KMFRI Website

Publication:
Automated classification of schools of the silver cyprinid Rastrineobola argentea in Lake Victoria acoustic survey data using random forests

dc.contributor.authorProud, R.
dc.contributor.authorMangeni-Sande, R.
dc.contributor.authorKayanda, R. J.
dc.contributor.authorCox, M. J.
dc.contributor.authorNyamweya, C. S.
dc.contributor.authorOngore, C. O.
dc.contributor.authorNatugonza, V.
dc.contributor.authorEverson, I.
dc.contributor.authorElison, M.
dc.contributor.authorHobbs, L.
dc.contributor.authorKashindye, B. B.
dc.contributor.authorMlaponi, E. W.
dc.contributor.authorTaabu-Munyaho, A.
dc.contributor.authorMwainge, V.
dc.contributor.authorKagoya, E.
dc.contributor.authorPegado, A.
dc.contributor.authorNduwayesu, E.
dc.contributor.authorBrierley, A. S.
dc.contributor.editorGodo, O.
dc.coverage.spatialKenya
dc.date.accessioned2026-11-12T09:15:24Z
dc.date.issued2020-05-09
dc.description.abstractBiomass of the schooling fish Rastrineobola argentea (dagaa) is presently estimated in Lake Victoria by acoustic survey following the simple “rule” that dagaa is the source of most echo energy returned from the top third of the water column. Dagaa have, however, been caught in the bottom two-thirds, and other species occur towards the surface: a more robust discrimination technique is required. We explored the utility of a school-based random forest (RF) classifier applied to 120 kHz data from a lake-wide survey. Dagaa schools were first identified manually using expert opinion informed by fishing. These schools contained a lake-wide biomass of 0.68 million tonnes (MT). Only 43.4% of identified dagaa schools occurred in the top third of the water column, and 37.3% of all schools in the bottom two-thirds were classified as dagaa. School metrics (e.g. length, echo energy) for 49 081 manually classified dagaa and non-dagaa schools were used to build an RF school classifier. The best RF model had a classification test accuracy of 85.4%, driven largely by school length, and yielded a biomass of 0.71 MT, only c. 4% different from the manual estimate. The RF classifier offers an efficient method to generate a consistent dagaa biomass time series.
dc.description.sponsorshipScottish Funding Council Global Challenge Research Fund
dc.description.sponsorshipGCRF
dc.description.sponsorshipUniversity of St Andrews
dc.description.sponsorshipUniversity of Strathclyde
dc.description.sponsorshipGCRF Networking Grant
dc.description.sponsorshipUK Academy of Medical Sciences (grant GCRFNG\100371)
dc.description.sponsorshipRoyal Society International Collaboration Award
dc.description.sponsorshipRhoda Tumwebaze (grant ICA\R1\180123)
dc.identifier.citationProud, R., Mangeni-Sande, R., Kayanda, R. J., Cox, M. J., Nyamweya, C., Ongore, C., Natugonza, V., Everson, I., Elison, M., Hobbs, L., Kashindye, B. B., Mlaponi, E. W., Taabu-Munyaho, A., Mwainge, V. M., Kagoya, E., Pegado, A., Nduwayesu, E., & Brierley, A. S. (2020). Automated classification of schools of the silver cyprinid Rastrineobola argentea in Lake Victoria acoustic survey data using random forests. ICES Journal of Marine Science, 77(4), 1379–1390. https://doi.org/10.1093/icesjms/fsaa052
dc.identifier.doi10.1093/icesjms/fsaa052
dc.identifier.issn1095-9289
dc.identifier.urihttps://repository.kmfri.go.ke/handle/123456789/1954
dc.language.isoen
dc.publisherOxford University Press (OUP)
dc.relation.ispartofICES Journal of Marine Science
dc.relation.urihttps://doi.org/10.1093/icesjms/fsaa052
dc.rightsCC BY 4.0
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/
dc.subjectRastrineobola argentea
dc.subjectfish schooling
dc.subjectrandom forest
dc.subjectacoustic biomass estimation
dc.subjectLake Victoria
dc.subjectfish stock assessment
dc.titleAutomated classification of schools of the silver cyprinid Rastrineobola argentea in Lake Victoria acoustic survey data using random forests
dc.typeJournal article
dspace.entity.typePublication
oaire.citation.endPage1390
oaire.citation.issue4
oaire.citation.startPage1379
oaire.citation.volume77
person.identifier.orcid0000-0002-7135-7379
person.identifier.orcid0000-0002-0087-9268
person.identifier.orcid0000-0002-2260-0782
relation.isAuthorOfPublicationa669b997-181d-4369-9e45-6715fd0f0d1e
relation.isAuthorOfPublication3d65aa6f-a79f-4f67-b6c9-4383bcfbeb98
relation.isAuthorOfPublicationd5b1957c-ab5e-4ada-94ae-301d54d37579
relation.isAuthorOfPublication.latestForDiscoveryd5b1957c-ab5e-4ada-94ae-301d54d37579

Files

Collections