Our Projects

This Prototype-Open Knowledge Network (OKN) project seeks to ensuring the growth of a community of learning and practice centered on the OKN and its use in solving critical, real-world problems. This Proto-OKN Education Gateway, EduGate, effort will provide a comprehensive education platform that would also facilitate close collaborations and convergence among current OKN projects, as well as future entrants to the network. As the entry-point to the Proto-OKN environment and community, EduGate can have widespread impact and can contribute directly to the overall success of the Proto-OKN effort. While some of the OKN projects will be deploying newer technologies, including distributed ledgers, blockchain technology, and large language models (LLMs), many of the underlying technologies and standards that power OKN are well-established and have been around for some time. There is a plethora of extant educational material, tutorials, reference texts, and technical papers describing the state of the art of these technologies. The Education Gateway will bring together and link these different materials via the OKN Curriculum Knowledge Graph (CurrKG), which will be purpose-built for educating learners of all backgrounds.

The Education Gateway provides a unified, foundational learning platform, with customized pathways for users and other stakeholder from various sectors including government, industry, non-profit and other sectors. The project encompasses four major initiatives: (1) Community Development, Outreach, and Engagement (2) Industry Connection, Outreach, and Engagement (3) Education and Support activities among the cohort of OKN projects, and (4) Development of an OKN Curriculum Knowledge Graph (CurrKG) to assist with navigation through these materials.

NSF

ProtoOKN Theme 3: EduGate

Prototype-Open Knowledge Network (OKN) project seeks to ensuring the growth of a community of learning and practice centered on the OKN and its use in solving critical, real-world problems. Proto-OKN Education Gateway, EduGate, effort will provide a comprehensive education platform that would also facilitate close collaborations and convergence among current OKN projects, as well as future entrants to the network.

The Safe Agricultural Products and Water Graph (SAWGraph) project aims to build and test a knowledge graph as a novel tool for (1) monitoring and tracing Per- and polyfluoroalkyl substances (PFAS) in our environment, food and water supplies, and for (2) assessing how different communities are exposed to different levels of PFAS-related health risks. PFAS, commonly referred to as "forever chemicals" due to their resistance to degradation, pose significant health risks and have become pervasive in our environment, water supplies, and food chain. Progress on addressing PFAS contamination is hampered by the fragmented nature of relevant data and knowledge. SAWGraph will bring together diverse datasets that span: (1) sites of concerns with known or suspected PFAS contamination, (2) samples of PFAS levels in water, soil, plant and animal tissue, feed, and agricultural food products, and (3) sites and communities that may be at highest risk of exposure. This will be integrated with knowledge from EPA?s CompTox Chemical Dashboard on chemical composition, known toxicity, regulatory status, and properties relevant to transport and fate analysis. To evaluate and facilitate dialogue about SAWGraph, it will be equipped with prototype user interfaces that support query and faceted search, along with offering interactive geo-visualizations and spatial analysis functions.

SAWGraph will incorporate data considering social aspects, including PFAS exposure risks in disadvantaged communities, and seek expert input to balance health and economic implications of PFAS contamination, particularly regarding the potential impact on agriculture. In response to the evolving PFAS monitoring and safety regulations, SAWGraph will align its efforts with governmental stakeholders to ensure it remains supportive of the decision-making processes concerning PFAS regulations. To ensure success of the work, the team will partner with federal agency and state-level stakeholders who are key producers, maintainers, and users of PFAS data. Partnerships with stakeholders will enhance the efficacy of tools like SAWGraph in informing PFAS-related decisions, with the aid of stakeholder expertise for data access, processing, and interpretation. Through continuous interaction and collaboration with these partners and additional stakeholders, the project seeks to secure widespread buy-in and support, ensuring the graph's long-term success and sustainability beyond the project's duration.

NSF

ProtoOKN Theme 1: Safe Agricultural Products and Water Graph (SAWGraph): An OKN to Monitor and Trace PFAS and Other Contaminants in the Nation's Food and Water Systems

This project aims building knowledge graphs and applications using wheat data will be the first stage of this project. We are focusing on data sets based on wheat yield potential, optimal nitrogen rate application and fungal foliar disease management as the first stage of this project.

K-State GRIP

Towards a Global Food Systems Data Hub: Seeding the Center for Sustainable Wheat Production

This project aims to build knowledge graphs and predictive models using Urban Agricultural Systems in Kansas to Ensure Food Security.

K-State GRIP

Development of Resilient Urban Food Systems That Ensure Food Security in the Face of Climate Change.

This project aims to approach seed placement analysis by developing a computer vision (CV) system with embedded artificial intelligence (AI) and Knowledge Graphs (KGs). Current seeding technologies rely on manual methods to evaluate seed placement, which limits efficiency and insights into its impact on plant health, crop yield, and disease management. By integrating CV-AI systems, this project will capture real-time data on seed placement, trench characteristics, plant health, and weed diversity. The KGs will process this data to provide predictive models that optimize yield, sustainability, and innovation. The initiative will position K-State as a leader in advanced agricultural technology, driving innovation and supporting food security efforts in Kansas.

K-State GRIPex

Mapping Seed-to-Plant Life Cycle to Predict Yields - Integrated Artificial Intelligence and Data Analytics Approach

Over the past two decades, the Web Ontology Language (OWL) has been instrumental in advancing the development of ontologies and knowledge graphs, providing a structured framework that enhances the semantic integration of data. However, the reliability of deductive reasoning within these systems remains challenging, as evidenced by inconsistencies among popular reasoners in competitions. This evidence underscores the limitations of current testing-based methodologies, particularly in high-stakes domains such as healthcare. To mitigate these issues, in this study, we have developed VEL, a formally verified ℰℒ++ reasoner equipped with machine-checkable correctness proofs that ensure the validity of outputs across all possible inputs.

Koncordant Lab

VEL: Verified EL++ Reasoner

The goal of this research project is to experimentally investigate dropwise condensation and condensate freezing of water from the air on the international space station. It is hypothesized that the microgravity environment will affect both the droplet dynamics and freezing mechanisms due to the impact on heat transfer, humidity gradients, and crystal growth. This fundamental new insight into droplet dynamics and freezing couple with machine learning will enable new mechanistic models and the engineering of surfaces and process that can suppress or promote water collection and freezing to benefit life on Earth.

NSF

ISS: Predicting condensation and freezing behavior via a machine learning model

Antimicrobial use within diverse animal sectors, spanning domestic livestock, poultry, companion animals (e.g. dogs, cats, and horses), and minor species (e.g. fish, sheep, and goats) is a critical aspect of veterinary medicine. The overarching goal of this research is to leverage our tools and their data extraction capabilities to comprehensively characterize antimicrobial use practices within diverse animal populations, including domestic livestock, poultry, companion animals, and minor species. The end goal of this work is to provide thorough, high-quality data to regulatory agencies like the FDA to support evidence-based decision-making on where to focus antimicrobial use data collection efforts.

HHS

Bridging Critical Data Gaps in Veterinary Medicine Via Artificial Intelligence and Advanced Large Language Models to Procure Real-Time Antibiotic Use Data in Livestock, Poultry and Companion Animals