Seminars

UGA Phenomics and Plant Robotics Center Seminar

 

Robotics for Agriculture

 

2:00 – 3:00 PM (eastern), Thursday, June 30th,  2022

ehsani_reza_170828-1

Presenter: Reza Ehsani

Professor
Mechanical Engineering
School of Engineering
University of California, Merced

ZOOM Link
Zoom ID: 6152579133
Password: 2021

 

Dr. Reza Ehsani received his Ph.D. in Biological and Agricultural Engineering from the University of California, Davis, where he worked on precision agriculture applications for high-value crops. He joined the Ohio State University as a faculty member and state precision agriculture specialist in 2000. His work at the Ohio State University included the application of precision agriculture for row crops with a focus on auto-steering systems. In 2005, he joined the University of Florida. He worked on developing tools and techniques for early biotic and abiotic stress detection disease sensors and machine enhancement for fruit harvesting machines. Currently, he is a professor of Mechanical Engineering at the University of California, Merced. His current research areas include soil and plant sensors, automation, and intelligent machines for agriculture.

 

Abstract:  Over the last decade, growers have had access to a significantly more diverse set of environmental, soil, and plant data. Recent advances in autonomous platforms and the commercial availability of autonomous tractors provided more opportunities for cost-effective data collection.  The recent advances in sensor technologies provided an opportunity to enhance existing soil and plant sensors by reducing the cost and size of some of the existing optical sensors. Also, new concepts and data analytics are emerging that can help develop better sensors for quantifying some of the soil and plant properties.  There is a need for more rugged and cost-effective sensors for the early detection of biotic and abiotic stress for high-value crops since the cost of late detection could be significant. This presentation provides an overview of sensors for different applications in high-value crops. It also introduces the newly NSF-funded Engineering Research Center called “the Internet of Things for Precision Agriculture” which is focused on developing new sensors and sensor platforms for different crops. The talk will cover some examples of ongoing projects in this center and explain how the data from these sensors are being used in developing the data-driven model for a high-value crop production system.

 

UGA Phenomics and Plant Robotics Center Seminar

 

AI and Robotics for Specialty Crop Agriculture

 

1:00 – 2:00 PM, Thursday, May 12th, 2022

Manoj Karkee

Presenter: Manoj Karkee
Associate Professor
Biological Systems Engineering
Center for Precision and Automated Agricultural Systems
Washington State University

ZOOM Link
Zoom ID: 6152579133
Password: 2021

 

Dr. Manoj Karkee is an Associate Professor in the Biological Systems Engineering Department at Washington State University (WSU). He received his PhD in Agricultural Engineering and Human Computer Interaction from Iowa State University. Dr. Karkee leads a strong research program in the area of sensing, machine vision and #AgRobotics ( https://labs.wsu.edu/karkee-ag-robotics/ ) at the Washington State University Center for Precision and Automated Agricultural Systems (CPAAS). He has published widely in such journals as ‘Computers in Industry’, ‘Journal of Field Robotics’, ‘Computers and Electronics in Agriculture’, and ‘Transactions of the ASABE’, and has been an invited speaker at numerous national and international conferences and universities. Dr. Karkee is currently serving as an elected chair for International Federation of Automatic Control (IFAC) Technical Committee 8.1, Control in Agriculture, as an associate editor for ‘Computers and Electronics in Agriculture’ and ‘Transactions of the ASABE’, and as a guest editor for ‘Journal of Field Robotics’. Dr. Karkee was awarded ‘2020 Railbird Engineering Concept of the Year’ by American Society of Agricultural and Biological Engineers, and was recognized as ‘2019 Pioneer in Artificial Intelligence and IoT’ by Connected World magazine.

 

Abstract: AI and Robotics has been and will continue to play a key role in reducing farming inputs such as labor, water and fertilizer and increasing productivity. Modular sensing, automation and robotics technologies developed in recent years (including mobile device-based Applications), decreasing cost and increasing capabilities of sensing, control and automation technologies such as UAVs, robust AI tools such as deep learning, and increasing emphasis by governments around the world in advancing AI-empower smart and automated technologies have created a conductive environment to develop and adopt smart farming systems for the benefit of agricultural industries around the world with a wide range of farming scale and environment. In this presentation, the author will first discuss the importance of AI-empowered precision and automated/robotic systems for the future of farming (Smart Farming, Ag 4.0). He will then summarize past efforts and current status of agricultural automation and robotics including examples from fruit harvesting and fruit tree pruning, followed by an introduction of the novel systems being developed in his program. At the end, major challenges and opportunities in agricultural robotics and related areas including potential future directions in research and development will be discussed.

UGA Phenomics and Plant Robotics Center Seminar

 

Agricultural robotics, robotic-aided harvesting and automation

 

1:00 – 2:00 PM, Thursday, March 17th, 2022

Stavros G. Vougioukas

Stavros G. Vougioukas
Professor
Biological and Agricultural Engineering
University of California Davis

ZOOM Link
Zoom ID: 6152579133
Password: 2021

 

Professor Vougioukas received his Ph.D. in Electrical, Computer and Systems Engineering from Rensselaer Polytechnic Institute, Troy, NY, in Robotics and Automation. Before joining the UC, he worked as post-doctoral researcher at the Department of Industrial Engineering at the University of Parma, Italy, and as faculty at Aristotle University, Greece, at the department of Agricultural Engineering. His main research interests are in the area of agricultural robotics and automation for specialty crops. He is currently leading several research projects on agricultural robotics – focusing on labor saving technologies – and precision yield mapping for specialty crops, with funding from USDA-NIFA, grower commodity boards, and private industry.

 

Abstract: Agricultural robots offer advanced sensing and actuation functionalities that can drastically improve crop breeding, precision management, and the efficiency of labor-intensive tasks. Fresh-market fruit harvesting is one of the most labor-intensive operations in specialty crop production. Despite decades of research, commercial-scale robotic harvesting is still an elusive target, especially for crops grown outdoors. This presentation will first discuss the main challenges for cost-efficient robotic harvesting. Then, it will present examples of robot-aided harvesting technology, which aims to increase harvest efficiency without replacing the farm workers. The use of this technology for precision yield mapping will also be discussed. Finally, directions for future research and development will be suggested, aiming to spark some ‘fruitful’ discussion.

UGA Phenomics and Plant Robotics Center Seminar

 

The AgAID AI Institute for Transforming Workforce and Decision Support in Agriculture

 

1:00 – 2:00 PM, Thursday, November 18th,  2021

Anantharaman Kalyanaraman

Anantharaman Kalyanaraman
Professor and Boeing Centennial Chair
Computer Science
Director of the AgAID AI Institute
Washington State University

ZOOM Link
Zoom ID: 6152579133
Password: 2021

 

Ananth is a Professor and Boeing Centennial Chair in Computer Science at Washington State University in Pullman. He is the lead PI and Director for the newly established AgAID Institute, led by Washington State University. He also holds a joint position at the Pacific Northwest National Lab and affiliate faculty positions at the WSU Molecular Plant Sciences Graduate Program and the Paul G. Allen School for Global Animal Health. Ananth received his Ph.D. from Iowa State University. Ananth works in scalable data science, focusing on problems and applications of data science at the interface of high performance computing, graph analytics, and computational life sciences. Research in his lab has been supported by NSF, DOE, CDC, and USDA. Ananth is a recipient of U.S. DOE Early Career Research Award and multiple conference best paper awards. Ananth is the elected Vice-Chair of ACM SIGBIO, and a Vice-Chair for the IEEE Technical Committee on Parallel Programming.

 

Abstract:

Tackling the grand challenges of 21st century agriculture (Ag) will require a fundamental shift in the way we envision the role of artificial intelligence (AI) technologies, and in the way we build agricultural AI systems. This shift is needed especially for complex agricultural ecosystems such as in the Western U.S., a multibillion-dollar industry, accounting for 300+ crop varieties. Farmers and policy makers in this region face variable profitability, major crop loss and poor crop quality owing to a number of challenges including: increased labor costs and fewer skilled workers, weather and production uncertainties, and water scarcity.  The newly established AgAID Institute, led by Washington State University, is a multi-institution, transdisciplinary coalition that will build partnerships between the Institute’s core members (six universities, two community/4-year colleges, and two tech companies) and a diverse range of key stakeholder groups. The overall approach will be guided by a cross-cutting mantra of adopt-adapt-amplify, i.e., adoption as a first principle in AI design, adaptability to changing environments and scales, and amplification of human skills and machine efficiency. Activities will include: using agricultural AI applications as testbeds for developing innovative AI technologies and workflows; serving as a nexus for culturally inclusive collaborative transdisciplinary learning and knowledge co-production; preparing the next generation workforce for careers at the intersection of Ag and AI technology; and facilitating technology adoption and transfer.

UGA Phenomics and Plant Robotics Center Seminar

 

Is there a role for biophysical models in an AI world?

 

Wednesday, October 13th, 1:00 – 2:00 PM

Gerrit Hoogenboom

Gerrit Hoogenboom
Professor and Preeminent Scholar
Department of Agricultural and Biological Engineering
University of Florida

ZOOM Link
Zoom ID: 6152579133
Password: 2021

 

Gerrit Hoogenboom is a Preeminent Scholar in the Institute for Sustainable Food Systems and Professor of Agricultural and Biological Engineering at the University of Florida. His main research focusses on the development and application of dynamic of crop simulation models and decision support systems. Applications range from precision management to climate variability and climate change, resources management, economic and environmental sustainability, and food and nutrition security. He currently coordinates the development of the Decision Support System for Agrotechnology Transfer (DSSAT; www.DSSAT.net), one of the most popular crop modeling systems across the world. Prior to his appointment at the University of Florida, he was a faculty member at Washington State University and The University of Georgia.

 

Abstract:

Crop models simulate the processes associated with the Genotype x Environment x Management interactions of the agricultural system to ultimately predict growth, development and yield of different crops. Although there are challenges to capture all the underlying physical, chemical, and biological processes in mathematical and statistical equations, there are many opportunities for applications. In this presentation, I will present various examples on the use of crop simulation models at different temporal and spatial scales.

UGA Phenomics and Plant Robotics Center Seminar

 

Replacing the Expert? – Detecting Deviations from Normal using Machine Learning

 

Wednesday, September 1st, 1:00 – 2:00 PM

David V. Anderson

David V Anderson
Professor
School of Electrical and Computer Engineering
Georgia Institute of Technology

ZOOM Link
Zoom ID: 6152579133
Password: 2021

 

Dr. David Anderson has been a professor at Georgia Tech for nearly 20 years.  Prior to that, he received his BS and MS from Brigham Young University and PhD from Georgia Tech in Electrical and Computer Engineering.  He has received numerous awards including the Presidential Early Career Award for Scientists and Engineers.  His core research is in signal processing but his research has ranged over many collaborative areas including IC design, processor architectures, and a variety of applications of signal processing and machine learning to audio and image processing problems.

 

Abstract:

Great strides have been made in machine learning, especially in image, speech, and natural language understanding due to the large datasets and the application of tremendous resources. However, for many problems, there is a lack of good data and labels and other characteristics needed for traditional machine learning. We have been exploring methods of learning from unlabeled and/or weakly labeled data by “learning normal” and how to characterize deviations from normal.

UGA Phenomics and Plant Robotics Center Seminar

 

Refining our understanding about agroecosystem variability of the Little River Experimental Watershed through the use of geospatial intelligence

 

1:00 – 2:00 PM, Wednesday, August 4th,  2021

Alisa W. Coffin

Alisa W. Coffin, USDA-ARS, Southeast Watershed Research Laboratory, Tifton, GA

Guoyu Lu

Guoyu Lu, Chester F. Carlson Center for Imaging Science, Rochester Institute of Technology, Rochester, NY

Dr. Alisa Coffin is a Research Ecologist at the USDA-ARS Southeast Watershed Research Laboratory in Tifton, GA, where she has worked for the last 6 years. Prior to working with USDA, Dr. Coffin worked with the US Geological Survey in Fort Collins, Colorado. She received her PhD from the University of Florida in Geography and has a background in landscape ecology and agroecology. Dr. Coffin’s research focuses on the use of remote sensing and geospatial analysis to scale measurements from local to watershed and landscape levels, and to evaluate tradeoffs in ecosystem services resulting from agricultural land management decisions.

 

Dr. Guoyu Lu is an Assistant Professor at the Chester F. Carlson Center for Imaging Science of Rochester Institute of Technology (RIT). Before joining RIT, he was a research scientist on autonomous driving at Ford Research and computer vision engineer at ESPN Advanced Technology Group. Dr. Lu finished his PhD Computer Science at the University of Delaware, MS degrees from University of Trento and RWTH Aachen University. He was a visiting scholar at the Auckland University of Technology. He has been awarded Tencent Rhino-Bird Young Faculty, US Department of Agriculture (USDA) New Investigator, and NSF CRII Award.  Dr. Lu has board research interests spreading across computer vision, machine learning, multimedia, robotics, and their applications in agriculture.

 

Abstract:

Geospatial intelligence is the conscious understanding of geography through the acquisition, analysis, and interpretation of spatial information about the environment. In south-central Georgia, where the Little River Experimental Watershed (LREW) is located, landscapes consist of rolling terrain used for timber and crop production, with crop fields edged by riparian forests. As a benchmark watershed for the Agricultural Research Service, scientists at the Southeast Watershed Research Laboratory have been collecting data on LREW water quality, quantity, and land use since the late 1960s. More recently the LREW has served as a key validation site for remotely sensed data products, such as the Soil Moisture Active Passive (SMAP) satellite soil moisture maps. While much of the data collected in the LREW relate to watershed-to-regional scale agroecological models and remote sensing data products, land management occurs at sub-regional levels where decisions are made at farm, stand, field and even sub-field levels. Therefore, it is necessary to refine our understanding about agroecosystem function to explicitly account for the spatial variability and dynamics occurring at sub-regional/sub-watershed levels. For example, as part of the Long-Term Agroecosystem Research Network (LTAR), efforts have been expanding to deepen our understanding about the balance of water and cycling of nutrients within sub-basins and fields of the LREW. To accomplish this, work has focused on collecting and analyzing data at levels that enable a better understanding of the variability in agroecosystem components at scales consistent with producer decisions. The required technologies for this effort include: uncrewed aerial systems (UAS) mounted sensors that regularly and consistently capture of optical/thermal/physical properties of soils and vegetation; seasonal in-situ sensors that provide information about microclimate, gas fluxes and soil water; and ephemeral manual measurements related to plant characteristics (e.g., leaf area index), biomass, and arthropod communities. The addition of finer-scale measurements adds a level of complexity to the automated data streams being collected in the watershed and requires the use of more advanced geospatial and artificial intelligence methods to synthesize the data. Efforts are continuing to test and advance new methods including 3D reconstruction and multi-frequency data fusion to provide finer resolution knowledge about agroecosystem responses to management practices in space and time.