Pierre C. Robert

Identifying important factors influencing corn yield and grain quality variability using artificial neural networks

Soil, landscape and hybrid factors are known to influence yield and quality of corn (Zea mays L.). This study employed artificial neural network (ANN) analysis to evaluate the relative importance of selected soil, landscape and seed hybrid factors on yield and grain quality in two Illinois, USA fields. About 7 to 13 important factors were identified that could explain from 61% to 99% of the observed yield or quality variability in the study site-years. Hybrid was found to be the most important factor overall for quality in both fields, and for yield as well in Field 1. The relative importance of soil and landscape factors for corn yield and quality and their relationships differed by hybrid and field. Cation exchange capacity (CEC) and relative elevation were consistently identified as among the top four most important soil and landscape factors for both corn yield and quality in both fields in 2000. Aspect and Zn were among the top five most important factors in Fields 1 and 2, respectively. Compound topographic index (CTI), profile curvature and tangential curvature were, in general, not important in the study site-years. The response curves generated by the ANN models were more informative than simple correlation coefficients or coefficients in multiple regression equations. We conclude that hybrid was more important than soil and landscape factors for consideration in precision crop management, especially when grain quality was a management objective.

Spatial Variability of Soil Properties, Corn Quality and Yield in Two Illinois, USA Fields: Implications for Precision Corn Management

Better understanding of within-field spatial variability of crop quality parameters and yield are needed for precision management of crops. This study was conducted to determine the magnitude of within-field variability in soil properties, corn (Zea mays L.) quality parameters and yield and to characterize their spatial structures. Another objective was to compare the effects of hybrid on corn quality, yield, and the spatial structure of grain quality. Four Pioneer hybrids were planted side-by-side, two in each of the two study fields in eastern Illinois, USA. Coefficients of variation (CV%) for soil properties varied from 6.3 (pH) to 56.8% (soil test P). All the soil properties (except pH at Site 2) displayed well-defined spatial structures, with either strong or moderate spatial dependence. Variability in corn quality and yield (CVs < 10%) was smaller than variability in soil properties. Most quality parameters examined at Site 1 exhibited either moderate or strong spatial dependence, except that corn oil (both hybrids), kernel roundness and weight (hybrid 33Y18) did not show any spatial correlation. Hybrid 33G26 had significantly higher yield and quality for most quality parameters than 33Y18 at Site 1. At Site 2, hybrid 34W67 was significantly lower in oil and protein content, length, roundness and vitreousness than 34K77, but higher in other quality parameters. Significant differences in spatial structures were also observed across hybrids for some corn quality parameters. We conclude that hybrid selection is an important strategy for precision management of corn for optimum yield and quality.

Precision agriculture: New developments and needs in remote sensing and technologies

Precision agriculture, a holistic approach to micro-manage agricultural landscapes based on information, knowledge, and new technologies, will accelerate the application of remote sensing techniques to agricultural management. In recent years there has been a wealth of new research developments, particularly based on ground platforms, but also on airborne and spatial platforms. The paper provides a summary of applications by platform. Presently, utilizations by producers are still rare but, in the past few years, several new programs have been offered for nutrient management, particularly nitrogen, crop status monitoring, and irrigation management. There are specific and unique technical and managerial barriers and requirements for the application of remote sensing to soil and crop management. The four principal requirements relate to: spatial resolution, timeliness, coverage frequency, and imagery management infrastructure. Through precision agriculture, specialists trained in imagery analysis, efficient infrastructure for the transfer and management of imagery, better sensor systems, all needed to successfully use remote sensing to precision agriculture include various aspects of soil monitoring, crop condition monitoring and management, and machinery performance evaluation. This will bring a more profitable and sustainable agriculture where optimal agricultural production is made while protecting environmental quality.

Remote sensing requirements for precision agriculture

Precision agriculture, an information and technology based agricultural system, will advance the application of remote sensing techniques to agricultural management. There are specific and unique technical and managerial barriers and requirements for the application of remote sensing to soil and corp management. The four principal requirements relate to: spatial resolution, timeliness, coverage frequency, and imagery management infrastructure.