Logo do repositório
 
Publicação

Validation of Early Vineyard Yield Estimation

2026-07Póster em conferência Acesso aberto
Ver registo simples
dc.contributor.authorSantos Costa, Diogo
dc.contributor.institutionNOVA Information Management School (NOVA IMS)
dc.contributor.institutionInformation Management Research Center (MagIC) - NOVA Information Management School
dc.date.accessioned2026-07-10T13:46:01Z
dc.date.available2026-07-10T13:46:01Z
dc.date.issued2026-07
dc.descriptionhttps://doi.org/10.54499/2024.07551.IACDC Santos Costa, D. (2026). Validation of Early Vineyard Yield Estimation: Comparing Leave-One-Year-Out and Walk-Forward Back-Testing in the Douro Demarcated Region. Poster session presented at Data Research Meetup by MagIC, 4th ed, Lisboa, Portugal. https://doi.org/10.34619/jlrs-lqw1
dc.description.abstractReliable early season vineyard yield estimation is increasingly important for planning, quota interpretation and regulatory decision support in wine regions exposed to strong interannual variability. However, the practical value of a predictive model depends not only on its error metrics, but also on the realism of the validation design used to assess its performance. This study evaluates an open data Long Short-Term Memory (LSTM) neural network pipeline for parish level wine grape yield estimation in the Douro Demarcated Region (DDR), comparing Leave-One-Year-Out (LOYO) validation with Walk-Forward (WF) back-testing. The modelling workflow combines Sentinel-derived Normalised Difference Vegetation Index (NDVI) time series with open-access gridded climate variables from AgERA5 and CHIRPS. Estimates are assessed across two early seasonal windows, flowering and veraison, and across multiple territorial levels, from parishes to sub-regions and the whole DDR. LOYO is used as a benchmark-oriented validation strategy that enables comparison across years, while WF imposes a stricter chronological structure in which each target year is estimated using only information available from previous campaigns. The comparison shows how validation design can change the interpretation of model readiness. LOYO supports methodological benchmarking and model comparison, whereas WF provides a more operationally realistic assessment of temporal generalisation. By making this distinction explicit, the study strengthens the methodological credibility of AI-based vineyard yield estimation and contributes to more transparent decision support for precision viticulture and regional wine governance.en
dc.description.versionpublishersversion
dc.description.versionpublished
dc.format.extent1
dc.format.extent1190416
dc.identifier.doi10.34619/jlrs-lqw1
dc.identifier.otherPURE: 164974853
dc.identifier.otherPURE UUID: ca627859-f74b-491b-90b7-0f343fc99410
dc.identifier.urihttp://hdl.handle.net/10362/204437
dc.language.isoeng
dc.peerreviewedno
dc.relationhttps://doi.org/10.54499/UID/04152/2025
dc.relationhttps://doi.org/10.54499/UID/PRR/04152/2025
dc.subjectVineyard Yield Estimation
dc.subjectLSTM Neural Networks
dc.subjectModel evaluation
dc.subjectSDG 2 - Zero Hunger
dc.subjectSDG 9 - Industry, Innovation, and Infrastructure
dc.subjectSDG 13 - Climate Action
dc.titleValidation of Early Vineyard Yield Estimationen
dc.title.subtitleComparing Leave-One-Year-Out and Walk-Forward Back-Testing in the Douro Demarcated Regionen
dc.typeconference poster
degois.publication.issue4
degois.publication.titleData Research Meetup by MagIC, 4th ed
dspace.entity.typePublication
rcaap.rightsopenAccess

Ficheiros

Principais
A mostrar 1 - 1 de 1
Miniatura
Nome:
MeetUp_Validation_of_Early_Vineyard_Yield_Estimation.pdf
Tamanho:
1.14 MB
Formato:
Adobe Portable Document Format
Ver/Abrir

Coleções

NIMS: MagIC - Documentos de conferências nacionais