People at DIFM
Dr. David Bullock leads the Data Intensive Farm Management (DIFM) research team that generates and analyzes “Big” agronomic data to improve the way the world fertilizes its crops. DIFM works with participating farmers, using GPS-reliant precision agriculture technology to conduct large-scale agronomic field trials on farmers’ own fields, to generate yield, input management, and field characteristics data in quantities and of quality only recently imaginable. DIFM’s research also looks at the effects of fertilizer management practices on water quality, with the aim of discovering efficient means of reducing the loss of nitrogen fertilizer into the Mississippi River basin.
The 2017 University of Illinois graduate stays busy these days as project coordinator for the Data-Intensive Farm Project (DIFM) at the university, plus an equine photography business Miller started about a year ago. She and fiancé, Wyatt Jones, also sell and train horses — everything from trail horses to working ranch horses to rodeo and show horses — under WRJ Equine. She also obtained her real estate broker’s license last year and Miller continues to train and compete on her barrel horses at the local, state and national level.
Brittani Edge is a PhD student at the University of Illinois at Urbana-Champaign specializing in precision agriculture and on-farm research. She worked with others at UIUC to design and host a workshop for producers who want to learn more about designing and analyzing their own on-farm trials.
Keith Curran is the director of Information Technology for the DIFM-CIG Grant Project and a former associate director of development for the Washington State University Farm Network. Mr. Curran Manages the DIFM-CIG Data in the Oracle Cloud using Oracles Enterprise Class Databases.
Dr. John Sheppard is a Norm Asbjornson College of Engineering Distinguished Professor of Computer Science at Montana State University and previously was the RightNow Technologies Distinguished Professor in Computer Science at MSU. He holds a BS in computer science from Southern Methodist University and an MS and PhD in computer science from Johns Hopkins University. In 2007, he was elected as an IEEE Fellow "for contributions to system-level diagnosis and prognosis." Prior to entering academia, he was a Fellow at ARINC Incorporated in Annapolis, MD where he worked for almost 20 years. Dr. Sheppard performs research in probabilistic graphical models, deep learning, evolutionary and swarm-based algorithms, distributed optimization, and applications to system-level test, diagnosis, and predictive health. He has published over 200 papers in peer-reviewed conference proceedings and journals as well as two books on the subject of system-level diagnosis. In addition, Dr. Sheppard is active in IEEE Standards activities where, currently, he serves as a member of the IEEE Computer Society Standards Activities Board and is the Computer Society designated representative to IEEE Standards Coordinating Committee 20 on Test and Diagnosis for Electronic Systems. He is also the chair of the IEEE P2848 Prognostics and Health Management for Automatic Test Systems standards development working group under SCC20 and has served as an official US delegate to the International Electrotechnical Commission's Technical Committee 93 on Design Automation.
Dr. Bruce Maxwell received his Ph.D. in Forest Ecology and Crop Science.1990, Oregon State University; M.S. Agronomy/Weed Science,1984, Montana State University, 1978-79 Peace Corps Micronesia, B.S. Botany, 1977, Montana State University. Research and teaching specialization in applied plant ecology including agroecology, invasive plant ecology and weed biology. Research on the design and development of sustainable production systems and adaptive management strategies for annual and perennial weeds in crop and natural ecosystems. I am a lead author for the Agricultural Sector of the Montana Climate Assessment. My current research interests are focused on creating an on-farm experimentation framework utilizing precision agriculture technologies to improve profitability and sustainability of small grain production in the Northern Great Plains. My expertise includes plant population and community modeling to understand weed and invasive plant population temporal and spatial dynamics and their impacts on the ecosystems they occupy. Historically I have conducted research on crop-weed competition, herbicide resistance evolution, and economic thresholds of weeds and invasive species. I have also conducted research on land use change and the consequences of fire as a disturbance in plant communities.
Dr. Paul Hegedus, Ph.D. Ecology & Environmental Sciences
Herbicide resistant weeds are an increasing threat to agricultural systems around the world. The reliance of high input agriculture on pesticides has led to the evolution of herbicide resistance in over 250 species, some of which are resistant to multiple herbicide’s site of action. Herbicide resistance modeling has been around for decades, most often in the form of population-based models. These models treat all the individuals in a population as a unit while individual-based models act independently on each individual in the population. The strength of individual-based models is their ability to address and express the realism of biological systems. This research involves developing a generic individual-based herbicide resistant simulation model to determine the variation in resistant phenotype dynamics for a single dominant allele mechanism. From this work, the rate of evolution of resistance in an individual-based model has been found to be greater compared to a population-based model. Additionally, the individual-based model indicates the potential for resistance to decline in generations after a peak proportion of resistance is achieved in the population. This is likely due to mating between heterozygotes and/or homozygous recessive individuals that reintroduce the susceptible phenotype to the population. Further objectives for this research include assessing the range of resistance evolution outcomes under different assumptions about 1) the initial frequency of resistance in the population, 2) the initial number of patches of individuals, 3) the management strategy applied to patches, 4) the mating behavior of individuals, and 5) fitness costs associated with resistant alleles.
PhD Candidate Amy Peerlinck is developing Yield Optimization Prescriptions for DIFM Farm Trial Collaborators based upon predictive models developed by Giorgio Moreles at MSU.
Nitrogen fertilizer response (N-response) curves are tools used to support farm management decisions. The conventional approach to model an N-response curve is to fit crop yield in response to a range of N fertilizer rates as a quadratic or exponential function. The purpose of the model is to identify the profit-maximizing N rate given the costs of nitrogen and the price paid for the crop yield. We show that N-response curves are not only field-specific but also site-specific and, as such, economic optimal (profit-maximizing) rates should be calculated for each field each year promoting the use of on-field precision experiments (OFPE) utilizing precision agriculture technologies. We propose a methodology that allows deriving N-response curves automatically instead of using parametric curve-fitting approaches. Thus, we obtain a specific non-parametric N-response curve for each 10 m x 10 m cell of a grid virtually draped on the field. First, we train a convolutional neural network called Hyper3DNetReg using remotely sensed data collected during the early stage of the winter wheat growing season (March) to predict crop harvest yield values. The neural network models the behavior of the field under different environmental and terrain conditions. Then, we use the trained prediction model to obtain an N-response curve per cell by simulating what would be the yield response given a range of nitrogen rate values between 0 and 150 pounds per acre (lbs/ac). Results show that the shape of the N-response curve depends on the region of the field from which it was calculated. Related work will address the problem of generating prescription maps that merge the site-specific economic optimal rates calculated from our N-response curves while also minimizing the overall fertilizer applied and the number of jumps between consecutive cells' nitrogen rates.
Giorgio Morales is a PhD candidate developing a DIFM application to build predictive yield modelling for farmers.
I am a PhD student in computer science at Montana State University and a current member of the Numerical Intelligent Systems Laboratory (NISL). I hold a BS in mechatronic engineering from the National University of Engineering, Peru, and an MS in computer science from Montana State University, USA. My research interests are Deep Learning, Explainable Machine Learning, Automated Machine Learning, Computer Vision, and Precision Agriculture.
Taro Mieno is an Assistant Professor at the Department of Agricultural Economics at the University of Nebraska-Lincoln since 2015. The core of his academic interests lies in the intersection of agricultural production, policy, resource uses, and the environment. In particular, he is interested in precision agriculture for sustainable and profitable agricultural production, water economics (particularly around groundwater-irrigated agriculture) for sustainable high-productivity production, and agricultural policies (such as crop insurance) and their implications on agricultural production and resources use
Susan Vanderplas is an assistant professor in the Statistics Department at University of Nebraska, Lincoln, researching the perception of statistical charts and graphs, and applying computer vision and machine learning techniques to image data. She also works with the Center for Statistical Applications in Forensic Evidence (CSAFE) at Iowa State University, developing statistical methods for examination of bullets, cartridges, and footwear.
Areas of Expertise:
FORENSIC STATISTICS, STATISTICAL GRAPHICS, COMPUTER VISION, HUMAN PERCEPTION, MACHINE LEARNING, AND STATISTICAL COMPUTING
