Mostrar el registro sencillo del ítem
dc.contributor.author
Rossit, Daniel Alejandro
dc.contributor.author
Olivera, Alejandro
dc.contributor.author
Viana-Céspedes, Víctor
dc.contributor.author
Broz, Diego Ricardo
dc.date.available
2024-04-08T16:11:13Z
dc.date.issued
2024-03-18
dc.identifier.citation
Rossit, Daniel Alejandro; Olivera, Alejandro; Viana-Céspedes, Víctor; Broz, Diego Ricardo; Forest harvest operations productivity forecasting: a decisions tree approach; Taylor & Francis; International Journal of Forest Engineering; 18-3-2024; 1-13
dc.identifier.issn
1494-2119
dc.identifier.uri
http://hdl.handle.net/11336/232419
dc.description.abstract
In recent years, the machinery used in forest harvesting operations has incorporated the ability to collect data during the harvesting operation automatically. The processing of these data allows for obtaining new perspectives on the harvest characteristics. In this sense, it is that the development of predictive models for harvest productivity is approached by processing the automatically retrieved data. In turn, these new models pave the way to develop new tools for operations management decision-making processes, providing a data-driven approach. In this case, forest productivity is analyzed based on different harvesting operational configurations defined by stand, trees, species, operators, shifts, etc., which make it possible to adequately predict what the wood-harvested volume will be, and thus, synchronize the rest of the supply chain logistics operations. The data processing is done through decision tree methods. Different methods of decision trees based on exhaustive CHAID, recursive binary partition, and conditional inference based that also uses binary recursive partition are tested. The results show that decision recursive binary partition methods tend to model more balanced the entire spectrum of the target variable more. While exhaustive CHAID-based methods tend to be more accurate in global terms but more unbalanced. As a general comment for the method, global confusion matrices are around 50% of accuracy, and some operational configurations and productivity classes are predicted with almost 90% of accuracy.
dc.format
application/pdf
dc.language.iso
eng
dc.publisher
Taylor & Francis
dc.rights
info:eu-repo/semantics/restrictedAccess
dc.rights.uri
https://creativecommons.org/licenses/by-nc-sa/2.5/ar/
dc.subject
MACHINE LEARNING
dc.subject
FOREST HARVEST PRODUCTIVITY
dc.subject
BINARY RECURSIVE PARTITION
dc.subject
OPERATIONS MANAGEMENT
dc.subject
DATA-DRIVEN
dc.subject
OPERATIONS PLANNING
dc.subject.classification
Otras Ingenierías y Tecnologías
dc.subject.classification
Otras Ingenierías y Tecnologías
dc.subject.classification
INGENIERÍAS Y TECNOLOGÍAS
dc.title
Forest harvest operations productivity forecasting: a decisions tree approach
dc.type
info:eu-repo/semantics/article
dc.type
info:ar-repo/semantics/artículo
dc.type
info:eu-repo/semantics/publishedVersion
dc.date.updated
2024-04-08T14:18:39Z
dc.identifier.eissn
1913-2220
dc.journal.pagination
1-13
dc.journal.pais
Reino Unido
dc.journal.ciudad
London
dc.description.fil
Fil: Rossit, Daniel Alejandro. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Bahía Blanca. Instituto de Matemática Bahía Blanca. Universidad Nacional del Sur. Departamento de Matemática. Instituto de Matemática Bahía Blanca; Argentina. Universidad Nacional del Sur. Departamento de Ingeniería; Argentina
dc.description.fil
Fil: Olivera, Alejandro. Universidad de la República; Uruguay
dc.description.fil
Fil: Viana-Céspedes, Víctor. Universidad de la República; Uruguay
dc.description.fil
Fil: Broz, Diego Ricardo. Universidad Nacional de Misiones. Facultad de Ciencias Forestales; Argentina
dc.journal.title
International Journal of Forest Engineering
dc.relation.alternativeid
info:eu-repo/semantics/altIdentifier/url/https://www.tandfonline.com/doi/full/10.1080/14942119.2024.2327243?src=exp-la
dc.relation.alternativeid
info:eu-repo/semantics/altIdentifier/url/https://doi.org/10.1080/14942119.2024.2327243
Archivos asociados