Show simple item record

Drought vulnerability of central Sahel agrosystems: a modelling-approach based on magnitudes of changes and machine learning techniques

dc.contributor.authorHanade Houmma, I.
dc.contributor.authorEl Mansouri, L.
dc.contributor.authorGadal, S.
dc.contributor.authorFaouzi, E.
dc.contributor.authorToure, A.A.
dc.contributor.authorGarba, M.
dc.contributor.authorImani, Y.
dc.contributor.authorEl-Ayachi, M.
dc.contributor.authorHadria, R.
dc.date.accessioned2024-02-08T15:14:04Z
dc.date.available2024-02-08T15:14:04Z
dc.date.issued2023-07-24
dc.identifier.citationHanadé Houmma, I., El Mansouri, L., Gadal, S., Faouzi, E., Toure, A.A., Garba, M., ... & Hadria, R. (2023). Drought vulnerability of central Sahel agrosystems: a modelling-approach based on magnitudes of changes and machine learning techniques. International Journal of Remote Sensing, 44(14), 4262-4300.
dc.identifier.issn0143-1161
dc.identifier.urihttps://hdl.handle.net/20.500.12478/8391
dc.description.abstractAgricultural drought is a complex phenomenon with numerous consequences and negative implications for agriculture and food systems. The Sahel is frequently affected by severe droughts, leading to significant losses in agricultural yields. Consequently, assessing vulnerability to agricultural drought is essential for strengthening early warning systems. The aim of this study is to develop a new multivariate agricultural drought vulnerability index (MADVI) that combines static and dynamic factors extracted from satellite data. First, pixel temporal regression from 1981 to 2021 was applied to climatic and biophysical covariates to determine the gradients of trend magnitudes. Second, principal component analysis was applied to groups of factors that indicate the same type of vulnerability to configure the basic equation of vulnerability to agricultural drought. Then, random forest (RF), K-nearest neighbours (KNN), support vector machine (SVM) and naïve Bayes (NB) were used to predict drought vulnerability classes using the 28 factors as inputs and 708 pts of randomly distributed class labels. The results showed statistical agreement between the predicted MADVI spatial variability and the reference model (R=0.86 for RF) and its statistical relationships with the vulnerability subcomponents, with an R=0.73 with exposure to climate risk, R=0.64 with the socioeconomic sensitivity index, R=0.6 with the biophysical sensitivity index and a relatively weak correlation (R=0.21) with the physiographic sensitivity index. The overall vulnerability situation in the watershed is 21.8% extreme, 10% very high, 16.8% high, 27.7% moderate, 22.2% low and 1.5% relatively low considering the cartographic results of the predicted vulnerability classes with SVM having the best performance (accuracy=0.96, Kappa=0.95). The study is the first approach that uses the gradients of magnitudes of satellite covariate anomaly trends in multivariate modelling of vulnerability to agricultural drought. It can be easily scaled up across the Sahel region to improve early warning measures related to the impacts of agricultural drought.
dc.description.sponsorshipIslamic Development Bank
dc.format.extent4262–4300
dc.language.isoen
dc.subjectVulnerability
dc.subjectDrought
dc.subjectClimate Change
dc.subjectMachine Learning
dc.subjectSahel
dc.titleDrought vulnerability of central Sahel agrosystems: a modelling-approach based on magnitudes of changes and machine learning techniques
dc.typeJournal Article
cg.contributor.affiliationUniversité Côte d’Azur
cg.contributor.affiliationHassan II Institute of Agronomy and Veterinary, Morocco
cg.contributor.affiliationSultan Moulay Slimane University
cg.contributor.affiliationInternational Institute of Tropical Agriculture
cg.contributor.affiliationInstitut National de la Recherche Agronomique du Niger
cg.coverage.regionAfrica
cg.coverage.regionWest Africa
cg.coverage.countryNiger
cg.coverage.hubHeadquarters and Western Africa Hub
cg.isijournalISI Journal
cg.authorship.typesCGIAR and developing country institute
cg.iitasubjectClimate Change
cg.iitasubjectFood Security
cg.iitasubjectFood Systems
cg.journalInternational Journal of Remote Sensing
cg.accessibilitystatusLimited Access
cg.reviewstatusPeer Review
cg.usagerightslicenseCopyrighted; all rights reserved
cg.targetaudienceScientists
cg.identifier.doihttps://doi.org/10.1080/01431161.2023.2234094
cg.iitaauthor.identifierGarba Maman: 0000-0002-3377-3064
cg.futureupdate.requiredNo
cg.identifier.issue14
cg.identifier.volume44


Files in this item

Thumbnail
Name:
Drought vulnerability of central ...
Size:
19.08Mb
Format:
PDF
Description:
Journal Article
View/Open

This item appears in the following Collection(s)

Show simple item record