Aquaculture and salt-culture are relevant economic activities in the Brazilian Coastal Zone (BCZ). However, automatic discrimination of such activities from other water-related covers/uses is not an easy task. In this sense, convolutional neural networks (CNN) have the advantage of predicting a given pixel’s class label by providing as input a local region (named patches or chips) around that pixel. Both the convolutional nature and the semantic segmentation capability provide the U-Net classifier with the ability to access the “context domain” instead of solely isolated pixel values. Backed by the context domain, the results obtained show that the BCZ aquaculture/saline ponds occupied ~356 km² in 1985 and ~544 km² in 2019, reflecting an area expansion of ~51%, a rise of 1.5× in 34 years. From 1997 to 2015, the aqua-salt-culture area grew by a factor of ~1.7, jumping from 349 km² to 583 km², a 67% increase. In 2019, the Northeast sector concentrated 93% of the coastal aquaculture/salt-culture surface, while the Southeast and South sectors contained 6% and 1%, respectively. Interestingly, despite presenting extensive coastal zones and suitable conditions for developing different aqua-salt-culture products, the North coast shows no relevant aqua or salt-culture infrastructure sign.

Urban and industrial effluents, stormwater, road runoff, agricultural runoff, urban or mine waste deposits and fuel storage sites can lead to the contamination of water sources with compounds that are hard to biodegrade, such as heavy metals, whose removal requires advanced and expensive technologies. The Sustainable Development Goals (SDGs) established by the UN and the current requirements in terms of energy efficiency, reduction of carbon emissions, water reuse, waste valorization and preservation of public health, have led to a rethink concerning the typology of technologies for the treatment of water and the production of drinking water. Electrocoagulation (EC) stands out in this scenario due to its high efficiency in the removal of several pollutants, production of low sludge volumes and adaptability to the use of renewable energies. This is in addition to the ease with which it can be combined with other water treatment technologies. This work presents a literature review to systematize the use of EC for the removal of transition metals in water to produce drinking water, since these elements are present in several natural water sources and are parameters used in the legislation of many countries for the quality control of drinking water. The works found were analyzed in detail, and relationships between pre-set variables and categories were determined through regression analysis. Generally, it was found that EC is a highly efficient technology for the removal of transition metals in water (above 75% for most metals), specifically through parallel plates technologies with iron and aluminum electrodes with a minimum spacing of 1 cm and density minimum applied current of 10 A/m².

The Brazilian Amazon Satellite Monitoring Program (PRODES Amazonia) tracks forest loss in the Brazilian Amazon but excludes about 6.6% ( ~ 280,000 km²) of non-forest vegetation (NF). Here we developed the PRODES NF system to address this gap by adapting the well-established methodology of PRODES Amazonia. Initial findings from PRODES NF show that the Brazilian Amazon lost 10.46% ( ~ 30,000 km²) of NF area, mainly in the last two decades, with the estates of Mato Grosso, Roraima, and Amapá being primary hotspots of losses. Savannas were the most affected (13.3% of their extent). NF loss strongly correlates (r = 0.87; p < 0.0001) with deforestation, suggesting a continuum of vegetation loss in the biome regardless of the predominant vegetation type. Combining data from PRODES Amazonia and PRODES NF reveals an official estimate of ~798,000 km² in total primary vegetation loss ( ~ 19% of the entire biome) in the Brazilian Amazon by 2022.

In Brasil ranching has played a fundamental role in the occupation of rural land. This process results in a series of environmental impacts, such as the erosion and compaction of the soil, and the emission of greenhouse gases, in addition to the intensive use of the soil and water resources. In part of the properties, inadequate management resulted in pastures with degradation levels. The literature points out the importance of intensifying technology as a way to guarantee sustainable pastures. The present study aims to identify and analyze the relationships between the technological level level of cattle production and the degradation of pastures in the Vermelho River basin in Goiás, central Brazil. This area is considered to be representative of livestock in the Brazilian Cerrado. The sample consisted of 60 cattle ranches, selected from each of the three sectors of the Vermelho River basin. The data were analyzed using a Multiple Correspondence Analysis, cluster analysis, and Beta regression to obtain Pasture Degradation Indice (PDI). Bivariate associations were found between the Technological Index (TI) and three variables – the manager’s income, topographic relief, and the size of the property. It was possible to verify the use of a higher technological level in the largest properties as well as in flatter areas. It was also found that the higher technological level provides higher remuneration to managers. However, there was no relationship between the technology used in the establishments and the cattle density, which can reduces profitability economic and animal welfare. There was also no association between TI and PDI, suggesting pasture degradation, even when using more intensive technologies in cattle production.

In Brazilian rural communities, the lack of treated water leads their residents to seek individual and alternative solutions, in which dug shallow wells (DSW) are quite widespread. However, water quality may not be fitted for human consumption. For this reason, the current study aimed to predict the contamination of DSW water in rural communities in the Brazilian state of Goiás. For this, secondary data related to water quality, the distance to possible contamination sources, structural conditions, and local geology were evaluated. Therefore, a generalized linear model was applied, and its predictors were evaluated by stepwise methods (Akaike information criterion—AIC and Bayesian information criterion—BIC), generating an intermediate model. After the analysis, turbidity parameter was chosen to be removed resulting in a final, submitted to leave-one-out cross-validation method, and its performance was measured by a confusion matrix. The final model resulted in four predictive variables: well diameter, contour paving width, poultry, and swine husbandry existence. The model accuracy was 82.61%, with a true positive predictor of 82.18% and a negative predictor of 85.71%.