Using explainable machine learning techniques to unpack farm-level management x climate interactions

Simple item page
cg.authorship.typesCGIAR multi-centreen
cg.contributor.affiliationInternational Center for Tropical Agricultureen
cg.contributor.affiliationInternational Maize and Wheat Improvement Centeren
cg.contributor.donorCGIAR Trust Funden
cg.contributor.initiativeAgriLAC Resiliente
cg.coverage.countryGuatemala
cg.coverage.iso3166-alpha2GT
cg.coverage.regionAmericas
cg.coverage.regionCentral America
cg.coverage.regionLatin America and the Caribbean
cg.creator.identifierJulian Ramirez-Villegas: 0000-0002-8044-583Xen
cg.creator.identifierLizeth Llanos-Herrera: 0000-0003-3540-7348en
cg.creator.identifierDaniel Jiménez: 0000-0003-4218-4306en
cg.creator.identifierAndrea Gardeazábal-Monsalve: 0000-0003-1529-4200en
cg.subject.actionAreaResilient Agrifood Systems
cg.subject.alliancebiovciatAGRICULTUREen
cg.subject.alliancebiovciatCLIMATE CHANGEen
cg.subject.alliancebiovciatCLIMATE CHANGE ADAPTATIONen
cg.subject.alliancebiovciatFARMING SYSTEMSen
cg.subject.impactAreaClimate adaptation and mitigation
cg.subject.sdgSDG 1 - No povertyen
cg.subject.sdgSDG 2 - Zero hungeren
cg.subject.sdgSDG 13 - Climate actionen
dc.contributor.authorRamírez Villegas, Julián Armandoen
dc.contributor.authorJaimes, Dianaen
dc.contributor.authorGonzalez Rodriguez, Carlos Eduardoen
dc.contributor.authorLlanos, Lizethen
dc.contributor.authorJimenez, Danielen
dc.contributor.authorGardeazabal, Andreaen
dc.contributor.authorEstrada, Oscaren
dc.contributor.authorNuñez, Danielen
dc.date.accessioned2023-12-01T10:39:40Zen
dc.date.available2023-12-01T10:39:40Zen
dc.identifier.urihttps://hdl.handle.net/10568/134910
dc.titleUsing explainable machine learning techniques to unpack farm-level management x climate interactionsen
dcterms.abstractOptimizing the management of maize production systems, including the milpa (intercropping of maize with beans and other species), is crucial for improving on-farm productivity and ultimately reducing food insecurity. This presentation showcases the results of a study aimed at identifying determinants of maize yield in Guatemala using agronomic and climate data. The study employs interpretability techniques in machine learning to explain the interactions between climatic factors and crop management in productivity. The study follows a three-step approach: (1) an Extract, Transform, Load (ETL) process of data, involving feature engineering and data standardization and cleaning; (2) identification of algorithms, metrics, and algorithmic tuning; and (3) delving into interpretability using techniques such as SHAP (SHapley Additive exPlanations), partial dependence plots (PDP), accumulated local effects (ALE) plots, and Friedman's H-statistic to evaluate interactions between featuresen
dcterms.accessRightsOpen Access
dcterms.bibliographicCitationRamirez Villegas, J.; Jaimes, D.; Gonzalez, C.; Llanos, L.; Jimenez, D.; Gardeazabal, A.; Estrada, O.; Nuñez, D. (2023) Using explainable machine learning techniques to unpack farm-level management x climate interactions. Presentation prepared from impact to solutions, data, data science and machine learning for climate adaptation at Wageningen University & Research. 26-28 November 2023. 14 sl.en
dcterms.extent14 sl.en
dcterms.issued2023-11-27en
dcterms.languageen
dcterms.licenseCC-BY-4.0
dcterms.subjectagronomic practicesen
dcterms.subjectadaptación al cambio climáticoen
dcterms.subjectmachine learningen
dcterms.subjectadaptationen
dcterms.subjectclimateen
dcterms.subjectagronomyen
dcterms.subjectagronomíaen
dcterms.subjectweatheren
dcterms.subjectprácticas agronómicasen
dcterms.subjecttiempoen
dcterms.subjectestadística como cienciaen
dcterms.typePresentation

Files

Original bundle

Now showing 1 - 1 of 1
Thumbnail Image
Name:
jrv_XIA-usecase-BM...pdf
Size:
4.63 MB
Format:
Adobe Portable Document Format
Description:
Download

Collections

Alliance Bioversity CIAT Posters, Presentations, and Infographics
Alliance Research Lever 3: Climate Action
Alliance Research Lever 5: Digital Inclusion
CGIAR Initiative on AgriLAC Resiliente
CIMMYT Presentations