Towards site and context-specific fertilizer recommendations for maize production in Northern Ghana using AgWise framework (Machine learning component)

Simple item page
cg.authorship.typesCGIAR and developing country institute
cg.contributor.affiliationInternational Center for Tropical Agriculture
cg.contributor.affiliationCouncil for Scientific and Industrial Research
cg.contributor.donorWorld Bank
cg.contributor.donorCGIAR Trust Fund
cg.contributor.initiativeExcellence in Agronomy
cg.coverage.countryGhana
cg.coverage.iso3166-alpha2GH
cg.coverage.regionAfrica
cg.coverage.regionWestern Africa
cg.coverage.regionSub-Saharan Africa
cg.creator.identifierAbdul-Latif Baamonyor Jizorkuwie: 0000-0003-3676-4443
cg.creator.identifierIsaac Boatey Akpatsu: 0000-0002-9416-9071
cg.creator.identifierWuletawu Abera: 0000-0002-3657-5223
cg.subject.actionAreaResilient Agrifood Systems
cg.subject.alliancebiovciatAGRICULTURE
cg.subject.alliancebiovciatCROP PRODUCTION
cg.subject.alliancebiovciatFOOD SECURITY
cg.subject.alliancebiovciatSOIL HEALTH
cg.subject.impactAreaClimate adaptation and mitigation
cg.subject.impactAreaEnvironmental health and biodiversity
cg.subject.sdgSDG 1 - No poverty
cg.subject.sdgSDG 2 - Zero hunger
cg.subject.sdgSDG 15 - Life on land
dc.contributor.authorJizorkuwie, Abdul-latif Baamonyor
dc.contributor.authorTilaye, Asmalu
dc.contributor.authorAmankwa-Yeboah, Patricia
dc.contributor.authorAssefa, Feben
dc.contributor.authorMasoud, Jalaludeen
dc.contributor.authorAkpatsu, Isaac Boatey
dc.contributor.authorAbera, Wuletawu
dc.date.accessioned2024-12-03T10:43:04Zen
dc.date.available2024-12-03T10:43:04Zen
dc.identifier.urihttps://hdl.handle.net/10568/162966
dc.titleTowards site and context-specific fertilizer recommendations for maize production in Northern Ghana using AgWise framework (Machine learning component)en
dcterms.abstractAgroadvisory services play vital roles in promoting sustainable and productive agricultural practices, particularly in areas that experience fluctuations in climate and limited resources. In Ghana, the Alliance of Bioversity International & CIAT in collaboration with IITA and CSIR aims integrate input supply, insurance, and advisory services as a bundle that provides holistic support to enhance productivity and mitigate the risks associated with maize cultivation. This study aims to improve advisory services concerning fertilizer use by maize farmers from the Guinea Savannah zone of Ghana. The objective is to generate recommendations that are tailored to specific areas as current practice or recommended rates a based on current and legacy soil tests and experiments datasets. Site and context-specific fertilizer recommendations were generated using the AgWise framework. More than 1,740 data points were gathered from scientific publications, field trials and crop cut surveys and used in the model development. To ensure precision, only studies that reported site-specific trial locations were included, with data gathered on nitrogen, phosphorus, and potassium application and their effects on maize yield. To build robust models, a thorough exploration of the extracted covariate data was conducted, encompassing soil characteristics, climate patterns, and topography. After careful pre-processing, a dataset ready for model training was obtained, containing 1532 observations and 47 data columns. The modeling process utilized the H2O package within RStudio. H2O's AutoML functionality was employed to streamline the workflow. A total of ten models were trained using AutoML, and the most promising ones from the output were selected for additional refinement. These included Random Forest (RF), Gradient Boosting Machine (GBM), Deep Learning Artificial Neural Network (ANN), and Generalized Linear Models (GLM). The random forest model emerged as the top performer through rigorous evaluation, based on MAE, RMSE, and R², which was utilized in the prediction. Analysis revealed that nitrogen application rate, soil characteristics, and climatic conditions are the primary determinants of maize yield. Preliminary results indicate significant variability in fertilizer requirements across different districts, reinforcing the need for data-driven, context-specific recommendations. The model successfully generated preliminary fertilizer recommendations for nitrogen (30–140 kg/ha), phosphorus (10–35 kg/ha), and potassium (0–40 kg/ha) across various districts. Expanding the dataset and refining the model will further enhance these recommendations, supporting maize growth, improving yields, boosting farmer productivity, and reducing production risks in Ghana.en
dcterms.accessRightsOpen Access
dcterms.bibliographicCitationJizorkuwie, A.B.; Tilaye, A.; Amankwa-Yeboah, P.; Assefa, F.; Masoud, J.; Akpatsu, I.B.; Abera, W.. (2024) Towards site and context-specific fertilizer recommendations for maize production in Northern Ghana using AgWise framework (Machine learning component). 34 p.en
dcterms.extent34 p.
dcterms.issued2024-11-22
dcterms.languageen
dcterms.licenseCC-BY-4.0
dcterms.subjectsoil fertilityen
dcterms.subjectproductivityen
dcterms.subjectsite-specific nutrient managementen
dcterms.typeReport

Files

Original bundle

Now showing 1 - 1 of 1
Thumbnail Image
Name:
report.pdf
Size:
1.61 MB
Format:
Adobe Portable Document Format
Download

Collections

Alliance Bioversity CIAT Reports
Alliance Research Area 2: Multifunctional Landscapes
CGIAR Initiative on Excellence in Agronomy