Due to different combinations of agriculture, livestock and forestry managed by rotation, succession and intercropping practices, integrated agriculture production systems such as integrated crop–livestock systems (iCL) constitute a very complex target and a challenge for automatic mapping of cropping practices based on remote sensing data. The overall objective of this study was to develop a classification strategy for the annual mapping of integrated Crop–Livestock systems (iCL) at a regional scale. This strategy was designed and tested in the six agro-climatic regions of Mato Grosso, the largest Brazilian soybean producer state, using MODIS satellite time-series images acquired between 2012 and 2019, ground data with heterogeneous distribution in space and time and a Random Forest classifier. The results showed that: 1. the use of unbalanced training samples with a class composition close to the real one was the right classifier training strategy; 2. the use of a single training database (pooling samples from different years and regions) to classify each region and year individually proved to be robust enough to provide similar classification accuracies in comparison to those based on the use of a database acquired for each region and for each year. The final hierarchical classification overall accuracy was 0.89 for Level 1, the cropping pattern level (single and double crops DC); 0.84 for Level 2, the DC category level (integrated system iCL soy-pasture/brachiaria, soy-cotton and soy-cereal); 0.77 for Level 3, the iCL level (iCL1 soy-pasture and iCL2 soy-pasture mixed with corn). The F-scores for DC, iCL and iCL1 cropping systems presented high accuracy (0.89, 0.85 and 0.84), while iCL2 was more difficult to classify (0.63). This approach will next be applied across the entire Brazilian soybean corridor, leading to an operational tool for monitoring the adoption of sustainable intensification practices recognized by Brazil’s Agriculture Low Carbon Plan (ABC PLAN).

Childhood-related obesity and overweight are increasing concerns for the health and well-being of children. Dental caries (decay) is the most prevalent oral disease during childhood, and several studies have suggested that nutritional status and dental caries are associated in children. Therefore, this study aimed to determine the geographic distribution of childhood overweight/obesity and dental caries in a medium-sized Brazilian city. This cross-sectional study was conducted with 269 children of both genders enrolled in four public schools in the city of Alfenas. The children were clinically examined to assess cavitated dental caries and nutritional status (overweight and obesity). In addition, the GIS was used for the geospatial clustering analyses. A heat map was created by the Kemel method to estimate the concentration of the outcomes. The cavitated dental caries and overweight/obesity were also pointed out by dots on the map. However, of the 269 children, 118 were boys (43.87%) and 151 were girls (56.13%). One hundred fifty-seven children (58.4%) were classified as having “non-cavitated caries,” while 112 (41.6%) were classified as having “cavitied caries.” In the nutritional status assessment, 204 children (75.84%) were classified as “eutrophic,” while 65 children (24.16%) were classified as “overweight/obesity,” A geographical correlation of dental caries with overweight/obesity may exist in the northeast and southwest areas. In conclusion, a geographical concordance between the dental caries and the occurrence of overweight/obesity among the schoolchildren from Alfenas may exist in some areas. Future studies are necessary.

Entre as principais potências agropecuárias, o Brasil se destaca como um dos poucos países que ainda dispõe de extensas áreas de terra com potencial de produção agropecuária, sem a necessidade do desmatamento. O país busca reverter a degradação do solo por meio de políticas públicas, incluindo a criação de indicadores Sócio-Agro-Ambientais multiescalares. Este trabalho tem como objetivo desenvolver uma solução para diagnosticar áreas degradadas, oferecendo recomendações técnicas regionalizadas para a conservação, recuperação e reintegração dessas áreas à cadeia produtiva de alto rendimento. Duas abordagens inovadoras foram adotadas: (i) uso de deep learning, com uma acurácia de 95,9% para diagnósticos locais por smartphones; (ii) baseada em machine learning e satélites, que alcançou 95,90% de acurácia para avaliações regionais. Ambas as metodologias convergem para soluções acessíveis e inovadoras, estimulando ações de recuperação de áreas degradadas.