Discriminating Robusta coffee (Coffea canephora) cropping systems using leaf-level hyperspectral data

Simple item page
cg.authorship.typesCGIAR and developing country instituteen
cg.authorship.typesCGIAR and advanced research instituteen
cg.contributor.affiliationInternational Centre of Insect Physiology and Ecologyen
cg.contributor.affiliationUniversity of Kwazulu Natalen
cg.contributor.affiliationInternational Potato Centeren
cg.contributor.affiliationCentre de Coopération Internationale en Recherche Agronomique pour le Développementen
cg.contributor.donorDeutscher Akademischer Austauschdiensten
cg.contributor.donorEuropean Unionen
cg.contributor.donorNorwegian Agency for Development Cooperationen
cg.contributor.donorAustralian Centre for International Agricultural Researchen
cg.contributor.donorFederal Democratic Republic of Ethiopiaen
cg.contributor.donorGovernment of the Republic of Kenyaen
cg.contributor.donorCentre de Coopération Internationale en Recherche Agronomique pour le Développementen
cg.coverage.countryUganda
cg.coverage.iso3166-alpha2UG
cg.coverage.regionAfrica
cg.creator.identifierBester Tawona Mudereri: 0000-0001-9407-7890en
cg.creator.identifierElfatih Mohamed Abdel-Rahman: 0000-0002-5694-0291en
cg.creator.identifierOnisimo Mutanga: 0000-0002-7358-8111en
cg.creator.identifierNatacha Motisi: 0000-0001-8313-6728en
cg.creator.identifierFabrice Pinard: 0009-0002-9577-9231en
cg.creator.identifierHenri TONNANG: 0000-0002-9424-9186en
cg.howPublishedFormally Publisheden
cg.identifier.doihttps://doi.org/10.1117/1.jrs.18.044503en
cg.isijournalISI Journalen
cg.issn1931-3195en
cg.issue4en
cg.journalJournal of Applied Remote Sensingen
cg.reviewStatusPeer Reviewen
cg.subject.actionAreaResilient Agrifood Systems
cg.subject.actionAreaSystems Transformation
cg.subject.cipBIGDATAen
cg.subject.cipCLIMATE-SMART AGRICULTUREen
cg.subject.cipCROP AND SYSTEMS SCIENCES CSSen
cg.subject.cipFOOD SYSTEMSen
cg.subject.cipCLIMATE CHANGEen
cg.subject.impactAreaClimate adaptation and mitigation
cg.subject.impactAreaEnvironmental health and biodiversity
cg.subject.sdgSDG 2 - Zero hungeren
cg.subject.sdgSDG 12 - Responsible consumption and productionen
cg.subject.sdgSDG 13 - Climate actionen
cg.subject.sdgSDG 15 - Life on landen
cg.volume18en
dc.contributor.authorKebede, G.en
dc.contributor.authorMudereri, B.T.en
dc.contributor.authorAbdel-Rahman, E.M.en
dc.contributor.authorMutanga, O.en
dc.contributor.authorLandmann, T.en
dc.contributor.authorOdindi, J.en
dc.contributor.authorMotisi, N.en
dc.contributor.authorPinard, F.en
dc.contributor.authorTonnang, H.E.Z.en
dc.date.accessioned2025-02-19T20:13:57Zen
dc.date.available2025-02-19T20:13:57Zen
dc.identifier.urihttps://hdl.handle.net/10568/173235
dc.titleDiscriminating Robusta coffee (Coffea canephora) cropping systems using leaf-level hyperspectral dataen
dcterms.abstractThe coffee agro-ecosystems are increasingly being transformed into small-scale coffee-growing agricultural systems. In this context, the challenge of accurately classifying coffee cropping systems (CSs) becomes more significant, particularly in regions such as Uganda where dense vegetation and diverse topography complicate traditional land surveys. We harness the capabilities of remote sensing to provide hyperspectral data crucial for distinguishing between various coffee CSs and other land covers. Specifically, we focus on the spectral analysis of three types of Robusta coffee CSs—those integrating agroforestry, those combined with banana cultivation, and those in full sun exposure. Using in situ hyperspectral measurements captured by the FieldSpec 2™ spectroradiometer across the 325 to 1075 nm range of the electromagnetic spectrum, we aimed to (1) analyze the unique spectral properties and behaviors of these Robusta coffee CSs and (2) effectively discriminate among them using advanced hyperspectral datasets alongside the machine learning (ML) classification algorithms. The key to this process was the use of narrow spectral bands (NSBs) and various narrow-band vegetation indices (VIs), serving as predictor variables. A selection of critical variables (NSB = 9 and VIs = 8) was identified through the guided regularized random forest (RF) technique and then applied to four ML algorithms—RF, stochastic gradient boosting (GB), linear discriminant analysis, and support vector machine for classification experiments. The findings indicated high discrimination accuracy, with the RF and GB algorithms achieving overall accuracies of 93% and 90.5%, respectively, when using the selected VIs, and 87.3% (RF) and 83% (GB) when applying the chosen NBSs. These results underline the efficacy of integrating hyperspectral datasets and ML algorithms in reliably categorizing Robusta coffee CSs, a crucial step toward enhancing sustainable coffee cultivation practices.en
dcterms.accessRightsLimited Access
dcterms.audienceAcademicsen
dcterms.audienceCGIARen
dcterms.audienceDevelopment Practitionersen
dcterms.audienceDonorsen
dcterms.audienceExtensionen
dcterms.audienceFarmersen
dcterms.audienceGeneral Publicen
dcterms.audienceNGOsen
dcterms.audiencePolicy Makersen
dcterms.audienceScientistsen
dcterms.available2024-10-04en
dcterms.bibliographicCitationKebede, G.; Mudereri, B.T.; Abdel-Rahman, E.M.; Mutanga, O.; Landmann, T.; Odindi, J.; Motisi, N.; Pinard, F.; Tonnang, H.E.Z. 2024. Discriminating Robusta coffee (Coffea canephora) cropping systems using leaf-level hyperspectral data. Journal of Applied Remote Sensing. ISSN 1931-3195. 18(04). https://doi.org/10.1117/1.jrs.18.044503en
dcterms.issued2025-02-11en
dcterms.languageen
dcterms.licenseCopyrighted; all rights reserved
dcterms.subjectmachine learningen
dcterms.subjectagroforestryen
dcterms.subjectcropping systemsen
dcterms.typeJournal Article

Files

License bundle

Now showing 1 - 1 of 1
Thumbnail Image
Name:
license.txt
Size:
1.75 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

CIP Journal Articles
CIP Science Goal: Regenerative Agriculture