Results of using machine learning and a proximal canopy reflectance sensor to predict biomass and nutritional quality in tropical forages (Urochloa humidicola) in three different locations in Colombia

Attributes such as biomass and nutritional quality are characteristics that allow for the selection of better pastures and, therefore, for obtaining greater quantities of meat and milk from livestock feed. However, the laboratory analytical method used to calculate these attributes is inefficient fo...

Descripción completa

Detalles Bibliográficos
Autores principales: Camelo, Rodrigo Andres, Hernandez, Luis Miguel, Cardoso, Juan Andres, Jauregui, Rosa Noemi
Formato: Informe técnico
Lenguaje:Inglés
Publicado: 2025
Materias:
Acceso en línea:https://hdl.handle.net/10568/179954
_version_ 1855513804225380352
author Camelo, Rodrigo Andres
Hernandez, Luis Miguel
Cardoso, Juan Andres
Jauregui, Rosa Noemi
author_browse Camelo, Rodrigo Andres
Cardoso, Juan Andres
Hernandez, Luis Miguel
Jauregui, Rosa Noemi
author_facet Camelo, Rodrigo Andres
Hernandez, Luis Miguel
Cardoso, Juan Andres
Jauregui, Rosa Noemi
author_sort Camelo, Rodrigo Andres
collection Repository of Agricultural Research Outputs (CGSpace)
description Attributes such as biomass and nutritional quality are characteristics that allow for the selection of better pastures and, therefore, for obtaining greater quantities of meat and milk from livestock feed. However, the laboratory analytical method used to calculate these attributes is inefficient for perennial species when there are more than hundreds of plants to evaluate. Therefore, it is necessary to develop methods that allow for the characterization and selection of genotypes using non-destructive, high-throughput techniques. For this purpose, active canopy sensors such as the Crop Circle Phenom have been used, capable of measuring reflectance, structural attributes, and climatic variables. The objective of this study was to build machine learning models to predict traits such as fresh biomass (FB), dry biomass (DBM) and nutritional traits such as crude protein (CP), in Urochloa humidicola genotypes in 3 locations (Palmira, Quilichao and Villavicencio) from harvests and analytical data (direct estimation method) and measurements acquired with portable multispectral sensors.
format Informe técnico
id CGSpace179954
institution CGIAR Consortium
language Inglés
publishDate 2025
publishDateRange 2025
publishDateSort 2025
record_format dspace
spelling CGSpace1799542026-01-17T02:00:36Z Results of using machine learning and a proximal canopy reflectance sensor to predict biomass and nutritional quality in tropical forages (Urochloa humidicola) in three different locations in Colombia Camelo, Rodrigo Andres Hernandez, Luis Miguel Cardoso, Juan Andres Jauregui, Rosa Noemi remote sensing teledetección feed crops-forage crops forraje high-throughput phenotyping nutritive value-nutritional value valor nutritivo fenotipado de alto rendimiento spectral analysis análisis espectral Attributes such as biomass and nutritional quality are characteristics that allow for the selection of better pastures and, therefore, for obtaining greater quantities of meat and milk from livestock feed. However, the laboratory analytical method used to calculate these attributes is inefficient for perennial species when there are more than hundreds of plants to evaluate. Therefore, it is necessary to develop methods that allow for the characterization and selection of genotypes using non-destructive, high-throughput techniques. For this purpose, active canopy sensors such as the Crop Circle Phenom have been used, capable of measuring reflectance, structural attributes, and climatic variables. The objective of this study was to build machine learning models to predict traits such as fresh biomass (FB), dry biomass (DBM) and nutritional traits such as crude protein (CP), in Urochloa humidicola genotypes in 3 locations (Palmira, Quilichao and Villavicencio) from harvests and analytical data (direct estimation method) and measurements acquired with portable multispectral sensors. 2025-12 2026-01-16T07:16:49Z 2026-01-16T07:16:49Z Report https://hdl.handle.net/10568/179954 en Open Access application/pdf Camelo, R.A.; Hernandez, L.M.; Cardoso, J.A.; Jauregui, R.N. (2025) Results of using machine learning and a proximal canopy reflectance sensor to predict biomass and nutritional quality in tropical forages (Urochloa humidicola) in three different locations in Colombia. 18 p.
spellingShingle remote sensing
teledetección
feed crops-forage crops
forraje
high-throughput phenotyping
nutritive value-nutritional value
valor nutritivo
fenotipado de alto rendimiento
spectral analysis
análisis espectral
Camelo, Rodrigo Andres
Hernandez, Luis Miguel
Cardoso, Juan Andres
Jauregui, Rosa Noemi
Results of using machine learning and a proximal canopy reflectance sensor to predict biomass and nutritional quality in tropical forages (Urochloa humidicola) in three different locations in Colombia
title Results of using machine learning and a proximal canopy reflectance sensor to predict biomass and nutritional quality in tropical forages (Urochloa humidicola) in three different locations in Colombia
title_full Results of using machine learning and a proximal canopy reflectance sensor to predict biomass and nutritional quality in tropical forages (Urochloa humidicola) in three different locations in Colombia
title_fullStr Results of using machine learning and a proximal canopy reflectance sensor to predict biomass and nutritional quality in tropical forages (Urochloa humidicola) in three different locations in Colombia
title_full_unstemmed Results of using machine learning and a proximal canopy reflectance sensor to predict biomass and nutritional quality in tropical forages (Urochloa humidicola) in three different locations in Colombia
title_short Results of using machine learning and a proximal canopy reflectance sensor to predict biomass and nutritional quality in tropical forages (Urochloa humidicola) in three different locations in Colombia
title_sort results of using machine learning and a proximal canopy reflectance sensor to predict biomass and nutritional quality in tropical forages urochloa humidicola in three different locations in colombia
topic remote sensing
teledetección
feed crops-forage crops
forraje
high-throughput phenotyping
nutritive value-nutritional value
valor nutritivo
fenotipado de alto rendimiento
spectral analysis
análisis espectral
url https://hdl.handle.net/10568/179954
work_keys_str_mv AT camelorodrigoandres resultsofusingmachinelearningandaproximalcanopyreflectancesensortopredictbiomassandnutritionalqualityintropicalforagesurochloahumidicolainthreedifferentlocationsincolombia
AT hernandezluismiguel resultsofusingmachinelearningandaproximalcanopyreflectancesensortopredictbiomassandnutritionalqualityintropicalforagesurochloahumidicolainthreedifferentlocationsincolombia
AT cardosojuanandres resultsofusingmachinelearningandaproximalcanopyreflectancesensortopredictbiomassandnutritionalqualityintropicalforagesurochloahumidicolainthreedifferentlocationsincolombia
AT jaureguirosanoemi resultsofusingmachinelearningandaproximalcanopyreflectancesensortopredictbiomassandnutritionalqualityintropicalforagesurochloahumidicolainthreedifferentlocationsincolombia