Domingos Guilherme Pellegrino Cerri

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.

Sistema de sincronismo entre a colhedora de cana-de-açúcar e o veículo de transbordo

One of the problems found in mechanical harvest of sugar cane is the lack of synchronism between the harvest machine and the infield wagon, causing crop losses as well as operational capacity. The objective of the present research was to design a system capable of helping to synchronize the sugar cane harvest machine with the wagon. The communication between tractor and harvest machine is wireless. Two ultrasound sensors coupled to the elevator and a microprocessor manage such information, generating a correct synchronization among the machines. The system was tested in laboratory and on field performing its function adequately, maintaining the two machines in synchronization, indicating and alerting the operators their relative positions. The developed system reduced the sugar cane lost in 60 kg ha-1 comparing to the harvest with the system turned off.

Correlation of physical and chemical attributes of soil with sugarcane yield

O objetivo deste trabalho foi avaliar as correlacoes entre a produtividade da cana‑de‑acucar e alguns atributos fisicos e quimicos do solo. Para isso, uma area de 42 ha, em Araras, SP, foi selecionada. As propriedades do solo foram determinadas a partir de amostras coletadas no inicio da safra 2003/2004, por meio de uma grade regular de 100x100 m. A produtividade foi avaliada por meio de um monitor de produtividade (Simprocana). Analises de correlacao foram realizadas entre a produtividade da cana‑de‑acucar e as seguintes propriedades do solo: pH, pH CaCl 2 , N, C, indice de cone, teor de argila, materia orgânica, P, K, Ca, Mg, H + Al, capacidade de troca cationica e saturacao por bases. Os coeficientes de correlacao foram respectivamente de ‑0,05, ‑0,29, 0,33, 0,41, ‑0,27, 0,22, 0,44, ‑0,24, traco, ‑0,06, 0,01, 0,32, 0,14 e 0,04. As correlacoes de atributos quimicos e fisicos do solo com a produtividade da cana‑de‑acucar sao baixas, por si mesmas, e nao sao capazes de explicar a variacao na produtividade da cana‑de‑acucar, o que indica que, alem das propriedades do solo, outras variaveis devem ser analisadas.

Spatial variability of soil attributes and sugarcane yield in relation to topographic location

Soils submitted to the same management system in places with little variation of landscape, manifest differentiated spatial variability of their attributes and crop yield. The aim of this work was to investigate the correlation between spatial variability of the soil attributes and sugarcane yield as a result of soil topography. To achieve this objective, a test area of 42 ha located at the Sao Joao Sugar Mill, in Araras, in the State of Sao Paulo, Brazil, was selected. Sugarcane yield was measured with a yield monitor fitted in a sugarcane harvester and GPS signal. A total of 170 soil samples were taken at regular 50 m grid, at a depth of 0 - 0.2 m. The area under study was divided into two sites based on topography. The following soil attributes were analysed: organic matter (OM) content, exchangeable potassium (K), calcium (Ca) and magnesium (Mg), their base saturation percentage (%BS), cation exchange capacity (CEC), pH, clay, silt, total sand and density. The use of landscape and geostatistics enable defining areas with different spatial variability in soil attributes and crop yield, providing the visualization and definition of homogeneous management zones. The largest spatial variability of soil attributes and sugarcane yield was in the lowest part of the field.

Sugar Cane Yield Monitor

Aiming to contribute for the implementation of Precision Agriculture in sugar cane crop in the Brazilian, the main objective of this research was to generate a yield map of this culture. In order to do that this project involved the design and test of a sugar cane yield monitoring system during 2003 and 2004-harvest seasons. The system was mounted on a CASE 7700 1999 sugar cane combine, and consisted of a scale, a data acquisition system, and a GPS. The scale consisted of a weigh plate supported by load cells. The load cells were supported by a protective box mounted in the frame of the harvester elevator. The scale, which was mounted in the floor of the elevator, directly recorded instantaneous measurements of the sugar cane yield. In order to evaluate the accuracy of the system, later each loaded truck was weighted on an electronic platform scale upon arrival at the sugarcane mill. The weight of each truck was used as the standard. For each test, the scale readings were totaled and compared to the actual yield, which was measured by the weight of each truck. The scale’s average percent error was 0.96 % and the maximum error was 6.4%. A sugar cane yield map was generated in a 43 ha area plot of a sugar plantation, located in Araras, Sao Paulo State, Brazil. The results show that the yield variability in this area is significant.

Applying Sugar Cane Precision Agriculture in Brazil

Aiming to contribute to the implementation of Precision Agriculture in sugar cane crop in Brazil, this project registers two fundamental process: i) to design a sugarcane yield monitor; ii) to map physical and chemical soil attributes. The main objective is to make a correlation with yield data and soil attributes obtained. The system designed uses load cells as a billets weighing instrument set up in the harvester side conveyor before the sugar cane billets are dropped in an in-field trailer. These data together with the geo-referenced position provided by the Differential Global Positioning System (DGPS) set up in the harvester, will allow the elaboration of a digital map, which will represent the yield area. This system is being tested under laboratory conditions for further field tests. The physical and chemical soil attribute maps were obtained using a 50 x 50 m grid sampling, obtained using a undisturbed soil sampler, in a 43 ha area plot of a sugar plantation (Usina Sao Joao), located in Araras, Sao Paulo State, Brazil. The Geostatistic techniques will be used to obtain the soil properties map.