Tim Fiez

Examination of the influence of data aggregation and sampling density on spatial estimation.

Spatial processes may be sampled by point sampling or by aggregate sampling. If aggregate samples are collected over a regular grid and used to represent the central point of each aggregation area, the aggregate sampling functions as a low-pass filter and may eliminate aliasing during spatial estimation. To assess potential accuracy improvements, a numerical procedure for calculating the estimation error variance was developed. Analysis of point and block sampling techniques for kriging and inverse distance interpolation showed that for the same sampling density, block sampling provides better estimation. To achieve the same error levels, over 30%–50% more point samples were required than block samples. Furthermore, interpolation of block sampled data resulted in lower error variability and surfaces with more visual appeal.

A data partitioning scheme for spatial regression

Precision agriculture data consisting of crop yield and topographic features are examined with the objective of explaining yield variability as a function of topographic attributes in order to extrapolate this knowledge to unseen agricultural sites. It is demonstrated that random data partitioning into training, validation and test subsets is not appropriate when dealing with agricultural problems characterized with strong spatial data correlation. A simple spatial data partitioning scheme that leads to significantly faster neural network training and slightly better generalization is proposed. Also, integration of predictors formed from spatially partitioned data led to improved generalization over a bagging integration procedure in experiments. The margin between the best spatial model and a trivial predictor for our precision agriculture problem was small indicating that topographic features alone could explain only a small amount of the yield variability.

Distribution comparison for site-specific regression modeling in agriculture

A novel method for problem decomposition and for local model selection in a multimodel prediction system is proposed. The proposed method partitions the data into disjoint subsets obtained by the local regression modeling and then it learns the distributions on these sets in order to identify the most appropriate regression model for each test point. The system is applied to a site specific agriculture domain and is shown to provide a substantial improvement in the prediction quality as compared to a global model. Also, some aspects of local learner choice and setting of their parameters are discussed and an overall ability of the proposed model to accurately perform regression is assessed.

A Data Generator for Evaluating Spatial Issues in Precision Agriculture

With the rapid rise in site-specific data collection, many research efforts have been directed towards finding optimal sampling and analysis procedures. However, the absence of widely available high quality precision agriculture data sets makes it difficult to compare results from separate experiments and to assess the optimality and applicability of procedures. To provide a tool for spatial data experimentation, we have developed a spatial data generator that allows users to produce data layers with given spatial properties and a response variable (e.g. crop yield) dependent upon user specified functions. Differences in response functions within fields can be simulated by assigning different models to regions in coordinate-(x and y) or feature space (multidimensional space of attributes that may have an influence on response). Noise, either unexplained variance or sensor error, can be added to all spatial layers. Sampling and interpolation error is modeled by sampling a continuous data layer and interpolating values at unsampled locations. The program has been successfully tested for up to 15000 grid points, 10 features and 5 models. As an illustration of the potential uses of generated data, the effect of sampling density and kriging interpolation on neural network prediction of crop yield was assessed. Yield prediction accuracy was highly related (correlation coefficient 0.98) to the accuracy of the interpolated layers indicating that unless data are sampled at very high densities relative to their geostatistical properties, one should not attempt to build highly accurate regression functions using interpolated data. By allowing users to generate large amounts of data with controlled complexity and features, the spatial data generator should facilitate the development of improved sampling and analysis procedures for spatial data.

A software system for spatial data analysis and modeling

Advances in geographical information systems (GIS) and supporting data collection technology has resulted in the rapid collection of a huge amount of spatial data. However, known data mining techniques are unable to fully extract knowledge from high dimensional data in large spatial databases, while data analysis in typical knowledge discovery software is limited to non-spatial data. Therefore, the aim of the software system for spatial data analysis and modeling (SDAM) presented in this article was to provide flexible machine learning tools for supporting an interactive knowledge discovery process in large centralized or distributed spatial databases. SDAM offers an integrated tool for rapid software development for data analysis professionals as well as systematic experimentation by spatial domain experts without prior training in machine learning or statistics. When the data are physically dispersed over multiple geographic locations, the SDAM system allows data analysis and modeling operations to be conducted at distributed sites by exchanging control and knowledge rather than raw data through slow network connections.

Providing Precision Farming Education Through Conferences and Workshops

In response to rapidly growing interest in precision farming, universities and others have developed numerous educational programs. Many of these events are multi-day conferences and workshops as these venues provide the time necessary for attendees to learn about the many technologies, analysis approaches, and management strategies that make up precision farming. The Washington State University Western Precision Agriculture Conference, the Assiniboine Community College Precision Agriculture Conference and the University of Nebraska–Lincoln Crop Modeling for Environment-Specific Management Workshop exemplify these types of educational programs. The Western Precision Agriculture Conference uses a traditional format where the audience primarily listens to presentations. The Assiniboine Community College Precision Agriculture Conference provides a mixture of presentations and “hands-on” sessions where attendees actually use precision farming tools or develop site-specific management plans. Finally, those who attend the University of Nebraska–Lincoln Crop Modeling for Environment-Specific Management Workshop complete exercises related to each topic and presentation. Because a conference or workshop brings many experts together for a short period of time, organizers of all three events have tried to capture conference content for later use in other educational programs. Their approaches to this include videotaping interviews of conference speakers and assembling software and data used during the conference on compact disk. Given the multidisciplinary nature of precision farming, conferences and workshops that utilize multiple expert presenters such as those discussed in this paper are among the best sources of precision farming education.

Image processing in precision agriculture

A brief review of our signal and image processing application in precision agriculture is presented. A method for determining sampling frequency for agriculture data is proposed, and some initial results based on data simulation and image processing are reported.