A combined random forest and OBIA classification scheme for mapping smallholder agriculture at different nomenclature levels using multisource data (simulated sentinel-2 time series, VHRS and DEM)
Sentinel-2 images are expected to improve global crop monitoring even in challenging tropical small agricultural systems that are characterized by high intra- and inter-field spatial variability and where satellite observations are disturbed by the presence of clouds. To overcome these constraints, we analyzed and optimized the performance of a combined Random Forest (RF) classifier/object-based approach and applied it to multisource satellite data to produce land use maps of a smallholder agricultural zone in Madagascar at five different nomenclature levels. The RF classifier was first optimized by reducing the number of input variables. Experiments were then carried out to (i) test cropland masking prior to the classification of more detailed nomenclature levels, (ii) analyze the importance of each data source (a high spatial resolution (HSR) time series, a very high spatial resolution (VHSR) coverage and a digital elevation model (DEM)) and data type (spectral, textural or other), and (iii) quantify their contributions to classification accuracy levels. The results show that RF classifier optimization allowed for a reduction in the number of variables by 1.5- to 6-fold (depending on the classification level) and thus a reduction in the data processing time. Classification results were improved via the hierarchical approach at all classification levels, achieving an overall accuracy of 91.7% and 64.4% for the cropland and crop subclass levels, respectively. Spectral variables derived from an HSR time series were shown to be the most discriminating, with a better score for spectral indices over the reflectances. VHSR data were only found to be essential when implementing the segmentation of the area into objects and not for the spectral or textural features they can provide during classification.
id |
dig-cirad-fr-583973 |
---|---|
record_format |
koha |
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 |
E11 - Économie et politique foncières E50 - Sociologie rurale E80 - Économie familiale et artisanale E90 - Structure agraire U30 - Méthodes de recherche utilisation des terres télédétection terre agricole cartographie de l'utilisation des terres cartographie de l'occupation du sol image spot classification des terres riz sécurité alimentaire imagerie par satellite imagerie multispectrale http://aims.fao.org/aos/agrovoc/c_4182 http://aims.fao.org/aos/agrovoc/c_6498 http://aims.fao.org/aos/agrovoc/c_2808 http://aims.fao.org/aos/agrovoc/c_9000100 http://aims.fao.org/aos/agrovoc/c_9000094 http://aims.fao.org/aos/agrovoc/c_16343 http://aims.fao.org/aos/agrovoc/c_15991 http://aims.fao.org/aos/agrovoc/c_6599 http://aims.fao.org/aos/agrovoc/c_10967 http://aims.fao.org/aos/agrovoc/c_36761 http://aims.fao.org/aos/agrovoc/c_36765 http://aims.fao.org/aos/agrovoc/c_4510 E11 - Économie et politique foncières E50 - Sociologie rurale E80 - Économie familiale et artisanale E90 - Structure agraire U30 - Méthodes de recherche utilisation des terres télédétection terre agricole cartographie de l'utilisation des terres cartographie de l'occupation du sol image spot classification des terres riz sécurité alimentaire imagerie par satellite imagerie multispectrale http://aims.fao.org/aos/agrovoc/c_4182 http://aims.fao.org/aos/agrovoc/c_6498 http://aims.fao.org/aos/agrovoc/c_2808 http://aims.fao.org/aos/agrovoc/c_9000100 http://aims.fao.org/aos/agrovoc/c_9000094 http://aims.fao.org/aos/agrovoc/c_16343 http://aims.fao.org/aos/agrovoc/c_15991 http://aims.fao.org/aos/agrovoc/c_6599 http://aims.fao.org/aos/agrovoc/c_10967 http://aims.fao.org/aos/agrovoc/c_36761 http://aims.fao.org/aos/agrovoc/c_36765 http://aims.fao.org/aos/agrovoc/c_4510 |
spellingShingle |
E11 - Économie et politique foncières E50 - Sociologie rurale E80 - Économie familiale et artisanale E90 - Structure agraire U30 - Méthodes de recherche utilisation des terres télédétection terre agricole cartographie de l'utilisation des terres cartographie de l'occupation du sol image spot classification des terres riz sécurité alimentaire imagerie par satellite imagerie multispectrale http://aims.fao.org/aos/agrovoc/c_4182 http://aims.fao.org/aos/agrovoc/c_6498 http://aims.fao.org/aos/agrovoc/c_2808 http://aims.fao.org/aos/agrovoc/c_9000100 http://aims.fao.org/aos/agrovoc/c_9000094 http://aims.fao.org/aos/agrovoc/c_16343 http://aims.fao.org/aos/agrovoc/c_15991 http://aims.fao.org/aos/agrovoc/c_6599 http://aims.fao.org/aos/agrovoc/c_10967 http://aims.fao.org/aos/agrovoc/c_36761 http://aims.fao.org/aos/agrovoc/c_36765 http://aims.fao.org/aos/agrovoc/c_4510 E11 - Économie et politique foncières E50 - Sociologie rurale E80 - Économie familiale et artisanale E90 - Structure agraire U30 - Méthodes de recherche utilisation des terres télédétection terre agricole cartographie de l'utilisation des terres cartographie de l'occupation du sol image spot classification des terres riz sécurité alimentaire imagerie par satellite imagerie multispectrale http://aims.fao.org/aos/agrovoc/c_4182 http://aims.fao.org/aos/agrovoc/c_6498 http://aims.fao.org/aos/agrovoc/c_2808 http://aims.fao.org/aos/agrovoc/c_9000100 http://aims.fao.org/aos/agrovoc/c_9000094 http://aims.fao.org/aos/agrovoc/c_16343 http://aims.fao.org/aos/agrovoc/c_15991 http://aims.fao.org/aos/agrovoc/c_6599 http://aims.fao.org/aos/agrovoc/c_10967 http://aims.fao.org/aos/agrovoc/c_36761 http://aims.fao.org/aos/agrovoc/c_36765 http://aims.fao.org/aos/agrovoc/c_4510 Lebourgeois, Valentine Dupuy, Stéphane Vintrou, Elodie Ameline, Maël Butler, Suzanne Bégué, Agnès A combined random forest and OBIA classification scheme for mapping smallholder agriculture at different nomenclature levels using multisource data (simulated sentinel-2 time series, VHRS and DEM) |
description |
Sentinel-2 images are expected to improve global crop monitoring even in challenging tropical small agricultural systems that are characterized by high intra- and inter-field spatial variability and where satellite observations are disturbed by the presence of clouds. To overcome these constraints, we analyzed and optimized the performance of a combined Random Forest (RF) classifier/object-based approach and applied it to multisource satellite data to produce land use maps of a smallholder agricultural zone in Madagascar at five different nomenclature levels. The RF classifier was first optimized by reducing the number of input variables. Experiments were then carried out to (i) test cropland masking prior to the classification of more detailed nomenclature levels, (ii) analyze the importance of each data source (a high spatial resolution (HSR) time series, a very high spatial resolution (VHSR) coverage and a digital elevation model (DEM)) and data type (spectral, textural or other), and (iii) quantify their contributions to classification accuracy levels. The results show that RF classifier optimization allowed for a reduction in the number of variables by 1.5- to 6-fold (depending on the classification level) and thus a reduction in the data processing time. Classification results were improved via the hierarchical approach at all classification levels, achieving an overall accuracy of 91.7% and 64.4% for the cropland and crop subclass levels, respectively. Spectral variables derived from an HSR time series were shown to be the most discriminating, with a better score for spectral indices over the reflectances. VHSR data were only found to be essential when implementing the segmentation of the area into objects and not for the spectral or textural features they can provide during classification. |
format |
article |
topic_facet |
E11 - Économie et politique foncières E50 - Sociologie rurale E80 - Économie familiale et artisanale E90 - Structure agraire U30 - Méthodes de recherche utilisation des terres télédétection terre agricole cartographie de l'utilisation des terres cartographie de l'occupation du sol image spot classification des terres riz sécurité alimentaire imagerie par satellite imagerie multispectrale http://aims.fao.org/aos/agrovoc/c_4182 http://aims.fao.org/aos/agrovoc/c_6498 http://aims.fao.org/aos/agrovoc/c_2808 http://aims.fao.org/aos/agrovoc/c_9000100 http://aims.fao.org/aos/agrovoc/c_9000094 http://aims.fao.org/aos/agrovoc/c_16343 http://aims.fao.org/aos/agrovoc/c_15991 http://aims.fao.org/aos/agrovoc/c_6599 http://aims.fao.org/aos/agrovoc/c_10967 http://aims.fao.org/aos/agrovoc/c_36761 http://aims.fao.org/aos/agrovoc/c_36765 http://aims.fao.org/aos/agrovoc/c_4510 |
author |
Lebourgeois, Valentine Dupuy, Stéphane Vintrou, Elodie Ameline, Maël Butler, Suzanne Bégué, Agnès |
author_facet |
Lebourgeois, Valentine Dupuy, Stéphane Vintrou, Elodie Ameline, Maël Butler, Suzanne Bégué, Agnès |
author_sort |
Lebourgeois, Valentine |
title |
A combined random forest and OBIA classification scheme for mapping smallholder agriculture at different nomenclature levels using multisource data (simulated sentinel-2 time series, VHRS and DEM) |
title_short |
A combined random forest and OBIA classification scheme for mapping smallholder agriculture at different nomenclature levels using multisource data (simulated sentinel-2 time series, VHRS and DEM) |
title_full |
A combined random forest and OBIA classification scheme for mapping smallholder agriculture at different nomenclature levels using multisource data (simulated sentinel-2 time series, VHRS and DEM) |
title_fullStr |
A combined random forest and OBIA classification scheme for mapping smallholder agriculture at different nomenclature levels using multisource data (simulated sentinel-2 time series, VHRS and DEM) |
title_full_unstemmed |
A combined random forest and OBIA classification scheme for mapping smallholder agriculture at different nomenclature levels using multisource data (simulated sentinel-2 time series, VHRS and DEM) |
title_sort |
combined random forest and obia classification scheme for mapping smallholder agriculture at different nomenclature levels using multisource data (simulated sentinel-2 time series, vhrs and dem) |
url |
http://agritrop.cirad.fr/583973/ http://agritrop.cirad.fr/583973/1/remotesensing-09-00259.pdf |
work_keys_str_mv |
AT lebourgeoisvalentine acombinedrandomforestandobiaclassificationschemeformappingsmallholderagricultureatdifferentnomenclaturelevelsusingmultisourcedatasimulatedsentinel2timeseriesvhrsanddem AT dupuystephane acombinedrandomforestandobiaclassificationschemeformappingsmallholderagricultureatdifferentnomenclaturelevelsusingmultisourcedatasimulatedsentinel2timeseriesvhrsanddem AT vintrouelodie acombinedrandomforestandobiaclassificationschemeformappingsmallholderagricultureatdifferentnomenclaturelevelsusingmultisourcedatasimulatedsentinel2timeseriesvhrsanddem AT amelinemael acombinedrandomforestandobiaclassificationschemeformappingsmallholderagricultureatdifferentnomenclaturelevelsusingmultisourcedatasimulatedsentinel2timeseriesvhrsanddem AT butlersuzanne acombinedrandomforestandobiaclassificationschemeformappingsmallholderagricultureatdifferentnomenclaturelevelsusingmultisourcedatasimulatedsentinel2timeseriesvhrsanddem AT begueagnes acombinedrandomforestandobiaclassificationschemeformappingsmallholderagricultureatdifferentnomenclaturelevelsusingmultisourcedatasimulatedsentinel2timeseriesvhrsanddem AT lebourgeoisvalentine combinedrandomforestandobiaclassificationschemeformappingsmallholderagricultureatdifferentnomenclaturelevelsusingmultisourcedatasimulatedsentinel2timeseriesvhrsanddem AT dupuystephane combinedrandomforestandobiaclassificationschemeformappingsmallholderagricultureatdifferentnomenclaturelevelsusingmultisourcedatasimulatedsentinel2timeseriesvhrsanddem AT vintrouelodie combinedrandomforestandobiaclassificationschemeformappingsmallholderagricultureatdifferentnomenclaturelevelsusingmultisourcedatasimulatedsentinel2timeseriesvhrsanddem AT amelinemael combinedrandomforestandobiaclassificationschemeformappingsmallholderagricultureatdifferentnomenclaturelevelsusingmultisourcedatasimulatedsentinel2timeseriesvhrsanddem AT butlersuzanne combinedrandomforestandobiaclassificationschemeformappingsmallholderagricultureatdifferentnomenclaturelevelsusingmultisourcedatasimulatedsentinel2timeseriesvhrsanddem AT begueagnes combinedrandomforestandobiaclassificationschemeformappingsmallholderagricultureatdifferentnomenclaturelevelsusingmultisourcedatasimulatedsentinel2timeseriesvhrsanddem |
_version_ |
1792499255920820224 |
spelling |
dig-cirad-fr-5839732024-01-29T00:12:47Z http://agritrop.cirad.fr/583973/ http://agritrop.cirad.fr/583973/ A combined random forest and OBIA classification scheme for mapping smallholder agriculture at different nomenclature levels using multisource data (simulated sentinel-2 time series, VHRS and DEM). Lebourgeois Valentine, Dupuy Stéphane, Vintrou Elodie, Ameline Maël, Butler Suzanne, Bégué Agnès. 2017. Remote Sensing, 9 (3):259, 20 p.https://doi.org/10.3390/rs9030259 <https://doi.org/10.3390/rs9030259> A combined random forest and OBIA classification scheme for mapping smallholder agriculture at different nomenclature levels using multisource data (simulated sentinel-2 time series, VHRS and DEM) Lebourgeois, Valentine Dupuy, Stéphane Vintrou, Elodie Ameline, Maël Butler, Suzanne Bégué, Agnès eng 2017 Remote Sensing E11 - Économie et politique foncières E50 - Sociologie rurale E80 - Économie familiale et artisanale E90 - Structure agraire U30 - Méthodes de recherche utilisation des terres télédétection terre agricole cartographie de l'utilisation des terres cartographie de l'occupation du sol image spot classification des terres riz sécurité alimentaire imagerie par satellite imagerie multispectrale http://aims.fao.org/aos/agrovoc/c_4182 http://aims.fao.org/aos/agrovoc/c_6498 http://aims.fao.org/aos/agrovoc/c_2808 http://aims.fao.org/aos/agrovoc/c_9000100 http://aims.fao.org/aos/agrovoc/c_9000094 http://aims.fao.org/aos/agrovoc/c_16343 http://aims.fao.org/aos/agrovoc/c_15991 http://aims.fao.org/aos/agrovoc/c_6599 http://aims.fao.org/aos/agrovoc/c_10967 http://aims.fao.org/aos/agrovoc/c_36761 http://aims.fao.org/aos/agrovoc/c_36765 Madagascar http://aims.fao.org/aos/agrovoc/c_4510 Sentinel-2 images are expected to improve global crop monitoring even in challenging tropical small agricultural systems that are characterized by high intra- and inter-field spatial variability and where satellite observations are disturbed by the presence of clouds. To overcome these constraints, we analyzed and optimized the performance of a combined Random Forest (RF) classifier/object-based approach and applied it to multisource satellite data to produce land use maps of a smallholder agricultural zone in Madagascar at five different nomenclature levels. The RF classifier was first optimized by reducing the number of input variables. Experiments were then carried out to (i) test cropland masking prior to the classification of more detailed nomenclature levels, (ii) analyze the importance of each data source (a high spatial resolution (HSR) time series, a very high spatial resolution (VHSR) coverage and a digital elevation model (DEM)) and data type (spectral, textural or other), and (iii) quantify their contributions to classification accuracy levels. The results show that RF classifier optimization allowed for a reduction in the number of variables by 1.5- to 6-fold (depending on the classification level) and thus a reduction in the data processing time. Classification results were improved via the hierarchical approach at all classification levels, achieving an overall accuracy of 91.7% and 64.4% for the cropland and crop subclass levels, respectively. Spectral variables derived from an HSR time series were shown to be the most discriminating, with a better score for spectral indices over the reflectances. VHSR data were only found to be essential when implementing the segmentation of the area into objects and not for the spectral or textural features they can provide during classification. article info:eu-repo/semantics/article Journal Article info:eu-repo/semantics/publishedVersion http://agritrop.cirad.fr/583973/1/remotesensing-09-00259.pdf text cc_by info:eu-repo/semantics/openAccess https://creativecommons.org/licenses/by/4.0/ https://doi.org/10.3390/rs9030259 10.3390/rs9030259 info:eu-repo/semantics/altIdentifier/doi/10.3390/rs9030259 info:eu-repo/semantics/altIdentifier/purl/https://doi.org/10.3390/rs9030259 info:eu-repo/semantics/reference/purl/https://doi.org/10.18167/DVN1/8T3UJE info:eu-repo/grantAgreement/EC/FP7/603719//(EU) Stimulating Innovation for Global Monitoring of Agriculture and its Impact on the Environment in support of GEOGLAM/SIGMA |