Emílio Velloso Barroso

Artificial neural networks applied for soil class prediction in mountainous landscape of the Serra do Mar

Soil information is needed for managing the agricultural environment. The aim of this study was to apply artificial neural networks (ANNs) for the prediction of soil classes using orbital remote sensing products, terrain attributes derived from a digital elevation model and local geology information as data sources. This approach to digital soil mapping was evaluated in an area with a high degree of lithologic diversity in the Serra do Mar. The neural network simulator used in this study was JavaNNS and the backpropagation learning algorithm. For soil class prediction, different combinations of the selected discriminant variables were tested: elevation, declivity, aspect, curvature, curvature plan, curvature profile, topographic index, solar radiation, LS topographic factor, local geology information, and clay mineral indices, iron oxides and the normalized difference vegetation index (NDVI) derived from an image of a Landsat-7 Enhanced Thematic Mapper Plus (ETM+) sensor. With the tested sets, best results were obtained when all discriminant variables were associated with geological information (overall accuracy 93.2 - 95.6 %, Kappa index 0.924 - 0.951, for set 13). Excluding the variable profile curvature (set 12), overall accuracy ranged from 93.9 to 95.4 % and the Kappa index from 0.932 to 0.948. The maps based on the neural network classifier were consistent and similar to conventional soil maps drawn for the study area, although with more spatial details. The results show the potential of ANNs for soil class prediction in mountainous areas with lithological diversity.

Weathering of metapelites from the Quadrilátero Ferrífero mineral province, southeastern Brazil

Abstract Low-grade metamorphic rocks are known for their low mechanical strength and high weatherability. In the Quadrilátero Ferrífero, an important mineral province located in southeastern Brazil, this set of features results in frequent issues with mining and road slope instability, mainly associated with phyllites. Despite the significant iron ore production that occurs in this province, little is known about the geotechnical properties of the materials constituting the weathering front. Here, we report work aimed at investigating the changes in the basic properties of phyllites at four weathering grades. The methodology used included the field classification and mapping of four weathering grades in order to assess their spatial distribution on a road slope, as well as sampling for geological characterization by petrography and X-ray diffraction (XRD). In addition, the authors performed a physical characterization of all weathering grades, including index properties, mercury porosimetry, and strength data obtained with a Schmidt hammer both in the field and in the laboratory as well as using the point load test (PLT). Results showed the relevance of structural features such as discontinuities and metamorphic foliation observed in the weathering morphology in situ, with different weathering intensities occurring along the slope. Changes in the porosity and pore size distribution in the weathering front were nonlinear, as were resistance variations. The difficulty involved in performing the macroscopic identification of weathering grades due to the very fine texture of the rock as well as microstructural heterogeneities are likely causes of the observed variability in phyllite properties. This fundamental knowledge may aid the prediction of short-term and long-term scenarios for slope stability based on rock weatherability.