Análise da incerteza na representação de classes de cobertura do solo urbano resultantes da aplicação de uma rede neural artificial

The great diversity of materials that characterizes the urban environment determines a structure of mixed classes in a classification of multiespectral images. In that sense, it is important to define an appropriate classification system using a non parametric classifier, that allows incorporating non spectral (such as texture) data to the process. They also allow analyzing the uncertainty associated to each class from the output alues of the network calculated in relation to each class. Considering these properties, an experiment was carried out. This experiment consisted in the application of an Artificial Neural Network aiming at the classification of the urban land cover of Presidente Prudente and the analysis of the uncertainty in the representation of the mapped thematic classes. The results showed that it is possible to discriminate the variations in the urban land cover through the application of an Artificial Neural Network. It was also possible to visualize the spatial variation of the uncertainty in the attribution of classes of urban land cover from the generated representations. The class characterized by a defined pattern as intermediary related to the impermeability of the urban soil presented larger ambiguity degree and, therefore, larger mixture.

Efeitos de níveis de cobertura do solo sobre a produtividade e crescimento do feijoeiro irrigado, em sistema de plantio direto

The objective of this research was to study the effects of five different treatments of grass (Brachiaria decumbens) straw mulch on common beans (Phaseolus vulgaris L.): 0% (0 t.ha-1), 25% (2,25 t.ha-1), 50% (4,5 t.ha-1), 75% (6,75 t. ha-1) and 100% (9,0 t/ha) designed by randomized blocks, with four replicates. The irrigation was applied when minimum soil water potential were reached about - 30kPa. The water management based on tensiometers and soil water characteristic curve. A microsprinkler irrigation system was used. The experiment was set up at the Experimental Station of Embrapa Rice and Bean (Empresa Brasileira de Pesquisa Agropecuária Arroz e Feijão) at Santo Antonio de Goiás, Brazil, in a Dark - Red Latosol soil. The results showed: the bean yield and his components were not affected by treatments, except grain number/pod,. The mulch increased the water use efficiency and, consequently, decreased the number of irrigations when the mulch reached more than 50% straw mulch. The treatment with 100% of mulching presented the largest leaf area index and dry matter accumulation was not affected by mulching.

Levantamento gravimétrico na região de Franca - SP e delfinópolis - MG, no reconhecimento e delimitação de feições estruturais (Zonas de Sutura)

This paper presents the results of a geophysical study carried out in northeastern São Paulo State and southwestern Minas Gerais State over an area 80 km wide and 97.5 km long in SE Brazil. The Bouguer anomaly map, and geological and structural data allowed to identify three different gravity domains - crustal blocks limited by major discontinuities -related to the structural pattern of the area. These discontinuities were interpreted as geosuture zones underlying the Paraná Basin sediments which have extensions in the Pre-cambrian Basement. The crustal discontinuities named Alterosa and Ribeirão Preto may be seen as A - type collision sutures in a triple junction arramgement. Two prominent linear anomalies are recognized in the Bouguer anomaly map, as well as the limit between the Brasilia and São Paulo crustal blocks or paleoplates. The Alterosa suture zone trends NW-SE while the Ribeirão Preto suture has a NE-SW direction. The Bouguer anomaly map provides subsidies and information on new concepts and theories leading to the refinement of tectonic models.