Marcelo José Colet

Análise dos atributos do solo e da produtividade da cultura de cana-de-açúcar com o uso da geoestatística e árvore de decisão

One of the challenges of precision agriculture is to offer subsidies for the definition of management units for posterior interventions. Therefore, the objective of this work was to evaluate soil chemical attributes and sugarcane yield with the use of geostatistics and data mining by decision tree induction. Sugarcane yield was mapped in a 23ha field, applying the cell criterion, by using a yield monitor that allowed the elaboration of a digital map representing the surface of production of the studied area. To determine the soil attributes, soil samples were collected at the beginning of the harvest in 2006/2007 using a regular grid of 50 x 50m, in the depths of 0.0-0.2m and 0.2-0.4m. Soil attributes and sugarcane yield data were analyzed by using geostatistics techniques and were classified into three yield levels for the elaboration of the decision tree. The decision tree was induced in the software SAS Enterprise Miner, using an algorithm based on entropy reduction. Altitude and potassium presented the highest values of correlation with sugarcane yield. The induction of decision trees showed that the altitude is the variable with the greatest potential to interpret the sugarcane yield maps, then assisting in precision agriculture and, revealing an adjusted tool for the study of management definition zones in area cropped with sugarcane.

Alteração em atributos fisicos de um solo sob pastagem após escarificação

A compactacao do solo pode ser considerada uma das principais causas de degradacao de pastagens. Entre varias tecnicas de mobilizacao do solo para rompimento de camadas compactadas, a escarificacao apresenta aspectos positivos para um manejo conservacionista. Objetivou-se, neste trabalho, avaliar as alteracoes ocorridas na resistencia do solo a penetracao, porosidade do solo e densidade do solo de um Latossolo Vermelho-Amarelo, sob pastagem mediante sua escarificacao. Implementou-se um experimento em uma area de Brachiaria decumbens Stapf. em Nova Odessa (SP), utilizando um escarificador com discos de corte e ponteiras aladas. A resistencia do solo a penetracao foi avaliada utilizando um penetrografo hidraulico eletronico e a densidade do solo e porosidade do solo, a partir de amostras indeformadas. As camadas de solo identificadas por analise multivariada da resistencia do solo a penetracao foram alteradas pela escarificacao. A escarificacao do solo reduziu significativamente os valores de resistencia do solo a penetracao. A escarificacao do solo promoveu maiores alteracoes nos atributos fisicos na profundidade de 0,0-0,1 m, na entrelinha da passagem das hastes do escarificador.

Profundidade de deposição de semente de milho na região dos Campos Gerais, Paraná

No Tillage system is fully incorporated to farming in the region of Campos Gerais, state of Parana. Accuracy and precision in the planting process are items of great importance for the success of this system. In order to evaluate the planting process, thirty eight farms were selected as sites for analysis of the placement depth of seeds. The research area was 4 or 5 planting rows, evaluating 10 plantlets per row. The average seed depth was around 46 mm, and significant differences between rows were observed in 21 areas. The average coefficient of variation was around 20%, the statistical limit between medium and high. Analyses of other parameters show that those coefficients may represent different errors in the process. The planting process in Campos Gerais can be considered efficient regarding to the average seed depth. However, the analysis of variability implies de need of actions concerning to anthropic and machinery factors.

Distribuição longitudinal de plantas de milho (Zea mays L.) na região dos Campos Gerais, Paraná

The region of Campos Gerais in the State of Parana, Brazil, is a pioneer in the implementation of new technologies, with superior grain yield performance. No-tillage farming system, for instance, is widely adopted in this region. This particular system requires accuracy and precision in the planting process to achieve high grain yields. Regarding regional attributes, the corn planting process in Campos Gerais under no-tillage was evaluated. Forty-eight properties were selected for a plant population pressure analysis. Four or five planting rows delimited the study area, 3m per row. The spacing between plants and between rows was measured. No significant differences were observed between planting rows in 42 properties, and the average coefficient of variation was around 33%. None of the areas had an average lower than 50.000 plants ha-1, the lowest value recommended for the hybrids in study. The regional planting process can be considered efficient regarding the number of plants per area. Nevertheless, the high variability found on plant distribution in the planting rows suggests the need for further research and extension measures.