscale remote sensing approach |
title_full_unstemmed |
Landscape fragmentation in coffee agroecological subzones in central Kenya: A multiscale remote sensing approach |
title_sort |
landscape fragmentation in coffee agroecological subzones in central kenya: a multiscale remote sensing approach |
url |
http://agritrop.cirad.fr/597442/ http://agritrop.cirad.fr/597442/1/Mos2.pdf |
work_keys_str_mv |
AT mosomtaigladys landscapefragmentationincoffeeagroecologicalsubzonesincentralkenyaamultiscaleremotesensingapproach AT odindijohn landscapefragmentationincoffeeagroecologicalsubzonesincentralkenyaamultiscaleremotesensingapproach AT abdelrahmanelfatihm landscapefragmentationincoffeeagroecologicalsubzonesincentralkenyaamultiscaleremotesensingapproach AT babinregis landscapefragmentationincoffeeagroecologicalsubzonesincentralkenyaamultiscaleremotesensingapproach AT pinardfabrice landscapefragmentationincoffeeagroecologicalsubzonesincentralkenyaamultiscaleremotesensingapproach AT mutangaonisimo landscapefragmentationincoffeeagroecologicalsubzonesincentralkenyaamultiscaleremotesensingapproach AT tonnanghenriez landscapefragmentationincoffeeagroecologicalsubzonesincentralkenyaamultiscaleremotesensingapproach AT davidguillaume landscapefragmentationincoffeeagroecologicalsubzonesincentralkenyaamultiscaleremotesensingapproach AT landmanntobias landscapefragmentationincoffeeagroecologicalsubzonesincentralkenyaamultiscaleremotesensingapproach |
_version_ |
1792500090475118592 |