Predicting malaria prevalence with machine learning models using satellite-based climate information: technical report

Simple item page
cg.contributor.affiliationInternational Water Management Instituteen
cg.contributor.donorCGIAR Trust Funden
cg.contributor.initiativeClimate Resilience
cg.coverage.countrySenegal
cg.coverage.iso3166-alpha2SN
cg.coverage.regionWestern Africa
cg.creator.identifierMahesh Jampani: 0000-0002-8925-719Xen
cg.creator.identifierShweta Panjwani: 0000-0002-5558-5830en
cg.creator.identifierGiriraj Amarnath: 0000-0002-7390-9800en
cg.identifier.iwmilibraryH052669en
cg.placeColombo, Sri Lankaen
dc.contributor.authorIleperuma, Kaveeshaen
dc.contributor.authorJampani, Maheshen
dc.contributor.authorSellahewa, Uvinduen
dc.contributor.authorPanjwani, Shwetaen
dc.contributor.authorAmarnath, Girirajen
dc.date.accessioned2024-02-15T06:43:36Zen
dc.date.available2024-02-15T06:43:36Zen
dc.identifier.urihttps://hdl.handle.net/10568/139414
dc.titlePredicting malaria prevalence with machine learning models using satellite-based climate information: technical reporten
dcterms.abstractThe current report presents a machine learning model developed to predict malaria prevalence based on rainfall patterns, specifically tailored to different regions within Senegal. The developed model takes into account the varying climate conditions across regions to provide a more localized and accurate prediction. The primary input parameters used for prediction include rainfall, month, and year, allowing the model to capture each region's seasonal variations and trends. This research aims to enhance the precision of malaria predictions, contributing to more effective and targeted public health measures. The model is designed to provide future forecasts, offering valuable insights into early warning signals to help anticipate and mitigate the impact of malaria outbreaks. This proactive approach enables authorities and healthcare professionals to prepare and implement preventive measures in advance, potentially reducing the severity of malaria-related issues and aiding in the allocation of resources where they are most needed. By tailoring the prediction model to the unique characteristics of each region in Senegal, the current research addresses the localized nature of malaria outbreaks, recognizing that factors such as climate, geography, and environmental conditions can significantly influence the prevalence of malaria. The integration of predictive analytics and models in public health initiatives allows for a more strategic and responsive approach to malaria management, ultimately contributing to the overall well-being of the affected communities. This report includes an explanation of the methodology used for the development of the prediction model, along with the results obtained and their implications for public health in Senegal.en
dcterms.accessRightsOpen Access
dcterms.bibliographicCitationIleperuma, Kaveesha; Jampani, Mahesh; Sellahewa, Uvindu; Panjwani, Shweta; Amarnath, Giriraj. 2023. Predicting malaria prevalence with machine learning models using satellite-based climate information: technical report. Colombo, Sri Lanka: International Water Management Institute (IWMI). CGIAR Initiative on Climate Resilience. 32p.en
dcterms.extent32p.en
dcterms.issued2023-12-01en
dcterms.languageen
dcterms.licenseCC-BY-NC-ND-4.0
dcterms.publisherInternational Water Management Institute (IWMI). CGIAR Initiative on Climate Resilienceen
dcterms.subjectmalariaen
dcterms.subjectpredictionen
dcterms.subjectmachine learningen
dcterms.subjectmodelsen
dcterms.subjectclimatic dataen
dcterms.subjectsatellite observationen
dcterms.subjectrainfall patternsen
dcterms.typeReport

Files

Original bundle

Now showing 1 - 1 of 1
Thumbnail Image
Name:
Predicting malaria prevalence with machine learning models using satellite-based climate information - Technical report.pdf
Size:
1.94 MB
Format:
Adobe Portable Document Format
Description:
Download full publication
Download

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

IWMI Reports
CGIAR Initiative on Climate Resilience
Water Risk to Development and Resilience (WR2DR)