Predicting high-magnitude, low-frequency crop losses using machine learning: An application to cereal crops in Ethiopia

Simple item page
cg.authorship.typesCGIAR single centreen
cg.contributor.crpPolicies, Institutions, and Markets
cg.contributor.donorUnited States Agency for International Developmenten
cg.contributor.donorDepartment for International Development, United Kingdomen
cg.contributor.donorEuropean Unionen
cg.coverage.countryEthiopia
cg.coverage.iso3166-alpha2ET
cg.coverage.regionAfrica
cg.coverage.regionSub-Saharan Africa
cg.coverage.regionEastern Africa
cg.creator.identifierJames Warner: 0000-0002-5768-3004
cg.identifier.doihttps://doi.org/10.2499/1046080770en
cg.identifier.projectIFPRI - Markets, Trade, and Institutions Division
cg.identifier.projectIFPRI - Development Strategy and Governance Division
cg.identifier.projectIFPRI - Ethiopia Strategy Support Program
cg.identifier.publicationRankNot ranked
cg.number120en
cg.placeWashington, DCen
cg.placeAddis Ababa, Ethiopiaen
cg.reviewStatusInternal Reviewen
dc.contributor.authorMann, Michael L.en
dc.contributor.authorMalik, Arun S.en
dc.contributor.authorWarner, Jamesen
dc.date.accessioned2024-06-21T09:04:43Zen
dc.date.available2024-06-21T09:04:43Zen
dc.identifier.urihttps://hdl.handle.net/10568/145591
dc.titlePredicting high-magnitude, low-frequency crop losses using machine learning: An application to cereal crops in Ethiopiaen
dcterms.abstractTimely and accurate agricultural impact assessments for droughts are critical for designing appropriate interventions and policy. These assessments are often ad hoc, late, or spatially imprecise, with reporting at the zonal or regional level. This is problematic as we find substantial variability in losses at the village-level that are missing when reporting even at the zonal level. In this paper we propose a new data fusion method combining remotely-sensed data with agricultural survey data that might address these limitations. We apply the method to Ethiopia, which is regularly hit by droughts and is a substantial recipient of ad hoc imported food aid. We then utilize remotely-sensed data obtained near mid-season to predict substantial crop losses of greater than or equal to 25 percent due to drought at the village level for five primary cereal crops. We train machine learning models to predict the likelihood of losses and explore the most influential variables. On independent samples, the models identify substantial drought loss cases with up to 70 percent accuracy by mid- to late-September. We believe the proposed models could be used to help monitor and predict yields for disaster response teams and policy makers, particularly with further development of the models and integration of newly available high resolution remotely-sensed data, such as the Harmonized Landsat Sentinel (HLS) data set.en
dcterms.accessRightsOpen Access
dcterms.bibliographicCitationMann, Michael; Warner, James M.; and Malik, Arun S. 2018. Predicting high-magnitude, low-frequency crop losses using machine learning: An application to cereal crops in Ethiopia. ESSP Working Paper 120. Washington, DC and Addis Ababa, Ethiopia: International Food Policy Research Institute (IFPRI) and Ethiopian Development Research Institute (EDRI). https://hdl.handle.net/10568/145591en
dcterms.extent25 pagesen
dcterms.isPartOfESSP Working Paperen
dcterms.issued2018-07-25
dcterms.languageen
dcterms.publisherInternational Food Policy Research Instituteen
dcterms.publisherEthiopian Development Research Instituteen
dcterms.replaceshttps://ebrary.ifpri.org/digital/collection/p15738coll2/id/132765en
dcterms.subjectweather hazardsen
dcterms.subjectshocken
dcterms.subjectsurveysen
dcterms.subjectmachine learningen
dcterms.subjectdroughten
dcterms.subjectcereal cropsen
dcterms.subjectcrop lossesen
dcterms.subjectresilienceen
dcterms.subjectimpact assessmenten
dcterms.typeWorking Paper

Files

Original bundle

Now showing 1 - 1 of 1
Thumbnail Image
Name:
132976.pdf
Size:
795.23 KB
Format:
Adobe Portable Document Format
Description:
Working Paper
Download

Collections

IFPRI Project Papers
IFPRI Co-Publishing