Use este identificador para citar ou linkar para este item: http://www.alice.cnptia.embrapa.br/alice/handle/doc/1187068
Registro completo de metadados
Campo DCValorIdioma
dc.contributor.authorFONTENELLE, M. R.
dc.contributor.authorGUEDES, I. M. R.
dc.contributor.authorSUINAGA, F. A.
dc.contributor.authorSILVA, J. da
dc.contributor.authorBRAGA, M. B.
dc.contributor.authorMARTINS, S. C. V.
dc.contributor.authorLIMA, C. E. P.
dc.date.accessioned2026-05-25T21:13:25Z-
dc.date.available2026-05-25T21:13:25Z-
dc.date.created2026-05-25
dc.date.issued2026
dc.identifier.citationRevista DCS, V. 23, n. 90, p.1-24, 2026.
dc.identifier.issn224-4131
dc.identifier.urihttp://www.alice.cnptia.embrapa.br/alice/handle/doc/1187068-
dc.descriptionIn this context, low-cost digital technologies capable of democratizing access to technical and scientific tools are essential to enhance the resilience and adaptive capacity of vegetable production systems. This study aimed to develop and validate low-cost lettuce phenotyping platforms powered by generative artificial intelligence (AI), focusing on thermal physiological disorders, using Prompt Engineering and Prompt Chaining as core methodologies. The framework comprised: (i) compilation and mapping of climate information and thermal risk/severity for lettuce in Brazil; (ii) identification of key physiological disorders expected under GCC scenarios based on Lima et al.(2024) and a systematic literature review; (iii) design of an analytical pipeline using Prompt Engineering and Prompt Chaining for generative Ais; and (iv) extraction of Python scripts and generation of SHA-256 hash codes in Visual Studio Code (VSC), followed by validation through comparison between AI-generated reports and the reference results of Lima et al.(2024). The resulting set of scripts reproduced, with high consistency, the patterns reported in the benchmark study and were made publicly available under FAIR principles. These results represent an important tool to accelerate the development of technological solutions for increasing resilience and climate adaptation in Brazilian lettuce production, while remaining replicable and adaptable via open-source code to other regions of the world.
dc.language.isoeng
dc.rightsopenAccess
dc.subjectInteligência artificial
dc.subjectFenotipagem
dc.titleLow-cost lettuce phenotyping platforms powered by generative AI: development, validation, and methodological democratization for climate-just brazilian lettuce crops.
dc.typeArtigo de periódico
dc.subject.thesagroMudança Climática
dc.subject.thesagroHortaliça
dc.subject.thesagroAlface
dc.subject.thesagroTecnologia da Informação
dc.subject.thesagroResistência
riaa.ainfo.id1187068
riaa.ainfo.lastupdate2026-05-25
dc.contributor.institutionMARIANA RODRIGUES FONTENELLE, CNPH; ITALO MORAES ROCHA GUEDES, CNPH; FABIO AKIYOSHI SUINAGA, CNPH; JUSCIMAR DA SILVA, CNPH; MARCOS BRANDAO BRAGA, CNPH; SAMUEL CORDEIRO VITOR MARTINS, CNPH; CARLOS EDUARDO PACHECO LIMA, CNPH.
Aparece nas coleções:Artigo em periódico indexado (CNPH)

Arquivos associados a este item:
Arquivo Descrição TamanhoFormato 
CNPH-42433-AP.pdf1,06 MBAdobe PDFThumbnail
Visualizar/Abrir
Mostrar registro simples do item Visualizar estatísticas

FacebookTwitterDeliciousLinkedInGoogle BookmarksMySpace