https://www.alice.cnptia.embrapa.br/alice/handle/item/19 Embrapa Agricultura Digital (CNPTIA) Fri, 12 Jun 2026 04:57:25 GMT 2026-06-12T04:57:25Z https://www.alice.cnptia.embrapa.br/alice/handle/doc/1187372 Título: Components and environmental factors for the diagnosis of Brazilian Ecological-Economic Zoning, scale 1:250,000. Autoria: SILVA, A. A. B. da; SILVA, J. dos S. V. da Conteúdo: The Ecological-Economic Zoning (ZEE) analyzes the landscape potentialities and vulnerabilities   using different environmental information. This study identifies and prioritizes the components and environmental factors used for the diagnosis of Brazilian ZEEs at 1:250,000 scale. The methodological guidelines of the Ministry of Environment and Climate Change (MMA) and the consolidated zoning plans for the States Acre, Mato Grosso do Sul, and Tocantins were analyzed as references, according to the following methodology: literature review; survey and comparative analysis; development, application, and analysis of a questionnaire using percentages assigned to degrees of importance (0 to 10), and qualitative analysis based on the number of respondents. A total of 27 factors grouped into five environmental components were identified. The most important environmental components (degree 10) were the physical environment and integrated studies, highlighted by 57% of respondents. The environmental factors with the highest degree of importance were: water resources (74%) and geomorphology (69%) from the physical environment; vegetation (63%) and ecosystem services (56%) from the biota; land use (74%) and traditional populations (50%) from the socio-economic; legal aspects (54%) and institutional areas (37%) from the legal-institutional; and environmental vulnerability (65%) and environmental fragility (65%) from integrated studies. Qualitatively, all components and environmental factors were classified as class 4 (extremely important), with varying percentages. The preparation of maps and reports was identified as high and extremely important information in 13 factors. It is concluded that all analyzed components and environmental factors should be considered in studies, although with varying degrees of importance. Thu, 01 Jan 2026 00:00:00 GMT https://www.alice.cnptia.embrapa.br/alice/handle/doc/1187372 2026-01-01T00:00:00Z https://www.alice.cnptia.embrapa.br/alice/handle/doc/1187315 Título: Dynamics of agriculture 4.0 technology adoption in the agri-food system: insights from an exploratory study in Rio Grande do Sul—Brazil. Autoria: SILVEIRA, F. da; BHARTI, D.; KILINÇ, I.; FURUYA, D. E. G.; TETILA, E. C.; PARRA-LÓPEZ, C.; BOLFE, E. L.; SANTOS, T. T.; BARBEDO, J. G. A. Conteúdo: Despite the growing relevance of Agriculture 4.0 technologies for enhancing productivity, decision-making, and sustainability in agri-food systems, their adoption remains uneven in developing-country contexts. This study aims to analyze the perceived severity and co-occurrence structure of barriers to Agriculture 4.0 adoption in the agri-food system of Rio Grande do Sul (RS), Brazil, using an exploratory quantitative design grounded in a barrier co-occurrence perspective rather than a causal or actor-centered network interpretation. An online survey conducted in 2024 with farmers in RS evaluated 25 literature-validated barriers spanning technological, economic, political, social, and environmental dimensions. The analysis combined a Barrier Severity Index (BSI), reliability testing, Principal Component Analysis (PCA), K-means clustering, ANOVA by farm size, and proximity-based co-occurrence networks constructed from highly rated barriers. The results show that economic barriers remain the most severe overall, particularly the lack of affordable solutions, high maintenance costs, and limited infrastructure. At the same time, farm-size-stratified networks reveal distinct association structures: small farms display a more segmented pattern linking affordability and technical access to institutional and capability constraints; medium farms show the most globally integrated co-occurrence structure; and large farms exhibit a dense but more differentiated configuration combining cost, interoperability, skills, and governance-related barriers. These findings are interpreted descriptively, as the networks capture patterns of co-reporting rather than causal interdependence. The study contributes a network-analytic representation of perceived barrier configurations and highlights the need for scale-sensitive policy mixes that address bundles of constraints rather than isolated obstacles. Thu, 01 Jan 2026 00:00:00 GMT https://www.alice.cnptia.embrapa.br/alice/handle/doc/1187315 2026-01-01T00:00:00Z https://www.alice.cnptia.embrapa.br/alice/handle/doc/1187276 Título: Multi-fruit tracking and 3-D structure recovery via CoTracker. Autoria: SANTOS, T. T. Conteúdo: Abstract: In agricultural robotics and orchard automation, tasks such as fruit detection, tracking, and spatiallocalization are essential for applications like yield prediction and harvesting. However, these tasks arechallenging due to the similar appearance of fruits, occlusions, and the inherent difficulties of field robotics,including uncontrolled lighting conditions and the variability in orchard environments. This work leveragesCoTracker, a transformer-based model for point tracking using cross-track/cross-time attention, to simultaneouslyperform multiple fruit tracking, 3-D fruit localization, and camera pose estimation. The proposed approachdemonstrates promising results in fruit counting, tracking, and scene reconstruction, highlighting its potential inagricultural automation. Thu, 01 Jan 2026 00:00:00 GMT https://www.alice.cnptia.embrapa.br/alice/handle/doc/1187276 2026-01-01T00:00:00Z https://www.alice.cnptia.embrapa.br/alice/handle/doc/1187153 Título: Cattle weight estimation from dense point clouds. Autoria: CASTANHEIRO, L. F.; TETILA, E. C.; FURUYA, D. E. G.; SILVA, J. P. da; BARBEDO, J. G. A.; ROMANI, L. A. S.; BOLFE, E. L. Conteúdo: Cattle weight is essential for decision-making in precision livestock farming, directly supporting nutrition management, animal welfare, and production efficiency. Existing methods rely on close-range measurements or manual intervention, limiting scalability. This work proposes an workflow for cattle weight estimation based on point clouds derived from aerial images. RGB images acquired at low altitude were processed using Structure from Motion (SfM) techniques to generate dense point clouds. Individual animals were automatically segmented from the reconstructed 3D scene, and voxel-based volumetric features were extracted for each animal. Body weight was then estimated through linear regression models calibrated with ground truth measurements obtained from individual weighing. The proposed approach was evaluated on Nellore cattle in a feedlot environment and achieved a root mean square error (RMSE) of 8.35 kg, corresponding to an average relative error of approximately 2.29%. The results highlight the potential of UAV-based photogrammetry as a cost-effective decision support tool for digital and sustainable livestock management. Thu, 01 Jan 2026 00:00:00 GMT https://www.alice.cnptia.embrapa.br/alice/handle/doc/1187153 2026-01-01T00:00:00Z