Agenda Day 1

Time	Session
11:00-11:05	Opening Remarks Dhabaleswar K (DK) Panda, The Ohio State University
11:05-12:00	Keynote Speaker: Nicholas Butts, John Deere, USA Session Chair: Scott Shearer Title: Plows to Neurons: The Role of HPC and AI in Agriculture Abstract: The convergence of High-Performance Computing (HPC) and Artificial Intelligence (AI) is revolutionizing the landscape of autonomy and automation in agriculture. In this keynote, we explore how HPC serves as the backbone for advancing AI-driven systems, unlocking new capabilities in decision-making, real-time processing, and adaptive control. We emphasize the critical importance of performance per watt, highlighting the need to optimize energy efficiency as AI adoption scales in resource-constrained environments. Furthermore, we argue that while larger AI models have garnered significant attention, there is a pressing demand for more efficient and specialized AI architectures that deliver superior performance without compromising computational resources. Lastly, we discuss the necessity of innovative sensor fusion methods to enhance situational awareness and decision-making in complex, dynamic environments. By addressing these challenges, we pave the way for smarter, more sustainable, and scalable autonomous systems that will shape the future of technology. Speaker Bio: Nicholas Butts has over 25 years of experience in embedded systems. He holds both a B.S. and M.S. in Electrical Engineering from North Dakota State University. Currently, Nicholas is a Senior Staff Research Engineer at John Deere, where he focuses on high-performance computing at the edge and machine learning applications in perception and robotics. In the past he has worked on center pivot irrigation control systems, forklift displays, predictive semi-truck cruise controls, tractor displays, telematics devices, software-defined radios, cockpit video recorders, combine grain quality cameras, and digital signal processing for acoustic blockage monitors and seed counting. He has over 18 patents in the agriculture and aerospace markets.
12:00-12:30	Invited Talk 1 Speaker: Ben Craker, AgGateway, USA Title: AI – Agricultural Interoperability: Evolving Data Standards in the Era of Artificial Intelligence View Slides Abstract: For over two decades, AgGateway has addressed data interoperability challenges across the agricultural value chain, from standardized B2B messaging in the input supply chain to open-source tools that unlock high-resolution geospatial data from precision equipment. Throughout this journey, waves of technological innovation have shaped the member-led work, but few have shown as much transformative potential as the current surge in artificial intelligence. This session will explore historical parallels between past tech disruptions and today’s AI moment, highlighting how tools like chatbots and generative models are beginning to influence interoperability efforts. We’ll examine how agricultural data standards work is shifting and what new priorities are emerging among AgGateway members. Bio: Ben Craker is the Portfolio Manager at AgGateway, a global nonprofit organization whose members develop digital resources to address interoperability issues across agricultural industry sectors by providing a unique forum where companies can meet to solve digital challenges. In this role Ben helps facilitate working groups as they address pain points identified by the member organizations. He is also the president of the Ag Data Coalition (ADC), serving in that role since its founding in 2016. The ADC is a non-profit organization that promotes farmer control of data and operates an independent data repository farmers, researchers, and industry can use to store and permission access to data. The ultimate ADC goal is to make data storage a pre-competitive space in the agricultural industry. Prior to joining AgGateway staff he spent eighteen years in the farm equipment manufacturing industry at AGCO and Kuhn North America. He held both positions in marketing, sales, global partnering, and product management. He grew up on a farm in south central Wisconsin and graduated from the University of Wisconsin-Platteville with a BS in agricultural business with an engineering technology emphasis. He is still actively involved in the family farm, living in south-central Wisconsin with his wife and three children.
12:30-2:00	Lunch
2:00-3:30	Panel Discussion Panel Title: Current and Future Deployment of AI in Agriculture Panel Moderator: Scott Shearer Panelists: Nicholas Butts, John Deere, USA Ben Craker, AgGateway, USA Arthur "Barney" Maccabe, University of Arizona, USA Rich Wolski, University of California Santa Barbara, USA Steven J. Thomson, USDA National Institute of Food and Agriculture, USA
3:30-4:00	Coffee Break
4:00-4:30	Invited Talk 2 Speaker: Rich Wolski, University of California Santa Barbara, USA Professor of Computer Science, Duval Presidential Chair in Energy Efficiency Title: xGFabric: Coupling Sensor Networks and High-performance Computing Facilities with Advanced Wireless Networks for Near Real-Time Simulation of Digital Agriculture View Slides Abstract: Modern agriculture faces urgent challenges from climate variability and increasing global demands that require rapid, real-time decision support. Traditional High-performance computing systems, remotely sited sensor networks fail to provide the unified, adaptive insights needed for optimal crop management and biosecurity. Emerging 5G/6G technologies—with adaptive low-latency and high-throughput capabilities—offer a transformative opportunity to bridge this gap by creating a resilient, unified, and secure digital-physical fabric, enabling innovative scientific applications in digital agriculture. In this talk, we will present xGFabric -- and end-to-end system for coupling IoT devices and actuators with HPC systems to implement "modeling-in-the-loop" applications. xGFabric takes advantage of innovations in 5G/6G network infrastructure and a full-stack distributed runtime system to unify computing, network, and storage devices at all device scales. We will discuss the xGFabric architecture and discuss a working prototype that uses in-the-loop Computational Fluid Dynamics to generates real-time predictions of growing conditions for citrus in a specialized facility located in the California Central Valley. Bio: Dr. Rich Wolski is a Professor of Computer Science at the University of California, Santa Barbara (UCSB) where he holds the Duval Presidential Chair in Energy Efficiency. Having received his M.S. and Ph.D. degrees from the University of California at Davis (while a research scientist at Lawrence Livermore National Laboratory) he has also held positions at the University of California, San Diego, and the University of Tennessee, the the San Diego Supercomputer Center and Lawrence Berkeley National Laboratory. Rich has led several national scale research efforts in the area of distributed systems and is the progenitor of the Eucalyptus open source cloud project.
4:30-5:00	Invited Talk 3 Speaker: Steven J. Thomson, USDA National Institute of Food and Agriculture, USA Title: Funding Opportunities at the Intersection of Agricultural and Computer Science at the USDA-NIFA Abstract: The USDA-NIFA funds projects involving sensing, mechanization, modeling, water, nutrient, and general crop and animal management that involve Machine Learning and AI.  A broad MOU has been in place since 2023 between NIFA and NSF that also allows great flexibility in NSF program collaboration.  Pertinent grant programs will be outlined, and example funded projects will be highlighted. Bio: Dr. Steven J. Thomson is National Program Leader (NPL) with the USDA National Institute of Food and Agriculture (NIFA) and Fellow with the American Society of Agricultural and Biological Engineers (ASABE). He engages Universities, other federal agencies, and industry to provide national leadership in Capacity and Competitive Grant programs. Grant programs he manages or co-manages at NIFA include Data Science, Engineering and Precision Agriculture, and SBIR Engineering programs. NSF-collaborative programs he manages Include Foundational Research in Robotics, Cyber-Physical Systems, and AI Institutes. He was a Lead Scientist with the USDA ARS before joining USDA-NIFA in 2016 and served seven years on faculty in the Engineering Fundamentals and Biological Systems Engineering (BSE) Departments at Virginia Tech, where he received the Alpha Epsilon (Research/Extension) and Outstanding Faculty awards. He has authored or co-authored over 100 journal articles, two book chapters, and several Extension publications and software.
5:00-5:25	HARVEST Demo Matt Lieber, The Ohio State University Anirudh Potlapally, The Ohio State University
5:25-5:30	Closing Remarks Hari Subramoni, The Ohio State University Scott Shearer, The Ohio State University
5:35-7:00	Visit to SDSC Computing Facilities

Agenda Day 2

Time	Session
11:00-11:05	Opening Remarks Dhabaleswar K (DK) Panda, The Ohio State University
11:05-12:00	Keynote Speaker: Arthur "Barney" Maccabe, University of Arizona, USA Session Chair: Hari Subramoni Title: Building a Data Infrastructure for Agriculture in Arizona View Slides Abstract: While Arizona is not likely to be one of the first states that comes to mind when thinking about agricultural production in the US, agriculture in Arizona supports over 130,000 jobs, has a $23.3B economic impact, with exports to over 70 countries. The Yuma Valley in southwestern Arizona produces 90% of the leafy greens consumed in North America between November and March. Given the limited water supply, this kind of productivity could only be achieved by embracing technology. Today, this means embracing AI which means embracing the collection of data. Arizona has several resources, including Biosphere 2 and an outdoor phenotying facility , that will be essential for collecting the data needed to build new models needed for agriculture. Speaker Bio: Arthur B. (Barney) Maccabe is a professor in the College of Information Science at The University of Arizona. From 2009 to 2022, Dr Maccabe served as the Director of the Computer Science and Mathematics Division (CSMD) at the Department of Energy’s Oak Ridge National Laboratory (ORNL) and as the ORNL Point of Contact for the research portion of the Advanced Scientific Computing Research (ASCR) program in the Department of Energy, Office of Science. Prior to his appointment at ORNL, Dr. Maccabe spent over twenty-five years as a professor in the Computer Science Department at the University of New Mexico (UNM) where he graduated eleven PhD students and nine MS students. While at UNM, Dr. Maccabe also served as the director of the Center for High Performance Computing and as the Interim Chief Information Officer for the university. Professor Maccabe’s current research is focused on mechanisms and policies to ensure that the creators of data are able to realize value for the information they provide. His previous research focused on the design and development of system software for massively parallel systems. He was an architect for a series of lightweight operating systems for massively parallel computing systems. Dr. Maccabe has also conducted sponsored research in a wide- range of areas, including: dependence representation for compilers, network intrusion detection, network protocol offload, lightweight file and I/O systems, system software for sensor networks, and virtualization in high end computing systems.
12:00-12:30	Invited Talk 4 Speaker: Sheikh Ghafoor, National Science Foundation, USA Title: NSF Office of Advanced Cyberinfrastructure’s funding opportunity on HPC and AI Abstract: The Office of Advanced Cyberinfrastructure (OAC) supports and coordinates the development, acquisition, and provision of state-of-the-art cyberinfrastructure resources, tools and services essential to the advancement and transformation of domain science and engineering. OAC also supports forward-looking research and education to expand the future capabilities of cyberinfrastructure specific to science and engineering. In these efforts, OAC collaborates with all NSF Offices and Directorates to develop models, prototypes, and approaches to research cyberinfrastructure that open new frontiers for discovery, furthering the mission of the National Science Foundation and national science and engineering priorities. The goal of this talk is to provide an overview of OAC’s perspective, investments, and funding opportunities in HPC and AI. Bio: Sheikh Ghafoor is a professor of Computer Science at Tennessee Tech University. Currently he is serving as a program director at the US National Science Foundation in the office of Advanced Cyber Infrastructure in the directorate of Computer and Information Science and Engineering. His main research interests are: 1) High Performance Computing, 2) Computational Earth Science, 3) Computer Security, and 4) Computer Science Education. Dr. Ghafoor has published, secured external grants, and has mentored Ph.D. and master’s students in all these areas. Dr. Ghafoor has taught a wide variety of courses with primary teaching interest in HPC and computer networks-related courses. Dr. Ghafoor has been principal investigator on grants from the National Science Foundation, National Aeronautics and Space Administration, Department of Energy, National Security Agency, and other state and federal agencies.
12:30-2:00	Lunch
2:00-3:30	Research Paper Session Session Chair: Hari Subramoni Ortho-Fuse: Orthomosaic Generation for Sparse High-Resolution Crop Health Datasets Through Intermediate Optical Flow Estimation Rugved Katole OSU, Christopher Stewart, OSU HARVEST Inference: Characterizing Digital Agriculture Workloads across Compute Continuum Tian Chen, OSU, Quentin Anthony, OSU, Dhabaleswar K. Panda, OSU View Slides An HPC Framework for Multi-Modal Plant Phenotyping Integrating Controlled Environment and Open Field Studies Sungchan Oh, Purdue University, Libo Zhang, Purdue University, Yang Yang, Purdue University, Mitch Tuinstra, Purdue University View Slides PhenoTracker: A machine learning model to track grape phenology Nathan Balcarcel, Washington State University, Paola Pesantez-Cabrera, Washington State University, Kristen Goebel, Oregon State University, Markus Keller, Washington State University, Lav Khot, Washington State University, Alan Fern, Oregon State University, Ananth Kalyanaraman, Washington State University View Slides XAIPath: Temporal-Environmental Explainable AI Framework for Co-Contaminated Food Pathogen Detection in Microscopic Imaging Anas AlSobeh, Southern Illinois University, Amer AbuGhazaleh, Southern Illinois University, Namariq Dhahir, Southern Illinois University, Malek Rababa, Southern Illinois University View Slides
3:30-4:00	Coffee Break
4:00-5:00	Paper Presentation Session
5:00-5:25	Research Posters and Demo Session WILD-OV: Weakly-supervised Inference for Localization and Detection in Ecological and Agricultural Visual Scenes Using Open Vocabulary Models Anirudh Potlapally, OSU View Slides View Poster ArrayMorph: Efficient Edge-to-Cloud Data Management for Machine Learning Tinggang Wang, OSU View Slides Mining Earth's Digital Strata for Geospatial AI: Bridging Data Collection, Synthesis, and Self-Training for Intelligent Earth Observation Aswathnarayanan Radhakrishnan, OSU View Slides
5:25-5:30	Closing Remarks Hari Subramoni, The Ohio State University Scott Shearer, The Ohio State University