DSpace Communidade: Embrapa Gado de Corte (CNPGC)

Machine learning models for crude protein prediction in Tamani grass pastures.

2026-01-01T00:00:00Z

Título: Machine learning models for crude protein prediction in Tamani grass pastures. Autoria: MONTEIRO, G. O. de A.; DIFANTE, G. dos S.; MONTAGNER, D. B.; EUCLIDES, V. P. B.; CASTRO, M.; RODRIGUES, J. G.; PEREIRA, M. de G.; SANTANA, J. C. S.; ITAVO, L. C. V.; NANTES, R. T.; CAMPOS, J. A.; COSTA, A. B. da; MATSUBARA, E. T. Conteúdo: Understanding forage quality is essential for meeting animal demands and optimizing production. This study aimed to: (i) test the applicability of machine learning models with tabular data such as climate variables, light interception (LI), nitrogen dose (N dose), interval between grazing (GI), and pre- (HPRE) and post-grazing height (HPOST) to predict leaf crude protein (CP) content of tamani grass pastures; (ii) identify which variables contribute most to CP prediction. A set of 90 instances was used with 80% for training and validation and 20% for testing. The hyperparameters were adjusted with grid-search on the training set. We tested Linear Regression (LR), Multilayer Perceptron (MLP), Decision Trees (DT), Random Forest (RF), and XGBoost. The MLP (r=0.75, R2 =44.18%, MAE=1.55), RF (r=0.78, R2 =49.07%, MAE=1.59) and XGBoost (r=0.78, R2 =56.65% MAE=1.45) models presented the best prediction results (p<0.001). The variables most important in predicting CP content were GI, followed by N dose, HPRE and HPOST. XGBoost outperformed other tested models (p<0.001). Tabular data, including N dose, GI, HPRE, HPOST, LI, and climatic variables, is a viable alternative for predicting CP. In conclusion, the results of this study suggest that management practices may have a greater influence on the chemical composition of Tamani grass than environmental conditions, although further research with larger and more diverse datasets is needed to confirm these findings

Animal production on tropical pastures in Brazil.

2012-01-01T00:00:00Z

Título: Animal production on tropical pastures in Brazil. Autoria: VALLE, C. B. do; EUCLIDES, V. P. B. Conteúdo: Animal production in the tropics is done mostly on native and cultivated pastures. Brazil is predominantly tropical and is the fifth largest country in the world with about 20% of its area covered by pastures (174 million ha). It has a natural aptitude for livestock production also as climate and topography are concerned. Soils however, are acid and poor, with more than 90% dystrophic (soil base saturation less than 50%) in Central Brazil, the most significant region for livestock production. The majority of the cattle of 209 million head is on pastures, mostly of grasses and planted to a few Brachiaria and Panicum cultivars, characterizing extensive monocultures.

Reciprocal recurrent selection: a strategy to obtain superior apomictic hybrids in Brachiaria decumbens.

2012-01-01T00:00:00Z

Título: Reciprocal recurrent selection: a strategy to obtain superior apomictic hybrids in Brachiaria decumbens. Autoria: BARRIOS, S. C. L.; VALLE, C. B. do; ALVES, G. F.; SIMEÃO, R. M.; JANK, L. Conteúdo: Pastures of Brachiaria decumbens cv. Basilisk radically changed the scenario of central Brazil livestock production from the early 1970s and allowed the development of this vast region. Despite of the reasonable biomass yield and nutritional value, susceptibility to grassland spittlebugs limits its use nowadays. The breeding of B. decumbens was restricted to interspecific crosses using the cultivar Basilisk as pollen donor due to the lack of compatible sexual ecotypes within the species.

Profitability of increasing supplementation levels for beef cattle grazing tropical pastures.

2026-01-01T00:00:00Z

Título: Profitability of increasing supplementation levels for beef cattle grazing tropical pastures. Autoria: GALVANI, D. B.; PEREIRA, M. de A.; MONTAGNER, D. B. Conteúdo: ABSTRACT - This study assessed the economic feasibility of supplementation leveIs for beef catt1e grazing tropical pastures during the dry season. The central question was whether higher supplementation rates could improve system profitability and what leveI would provide the most advantageous balance between biological efficiency anel economic returno. Two experiments were conducted with 36 Angus x Nellore buIls each, receiving 0.2, 0.4, or 0.8% of body weight (BW) of a protein-energy supplement whilc grazing Brachiaria brizantha (I) or Brachiaria decumbens (2). Performance variables were measured over 110-150 days, and economic responses were calculated from feed costs and carcass revenues. A deterministic simulation was also run to determine how supplementation wouId affect feedlot finishing at 580 kg slaughter BW. Profitahility was further scaled to a 300-hs pastore base to integrate both per-animal and per-area perspectives. Supplementation linearly enhanced average daily gain (ADG) and stocking rate, but marginal advantages were greater between 0.2 and 0.4% BW than 0.4 and 0.8% BW. In Experiment 1, ADG increased frorn 0.33 to 0.67 kg/day and final BW frorn 302 to 351 kg; in Experiment 2, ADG improved from 0.41 to 0.74 kg/day and final BW from 365 to 415 kg. Revenues increased with supplementation, but not margin peaked at 0.4% BW (US$ 101 in Exp. I; US$ 83 in Exp. 2) and declined at 0,8% BW due to higher costs and reduced efficiency. The simulation confirmed that greater supplementation could shorten finishing time and reduce projected feedlot costs; however, system profit margin was maximized at 0.4% BW (US$ 183 in Exp. I; US$ 127 in Exp. 2). At tlhe 300-ha scale, output increased with higher supplementation, but total profit was optimized at 0.4% BW (US$ 253,000 in Exp. I; US$ 129,000 in Exp. 2). In conclusion, dry season beef cattle supplementation at 0.4% BW on tropical pastures yielded the best performance, cost management, and profitability in simulated pasture and feedlot finishing.