Life Sciences Commons^™

Image Analysis And Machine Learning In Agricultural Research, Xinzheng Chen

Doctor of Plant Health Program: Dissertations and Student Research

Agricultural research has been a focus for academia and industry to improve human well-being. Given the challenges in water scarcity, global warming, and increased prices of fertilizer, and fossil fuel, improving the efficiency of agricultural research has become even more critical. Data collection by humans presents several challenges including: 1) the subjectiveness and reproducibility when doing the visual evaluation, 2) safety when dealing with high toxicity chemicals or severe weather events, 3) mistakes cannot be avoided, and 4) low efficiency and speed.

Image analysis and machine learning are more versatile and advantageous in evaluating different plant characteristics, and this could …

Identifying Early-Life Behavior To Predict Mothering Ability In Swine Utilizing Nutrack System, Savannah Millburn

Department of Animal Science: Dissertations, Theses, and Student Research

Early recognition of indicator traits for swine reproduction and longevity supports economical selection decision making. Gilt activity is a key variable impacting a sow’s herd life and productivity. The purpose of this study was to examine early- life behaviors contributing to farrowing traits including gestation length (GL), number born alive (NBA), number weaned (NW), and herd life (HL). Herd life was a binary trait representing if a gilt was culled after one parity. Beginning at approximately 20 weeks of age, video recordings were taken on 480 gilts for 7 consecutive days and processed using the NUtrack system. Activity traits include …

Causal Forest Approach For Site-Specific Input Management Via On-Farm Precision Experimentation, Shunkei Kakimoto

Department of Agricultural Economics: Dissertations, Theses, and Student Research

Estimating site-specific crop yield response to changes to input (e.g., seed, fertilizer) management is a critical step in making economically optimal site-specific input management recommendations. Past studies have attempted to estimate yield response functions using various Machine Learning (ML) methods, including the Random Forest (RF), Boosted Random Forest (BRF), and Convolutional Neural Network (CNN) methods. This study proposes use of the Causal Forest (CF) model, which is one of the emerging ML methods that comprise “Causal Machine Learning.” Unlike previous yield-prediction-oriented ML methods, CF focuses strictly on estimating heterogeneous treatment effects (changes in yields that result from changes in input …

Non-Destructive Classification And Quality Evaluation Of Proso Millet Cultivars Using Nir Hyperspectral Imaging With Machine Learning, Laruen E. Doyle, Julia R. Loeb, Nader Ekramirad, Dipak K. Santra, Akinbode A. Adedeji

Department of Agronomy and Horticulture: Faculty Publications

Millet is a small-seeded cereal crop with big potential and remarkable characteristics such as high drought resistance, short growing time, low water footprint, and the ability to grow in acidic soil. There is a need to develop nondestructive methods for differentiation and evaluation of the quality attributes of different of proso millet cultivars grown in the U.S. Current methods of cultivar classification are either subjective or destructive, time consuming, not allowing for the whole population to be tested, and requiring trained operators and special equipment. In this study, the feasibility of using near-infrared (NIR) hyperspectral imaging (900-1700 nm) to predict …

On Line Fast Detection Of Defective Rice Flour Based On Machine Learning Algorithm, Tan Lu-Min, Feng Xin-Gang

Food and Machinery

Objective: To realize the rapid on-line detection of defective rice flour. Methods: Non-contact data acquisition of rice flour blocks through cameras, image upload and processing, obtained the contour perimeter and area, approximate contour perimeter and area, approximate contour points and radius of the contour circle. According to the characteristics of rice flour block sample data, the SVM classification algorithm was used to analyze the sample set composed of multi feature data of rice flour block. Results: Compared with five algorithms, the average accuracy of GBDT classification algorithm was 89% with elapsed time of 1.10 s. The average accuracy of KNN …

Where To Invest Project Efforts For Greater Benefit: A Framework Formanagement Performance Mapping With Examples For Potato Seed Health, C. E. Buddenhagen, Y. Xing, J. L. Andrade-Piedra, G. A. Forbes, P. Kromann, I. Navarrete, S. Thomas-Sharma, Robin A. Choudhury, K. F. Andersen Onofre, E. Schulte-Geldermann

School of Earth, Environmental, and Marine Sciences Faculty Publications and Presentations

Policymakers and donors often need to identify the locations where technologies are most likely to have important effects, to increase the benefits from agricultural development or extension efforts. Higher-quality information may help to target the high-benefit locations, but often actions are needed with limited information. The value of information (VOI) in this context is formalized by evaluating the results of decision making guided by a set of specific information compared with the results of acting without considering that information. We present a framework for management performance mapping that includes evaluating the VOI for decision making about geographic priorities in regional …

Corn Nitrogen Nutrition Index Prediction Improved By Integrating Genetic, Environmental, And Management Factors With Active Canopy Sensing Using Machine Learning, Dan Li, Yuxin Miao, Curtis J. Ransom, Gregory Mac Bean, Newell R. Kitchen, Fabián G. Fernández, John E. Sawyer, James J. Camberato, Paul R. Carter, Richard B. Ferguson, David W. Franzen, Carrie A. M. Laboski, Emerson D. Nafziger, John F. Shanahan

Department of Agronomy and Horticulture: Faculty Publications

Accurate nitrogen (N) diagnosis early in the growing season across diverse soil, weather, and management conditions is challenging. Strategies using multi-source data are hypothesized to perform significantly better than approaches using crop sensing information alone. The objective of this study was to evaluate, across diverse environments, the potential for integrating genetic (e.g., comparative relative maturity and growing degree units to key developmental growth stages), environmental (e.g., soil and weather), and management (e.g., seeding rate, irrigation, previous crop, and preplant N rate) information with active canopy sensor data for improved corn N nutrition index (NNI) prediction using machine learning methods. Thirteen …

Identifying Conifer Tree Vs. Deciduous Shrub And Tree Regeneration Trajectories In A Space-For-Time Boreal Peatland Fire Chronosequence Using Multispectral Lidar, Humaira Enayetullah, Laura Chasmer, Christopher Hopkinson, Dan Thompson, Danielle Cobbaert

Aspen Bibliography

Wildland fires and anthropogenic disturbances can cause changes in vegetation species composition and structure in boreal peatlands. These could potentially alter regeneration trajectories following severe fire or through cumulative impacts of climate-mediated drying, fire, and/or anthropogenic disturbance. We used lidar-derived point cloud metrics, and site-specific locational attributes to assess trajectories of post-disturbance vegetation regeneration in boreal peatlands south of Fort McMurray, Alberta, Canada using a space-for-time-chronosequence. The objectives were to (a) develop methods to identify conifer trees vs. deciduous shrubs and trees using multi-spectral lidar data, (b) quantify the proportional coverage of shrubs and trees to determine environmental conditions driving …

Corn Nitrogen Nutrition Index Prediction Improved By Integrating Genetic, Environmental, And Management Factors With Active Canopy Sensing Using Machine Learning, Dan Li, Yuxin Miao, Curtis J. Ransom, Gregory Mac Bean, Newell R. Kitchen, Fabián G. Fernández, John E. Sawyer, James J. Camberato, Paul R. Carter, Richard B. Ferguson, David W. Franzen, Carrie A.M. Laboski, Emerson D. Nafziger, John F. Shanahan

United States Department of Agriculture-Agricultural Research Service / University of Nebraska-Lincoln: Faculty Publications

Accurate nitrogen (N) diagnosis early in the growing season across diverse soil, weather, and management conditions is challenging. Strategies using multi-source data are hypothesized to perform significantly better than approaches using crop sensing information alone. The objective of this study was to evaluate, across diverse environments, the potential for integrating genetic (e.g., comparative relative maturity and growing degree units to key developmental growth stages), environmental (e.g., soil and weather), and management (e.g., seeding rate, irrigation, previous crop, and preplant N rate) information with active canopy sensor data for improved corn N nutrition index (NNI) prediction using machine learning methods. Thirteen …

Evaluation Of Uav-Derived Multimodal Remote Sensing Data For Biomass Prediction And Drought Tolerance Assessment In Bioenergy Sorghum, Jiating Li, Daniel P. Schachtman, Cody F. Creech, Lin Wang, Yufeng Ge, Yeyin Shi

Department of Agronomy and Horticulture: Faculty Publications

Screening for drought tolerance is critical to ensure high biomass production of bioenergy sorghum in arid or semi-arid environments. The bottleneck in drought tolerance selection is the challenge of accurately predicting biomass for a large number of genotypes. Although biomass prediction by low-altitude remote sensing has been widely investigated on various crops, the performance of the predictions are not consistent, especially when applied in a breeding context with hundreds of genotypes. In some cases, biomass prediction of a large group of genotypes benefited from multimodal remote sensing data; while in other cases, the benefits were not obvious. In this study, …

Optimising The Carcass Merit Of Irish Beef Cattle Using Genetic And Non-Genetic Information At The Animal And Herd Level, David Kenny

Theses

Failure of beef carcasses to achieve desirable carcass specifications represent inefficiencies within the supply chain, namely greater carcass processing costs and the inability of the resulting primal cuts to conform to high-value market specifications. Analysis of a representative sample of prime Irish beef cattle conducted in this thesis determined that 59% of cattle fail to achieve the desired carcass specifications of the supply chain at slaughter. The objective of this thesis was to use readily available information to define strategies that could help to reduce this statistic. Firstly, the likelihood of Irish beef carcasses achieving the desired carcass specifications was …