https://www.alice.cnptia.embrapa.br/alice/handle/item/235 Nota Técnica/Nota científica (CPAMN) 2026-04-06T06:17:26Z https://www.alice.cnptia.embrapa.br/alice/handle/doc/1185326 Título: Predicting individual dry matter intake in Holstein × Gyr cows using behavior-monitoring sensor, phenotypic, and weather data with supervised machine learning. Autoria: SILVA, C. S. D.; SILVA, T. E. da; SGUIZATTO, A. L. L.; MACHADO, A. F.; SILVA, A. S.; COSTA, J. H. C.; CAMPOS, M. M.; PACIULLO, D. S. C.; GOMIDE, C. A. de M.; MORENZ, M. J. F. Conteúdo: Accurate estimation of DMI is essential for optimizing nutrition, efficiency, and economic performance in modern dairy herds. However, most existing equations to estimate DMI are designed for herd-level predictions in purebred Holstein cows. This study evaluated the accuracy and precision of machine learning (ML) algorithms to predict daily individual DMI in Holstein × Gyr crossbred lactating cows using a supervised and integrative approach that combined behavior monitoring data, cow phenotypes, and weather features. Data from 31 cows were individually and consecutively collected over 18 d. Twenty-two cows (71% of the dataset) were used to train 4 linear regression models (multiple linear, ridge, lasso, and elastic net) and 3 ensemble algorithms (random forest, gradient boosting, and extreme gradient boosting) through leave-one-group-out cross-validation, with the number of folds equal to the number of cows (k = 22). The remaining 9 cows were used as an external test set. Among all algorithms, Gradient boosting achieved the best overall performance, yielding moderate precision (R2 = 0.68) and accuracy (root mean squared error = 1.60 kg/d) metrics on test data. Our results indicate that gradient boosting is more suitable for capturing complex nonlinear relationships underlying daily DMI compared with the other models evaluated. Further advancements in ML-based DMI prediction should consider integrating intra- and interindividual variability in feeding behavior and accounting for animal-specific effects. 2026-01-01T00:00:00Z https://www.alice.cnptia.embrapa.br/alice/handle/doc/1083197 Título: Níveis de dano e de controle do percevejo-verde-da-soja Nezara viridula (Hemiptera: Pentatomidae) em feijão-caupi. Autoria: SILVA, P. H. S. da; ATHAYDE SOBRINHO, C. 2017-01-01T00:00:00Z https://www.alice.cnptia.embrapa.br/alice/handle/doc/1065861 Título: Soil carbon pools in different pasture systems. Autoria: CARDOZO JUNIOR, F. M.; CARNEIRO, R. F. V.; LEITE, L. F. C.; ARAUJO, A. S. F. Conteúdo: The aim of this study was to assess the carbon pools of a tropical soil where the native forest was replaced with different pasture systems. We studied five pasture production systems, including four monoculture systems with forage grasses such as Andropogon, Brachiaria, Panicum, and Cynodon, and an agroforestry system as well as a native vegetation plot. Greater availability of fulvic acid was detected in the agroforestry system as compared with that in the other systems. Higher lability of C was detected in the Andropogon system during the dry and rainy seasons and during the dry season in Cynodon. During the dry season, all pastures systems showed deficits in the net removal of atmospheric CO2. The structure and practices of the agroforestry system enables more carbon to be sequestered in the soil as compared with the monoculture pasture, suggesting that it is an important practice to mitigate climatic change and to improve soil quality. 2016-01-01T00:00:00Z https://www.alice.cnptia.embrapa.br/alice/handle/doc/1058718 Título: Association of Anagrus amazonensis Triapitsyn, Querino & Feitosa (Hymenoptera, Mymaridae) with aquatic insects in upland streams and floodplain lakes in central Amazonia, Brazil. Autoria: FEITOSA, M. C. B.; QUERINO, R. B.; HAMADA, N. Conteúdo: Anagrus amazonensis Triapitsyn, Querino & Feitosa (Hymenoptera, Mymaridae) is a parasitoid that usesaquatic insect eggs as a host for the development of its immature stages. The objectives of this study areto record the interaction between A. amazonensis and its hosts and the aquatic plants used by these hoststo lay their eggs. Field work was conducted in floodplain lakes and upland (terra firme) streams, in fourmunicipalities in Amazonas State, Brazil, where aquatic plants were scanned for the presence of aquaticinsect eggs. In the laboratory, eggs were maintained in plastic containers with water until the emergenceof the parasitoid or of the first instar insect. A total of 1223 adults of A. amazonensis emerged from eggsof Hemiptera, Lepidoptera and Odonata; these eggs were collected on 12 species of aquatic plants. 2016-01-01T00:00:00Z