We present a methodology for automatic corrosion detection in digital images of carbon steel storage tanks and pipelines from a petroleum refinery. The database consists of optical digital images taken from equipments exposed to marine atmosphere during their operational life. This new approach focuses on color and texture descriptors to accomplish corroded and noncorroded surface area discrimination. The performance of the proposed corrosion descriptors is evaluated by using Fisher linear discriminant analysis (FLDA). This approach presents two main advantages: No refinery stoppages are required and potential-related catastrophes can be prevented.

Water fluxes in highly impounded regions are heavily dependent on reservoir properties. However, for large and remote areas, this information is often unavailable. In this study, the geometry and volume of small surface reservoirs in the semi-arid region of Brazil were estimated using terrain and shape attributes extracted by remote sensing. Regression models and data classification were used to predict the volumes, at different water stages, of 312 reservoirs, for which topographic information is available. The power function used to describe the reservoir shapes tends to overestimate the volumes; therefore, a modified shape equation was proposed. Among the methods tested, four were recommended based on the performance and simplicity, for which the mean absolute percentage errors varied from 24% to 39%, in contrast to the 94% error achieved with the traditional method. Despite the challenge of precisely deriving the flooded areas of reservoirs, water management in highly reservoir-dense environments should benefit from volume prediction based on remote sensing.

The increasing global demand for electricity has led to a significant increase in the search for low-impact alternative sources, with solar photovoltaic being identified as one of the most feasible options. However, photovoltaic power plants require large ground areas, which represent a major constraint. If the panels are installed on water bodies, this restriction may be avoided. In this work, a simulation was performed to assess the potential of floating photovoltaic power generation in the tropical Gavião reservoir, located in the Northeast of Brazil. A payback analysis indicated that the investment in construction of the system is fully recovered in eight years, and that water losses due to evaporation can be reduced by approximately 2.6 × 10⁶ m³/year, sufficient to supply roughly 50,000 people.