140816 research outputs found
Sort by
Scalable Machine Learning Framework for Adaptive Irrigation Management of Maize and Soybean in the U.S. Midwest
No full textConventional soil water balance (SWB) irrigation scheduling tools, such as FAO-56-based Spreadsheets and the Spatial Evapotranspiration Modeling Interface (SETMI), rely heavily on manual inputs and periodic field measurements, leading to delayed recommendations and missed opportunities to prevent crop stress. More critically, these tools lack the computational scalability and adaptability to leverage the high-frequency, high-volume datasets now available through modern sensing technologies. As precision irrigation increasingly depends on integrating spatially and temporally nuanced field information, there is a pressing need for decision-support systems that can process Big Data efficiently and respond in real-time. To overcome these limitations, we developed and validated a machine learning (ML) framework for near real-time prediction of soil water depletion (SWD) and site-specific irrigation recommendations in maize and soybean production systems. Unlike prior models, our approach integrates multi-source, multi-year (2020 and 2023) datasets, including remote sensing data, weather variables, soil properties, management practices, yield records, time-related features, and geospatial information, to train Decision Tree, Random Forest, Gradient Boosting, and Extreme Gradient Boosting (XGB) models. Feature selection combined agronomic domain knowledge, correlation analysis, and Random Forest feature importance to retain relevant predictors while minimizing model complexity. The SWD was typically between 0 mm (field capacity) and 110 mm (management allowable depletion with a dynamic root zone increasing up to 1000 mm for the second half of the season) for irrigated plots, and up to 180 mm in rainfed conditions. Among the models, XGB performed best in the 2024 independent validation, predicting SWD with high accuracy (maize: R2 = 0.72, RMSE = 22 mm; soybean: R2 = 0.78, RMSE = 24 mm). The average predicted SWD values were 53 mm (maize) and 54 mm (soybean), closely matching SWB Spreadsheet estimates (47 mm and 54 mm, respectively). Field deployment in 2024 demonstrated the model’s operational potential, with ML-generated irrigation recommendations (62–70 mm for maize; 73–83 mm for soybean) closely aligning with FAO-56 Spreadsheet (61 mm maize; 79 mm soybean) and SETMI (64–96 mm soybean) benchmarks. However, testing on independent 2021 data revealed reduced generalization performance, highlighting the need for more diverse training datasets. Overall, this study advances a practical, scalable, ML-driven decision support framework for real-time precision irrigation in commercial cropping systems
Review of \u3cem\u3eThe Land of Open Graves\u3c/em\u3e: \u3cem\u3eLiving and Dying on the Migrant Trail\u3c/em\u3e
No full textJason De León’s The Land of Open Graves: Living and Dying on the Migrant Trailis (2015), a raw and unwavering multidisciplinary exploration of the human cost of United States border policies, and this review reflects on his ability to meld ethnography, archaeology, forensic science, and narrative. De León exposes the brutal realities of the Sonoran Desert, where the U.S. policy of Prevention Through Deterrence (PTD) turns the landscape itself into a weapon. PTD directs illegal immigration away from more populated areas and instead towards the harsh deserts found occupying the border. De León holds a commitment to honoring the lives and dignity of migrants and critiquing the systemic necroviolence, including animal scavenging and loss of identity, that follows them in life and death. De León’s work insists that justice begins with listening to the voices of migrants, their families, and the landscapes that carry their stories. He does not seek to offer neat solutions but instead invites readers to witness suffering without looking away and to reimagine how we might engage with migrant death as both a humanitarian crisis and a call to action
Distributional Records of Blanding’s Turtles (Emydoidea blandingii) in Nebraska
No full textBlanding’s Turtle (Emydoidea blandingii) is a species of concern in North America as many populations have declined across its distribution. Environmental factors associated with alteration of natural ecosystems have played a role in declines leading to many isolated populations. Most populations exist in the Great Lakes region with a number of outlying populations, such as Nebraska. Understanding the current distribution of the species will facilitate regional management strategies to protect this species into the future. In Nebraska, Blanding’s Turtles were known from 23 counties prior to this study. Herein, we report on eight new county records, five (Blaine, Boone, Madison, Sherman, and Valley) that fill in gaps within the known distribution whereas three (Boyd, Dawes, and Knox) represent range extensions along edges of its known distribution in the state. These new records demonstrate that the complete distribution of Blanding’s Turtles in Nebraska is not yet fully understood, and future surveys are still needed to continue to update its distribution and monitor known populations
Uncle Sam and the Sea: An Administrative Red Herring
No full text“The law must be stable and yet it cannot stand still.”1
Compared to the Old Man and the Sea, the administrative state’s situation does not seem all that different.2 The idea of the administrative state has been around since the birth of civilization. There has always been a need for caretakers to protect the best interests of their people. While the administrative state is a testament of our society’s resilience and loyalty to the idea of one union providing for public good; it has become the Santiago.3 An administrative state is only as good as its output, and our current state cannot perform its’ desired function without the Manolin.4
1. Roscoe Pound, Interpretations of Legal History 1 (Cambridge Univ. Press 1923).2. See generally Ernest Hemingway, The Old Man and the Sea (1952).3. Id. (Santiago is the older fisherman character who is unable to bring in fish on his own, only bringing in the bones of a giant marlin he needs to catch to win his place back in society).4. Id. (Manolin is the young fisherman character, who has been learning from Santiago to improve his own fishing abilities).
I. Introduction
II. The ‘Santiago’ Administrative State ... A. Ancient Administrative Ideals: The Idea of Accountability ... B. Founding Ideas and Concerns: Concentrations of Power ... C. The New Deal Explosion and Progressive Era Problems: Judicial Activism ... D. The Modern Reality Check
III. The Loper Bright Future and the Chevron Past ... A. The Big Fish Called Chevron ... B. The Catch: Here Comes Loper Bright ... C. Suddenly Skidmore Is the Big Fish
IV. The ‘Manolin’ Solutions: Reconstruction, Reform, or Just a Drop in the Ocean ... A. Reconstruction & Reform: The Law Is Meant to Evolve ... B. Chevron and Loper Bright Are Red Herrings
V. Conclusio
Soil Health in Nebraska: Exploring Practitioners\u27 Needs and Insights from a Long-term Organic Farm
No full textSoil health is foundational to sustainable agriculture, environmental resilience, and long-term food security. Yet, the adoption of soil health assessments remains limited, often perceived as too technical, costly, or difficult to implement in real-world contexts. To better understand these challenges, the first chapter presents findings from a statewide survey of 41 soil health practitioners in Nebraska, including farmers, extension educators, NRCS staff, and conservation professionals. Respondents highlighted the need for simpler, more accessible, and context-specific tools for soil health assessment that help practitioners make informed decisions aligned with their management goals. Complementing these insights, the second chapter includes an independent, comprehensive soil health assessment conducted on a nine-year organic crop rotation at The Grain Place Foods Organic Farm in Central Nebraska. Physical, chemical, and biological soil health indicators were evaluated in 2021 across four crop phases: soybean, corn, popcorn, and pasture, and three benchmark systems: a conventionally managed cornfield, an unplowed pasture, and a 35-year-old tree line. Results showed that systems with perennial cover and reduced disturbance, such as the unplowed pasture benchmark and the soybean crop phase, performed better in terms of soil structure, nutrient cycling, and microbial activity compared to systems that are annually managed and conventionally tilled. These two chapters offer practical insights to improve soil health assessment in Nebraska. By combining practitioner perspectives with detailed field data, this work highlights ways to make soil health indicators more accessible, easier to interpret, and more useful across farms and diverse agroecosystems.
Advisors: Andrea D. Basche and Carolina Córdov
Clinical Case Study: The Effects of Saltatory Pneumotactile Stimulation of Glabrous Hand and Perioral Face on Cerebral Oxygenation, Cognitive Performance, and Sensorimotor Function in an Adult following Left Hemorrhagic Stroke
No full textStroke remains a leading cause of adult disability and a significant global health concern. Effective rehabilitation strategies for cognitive and communicative impairments following stroke are limited (Kuhn & Sharman, 2023). One emerging approach involves repetitive somatosensory stimulation to drive cerebral hemodynamic changes, potentially offering a novel rehabilitative method. Functional Near-Infrared Spectroscopy (fNIRS) is a non-invasive, accessible tool for monitoring these changes during stroke recovery. Prior studies suggest tactile stimulation rapidly affects brain hemodynamics (Custead et al., 2015; Oh et al., 2017). This clinical single-case study explored the use of GALILEO saltatory pneumotactile stimulation applied to the face and hand in an adult with Wernicke’s Aphasia following a major left hemorrhagic stroke. Stimulation was randomly applied before or after a cognitive and sensorimotor task protocol to evaluate its priming effects. The central hypothesis was that this repetitive stimulation would increase cerebral oxygenation and enhance task performance. The participant completed multiple sessions involving cognitive and sensorimotor tasks paired with random, bi-directional saltatory stimulation at velocities ranging from 5 to 105 cm/sec. Real-time cerebral oximetry monitored hemodynamic responses at frontal and parietal brain regions across four variables. Statistical analyses using regression and General Linear Mixed Models (GLM) showed that somatosensory stimulation significantly increased cerebral oxygenation and improved cortical vascular dynamics. These physiological changes were positively correlated with the participant’s improved performance on task-based protocols. Results support the potential of GALILEO somatosensory stimulation as a neurotherapeutic technique to enhance cognitive and sensorimotor function in stroke survivors. Overall, this study provides promising evidence that somatosensory stimulation can serve as a low-cost, evidence-based intervention to improve cerebral hemodynamics and functional outcomes in individuals recovering from stroke. While based on a single case, the findings contribute to the growing body of research supporting neuroplastic rehabilitation strategies, with implications for clinical practice in speech-language pathology and post-stroke care.
Advisor: Steven M. Barlo
Non-blackbox Robust Design of Machine Learning in Networks
No full textNetworked systems have become increasingly complex, with newer communication technologies and standards being added every day. Machine Learning (ML) and Artificial Intelligence (AI) paradigms have been adopted in networks to not only solve many fundamental problems, but also to allow seamless integration of components comprising them. The saying “let’s not reinvent the wheel” in ML/AI adoption implies that model architecture design be left for pure ML/AI researchers, while network researchers focus on input preprocessing (e.g. formatting the packet data to be fed to a model), hyperparameter fine-tuning and a trial-and-error approach to find the “best” result. This pipeline may work in theory, but is not always practical, especially considering the diversity in network behavior (e.g. communication patterns) in any given environment (even the same network that was used originally likely behaves differently, eventually). This dissertation is built around the following principle. While tackling the mathematical modeling of networks at-large is an impossibly daunting task and cannot be addressed in any single work, we sought out to address the task across multiple arcs. Intelligent techniques with ML/AI can help predict transfer patterns, resource usage, attack detection and even network infrastructure planning. For any semblance of network intelligence, modeling the statistical properties of the data are essential, either at micro- or macro-levels, and in the short- or long-term. This dissertation investigates the importance of careful mathematical modeling before/while adopting ML/AI techniques. We show that modeling the network behavior (say, traffic patterns for a traffic forecasting model) using a mathematical model (say, PDE or ODE) is sometimes more reliable than adopting a published ML model even if it promises great results in its original publication. Such effort produces objective, optimization and loss functions while keeping the ML/AI model architecture close to baseline. We chose to present proof-of-concepts across several selected problem statements inherent to the networked systems, namely, network management, large-scale network analysis, security and traffic classification, and traffic prediction. Each chapter in this dissertation focuses on one of these problems.
Chapter 2 presents a runtime Deep Learning (DL)-based approach for network management and orchestration in a cross-layer optical network setting. The work in chapter 3 presents a mathematical framework that models the traffic records collected from separate backbone routers collectively , and helps study not only its high-level statistical properties, but also cross-correlations between different collection points (i.e. different routers). Chapter 4 presents a novel way of tackling adversarial attacks on traffic classifiers, which deter and veer the classifier from accurately classifying the traffic samples. The classification model is designed to learn from encrypted packet bytes; the concepts of adversarial retraining and uncertainty quantification are used to improve adversarial robustness. Chapter 5 presents a traffic prediction approach for Research and Education Networks (RENs) via a mathematical model in the form of a system of Ordinary Differential Equations (ODEs) designed to capture the underlying data transfer behavior. In Chapter 6, we study the data/cache access patterns in the US High-Energy Physics (HEP) environment and design hourly access pattern prediction techniques using LSTM and CatBoost techniques. In Chapter 7, we studied the runtime network analysis problem, with the definition of “runtime network analysis” implying any network task with strict real-time needs. Motivated by the increasingly distributed aspect of many network systems, we combined theory from online and incremental learning and integrated it into Federated Learning (FL) paradigm, called Runtime Online Federated Learning (ROFL).
Advisor: Byrav Ramamurth
The Overturning of Roe v. Wade and People Capable of Pregnancy: An Interpretative Phenomenological Analysis
No full textOn June 24, 2022, the Supreme Court of the United States (SCOTUS) overturned Roe v. Wade in their decision within Dobbs v. Jackson Women’s Health Organization, removing the constitutional right to abortion within the United States (US). Leading up to this anticipated and highly politicized case, 13 states passed preemptive legislation (i.e. “trigger bans”) that immediately made abortion illegal following the Dobbs decision. Limited research has explicitly explored the intersection of sexual health and reproductive health from a psychological perspective. Grounded in a reproductive justice framework, this interpretative phenomenological analysis sought to understand how people capable of pregnancy living within trigger ban states experienced Dobbs and how, if at all, it impacted their sexual subjectivity. Eleven participants were interviewed and five themes emerged from their stories: 1) Sense-Making of Overturn Through Systems, 2) Perceived Impact of Overturn as it Relates to Diverse Privileges, 3) Reduced Reproductive Agency as Reproductive Being, 4) Intrapersonal Understanding and Enactment of Sexual Subjectivity, and 5) Reclaiming Lost Self-Expression and Connection Post-Overturn. Overall, the participants’ experience of the overturning of Roe v. Wade varied based on a few important factors, namely the degree to which they approved of the overturn, their desire for a pregnancy, and their willingness to have an abortion in the future, such that those in support of the overturn who wanted to become pregnant and were unwilling to have an abortion appeared to experience it the least negatively. Additionally, findings suggest that these factors protected the participants from changes in their sexual subjectivity. Clinical and policy implications are discussed.
Advisor: Dena M. Abbot
Authentication and Message Integrity Verification for Emerging Wireless Networks
No full textThis dissertation presents a comprehensive body of research on authentication and message integrity verification for emerging wireless networks, focusing on secret-free and physical layer security techniques across diverse, challenging, and unconventional environments.
It comprises four first-author contributions that span underground wireless systems, over-the-air (OTA) channels, vehicular communications, and nanoscale molecular networks.
The first contribution, Soil-Assisted Trust Establishment for Underground Wireless Networks (STUN), introduces a physical-layer trust bootstrapping protocol that achieves authentication and message integrity without pre-shared secrets. Leveraging underground-to-air propagation laws and trusted relay nodes, STUN resists active signal injection attacks and demonstrates security comparable to the unbalanced oil and vinegar cryptographic scheme, with practical applicability to underground agricultural IoT deployments.
The second contribution, RF Fingerprint-Based Location Authentication for Over-the-Air and Underground Wireless Networks (LAOUWN), proposes a robust location authentication framework based on channel impulse response (CIR) features and deep learning. It employs convolutional neural networks (ResNet-18/34/50) enhanced with transfer learning and adversarial domain adaptation, achieving over 90\% authentication accuracy across diverse testbeds. The system demonstrates complete resistance to advanced adversaries including Friis-based and ray-tracing-enhanced attackers whose success rate is reduced to random guessing.
The third contribution, VET: Autonomous Vehicular Credential Verification using Trajectory and Motion Vectors, presents a lightweight, privacy-preserving authentication protocol for vehicular networks. VET verifies credential legitimacy using trajectory similarity and motion-based trust metrics (TMVs), achieving a 97\% true positive rate under benign conditions and a 99.9\% detection rate against remote signal-manipulating adversaries. It remains agnostic to wireless channel variability and scalable to multi-attacker scenarios.
Finally, a Systematization of Knowledge for Security in Molecular and Nano-Communications surveys current threats and defense mechanisms in nanoscale networks. It identifies critical gaps such as the lack of structured taxonomies, active threat mitigation, and cross-layer integration and proposes novel solutions, including bio-inspired cryptographic models and enhanced error correction strategies.
Together, these contributions advance the field of physical-layer security by delivering robust, practical, and hard-to-forge mechanisms for secure communication in next-generation emerging wireless networks, especially in unconventional and resource-constrained settings where traditional cryptographic approaches fall short.
Advisor: Nirnimesh Ghos