CPS: Medium: Dig, Sip, Breathe: Automated Monitoring of Carbon and Water Cycles in Agriculture
Lead PI:
Justin Bradley
Abstract
Timely foreknowledge of soil water content (SWC) and soil organic content (SOC) has the potential to strongly impact watering and sequestration decisions, throughout the growing season. But currently, monitoring, reporting, and verification (MRV) of these is costly and time-consuming. Barriers include high equipment costs, infrastructure installation, and sensing capabilities. Our recent technological breakthrough in aerial robotics, the capability to dig into soil, coupled with advances in sensing technologies gives us the ability to build unmanned aircraft systems (UAS) to largely automate this process. We address the issue of SOC/SWC monitoring, reporting, and verification by building a multi-agent UAS team and accompanying controllers, task planners, and machine-learning classifiers capable of persistent atmospheric monitoring via tethered UAS, and heterogeneous sampling UAS for insertion of key sensor probes, and extraction of soil samples for automated collection. Together the UAS and algorithms provide a mechanism to collect automated, accurate, and high temporal and spatial resolution (e.g., much higher than satellites) SWC and SOC data which we then make available to the public. The data can be easily used to help make timely agricultural, sequestration, and water management decisions by stakeholders.
Justin Bradley
Performance Period: 01/01/2023 - 12/31/2025
Institution: University of Nebraska-Lincoln
Sponsor: USDA
Award Number: 2217327
CPS: Medium: Integrating sensors, controls, and ecotoxicology with decoupled aquaponics using brackish groundwater and desalination concentrate for sustainable food production
Lead PI:
Miguel Acevedo
Abstract
This project aims to develop a testbed of integrated sensors, controls, artificial intelligence, and ecotoxicology tools to engineer sustainable food production systems based on aquaculture, using brackish water. The testbed includes an automated recirculating aquaculture system based on desalination concentrate to demonstrate that brackish groundwater desalination costs can be offset by using its byproducts for profitable food production. Although aquaponics is becoming prevalent as a means of food production, efforts to develop these systems in brackish groundwater are very scarce. This project contributes to fill this need by understanding organism response to varying salinity and brackish groundwater chemistry, as well as impacting desalination technology as it proposes a profitable option for concentrate management. In addition to being the most efficient animal protein production system, aquaponics contributes to reduction of harmful effects on the environment. Brackish water aquaponics is of great interest for inland areas far from the coast since it includes products associated with marine resources. An important societal benefit of this project is demonstrating that it is possible to repurpose desalination byproducts to produce food, offsetting the costs of treatment, while reducing environmental impacts from those byproducts. Finding options for concentrate management, other than disposal, remains a major challenge to implement desalination in inland areas. Therefore, results of this project would have societal impacts in many areas with semi-arid and arid climate, scarcity of surface water, and brackish groundwater. Furthermore, the project would impact saline aquaculture producers worldwide, leading to protection of coastal ecosystems. We will conduct activities that directly contribute to broader impacts engaging with students of the local communities in three major ways: developing an exhibit and activity emphasizing interdisciplinary research conducted during the academic year, offering summer research experiences to students from underrepresented groups, and participating in science and technology outreach events targeting underrepresented groups.
Miguel Acevedo
Performance Period: 01/01/2023 - 12/31/2025
Institution: University of North Texas
Sponsor: USDA
Award Number: 2225976
Intelligent Resource Efficient Pond Aquaculture (IREPA): Cyber Physical System to Improve the Fish Farms Productivity in the U.S.
Lead PI:
Bing Ouyang
Abstract
Aquaculture, i.e., farming in an aquatic environment, plays an ever-growing role in food security in the US and worldwide. Since 2014 globally, more seafood consumed was farm-raised than wild-caught. Regrettably, aquaculture in the U.S. needs to catch up with the rest of the world, hindered by the high cost of resource-intensive operations. The labor shortage experienced in the industry exacerbates the problem.To revitalize the growth of the U.S. aquaculture industry, the proposed three-year Medium project - Intelligent Resource Efficient Pond Aquaculture (IREPA), aims to achieve transformative improvements in the productivity and sustainability in key pond aquaculture operations, namely, water quality management (i.e., monitoring and aeration), and feeding. The core concept of IREPA is to transform farm operations from the traditional reactive mode to proactive feedforward controlled processes underpinned by Cyber-Physical Systems (CPS), which include an AI-driven farm operation and control and heterogeneous robotic systems connected through a high-speed low-latency network infrastructure to seamlessly collaborate with and assist the human operators.
Bing Ouyang
Bing Ouyang received a Ph.D. degree in Electrical Engineering from Southern Methodist University, Dallas, TX, USA, in 2007. He joined Harbor Branch Oceanographic Institute at Florida Atlantic University (HBOI-FAU) at Fort Pierce, FL, USA, in 2009, where he is currently an Associate Research Professor and Director of the Systems and Imaging Lab (SAIL). Before joining HBOI-FAU, he was with Texas Instruments (TI), Dallas, TX, USA. From 2003 to 2009, he was an Algorithm Engineer with the TI DLP ASIC algorithm team. The projects in his lab encompass developing electro-optical sensors and image enhancement and computer vision algorithms for the underwater scenes and other visually degraded environments and developing robotic platforms and other novel structures to support effective sensing solutions. He holds nine US patents in the areas of video and graphics format detection and electro-optical sensors. Dr. Ouyang was peer-elected to TI's Member of Technical Staff in 2001. He was a recipient of the 2013 Young Investigator Research Program award from the US Air Force Office of Scientific Research. He received the 2016 FAU Researcher of the Year award at the Assistant Professor level.
Performance Period: 12/01/2023 - 11/30/2026
Institution: Florida Atlantic University
Sponsor: USDA
Award Number: 2313299
On-Line Control and Soft-Sensing for Thermal Food Processing Based on a Reduced-Order Modeling Approach
Lead PI:
Sanghyup Jeong
Abstract
Thermal food processing, which includes drying and cooking, is essential for preserving and sterilizing our food. However, it's not very energy-efficient, often using more energy than necessary.Improving the efficiency of this process could significantly reduce carbon emissions, benefiting our environment.However, the challenge is that this food processing method is subject to many variables. For example, changing the type of food being processed or the equipment used can disrupt the entire system, requiring it to be recalibrated or even rebuilt. Furthermore, certain essential data, like the exact moisture content in food during processing, is tricky to measure in real-time, which complicates optimization efforts.This project aims to revolutionize the way we manage these challenges. By creating a Cyber-Physical System (CPS), we should be ableto manage and account for both the variables we can measure and those we can't. This is done by building flexible models that can be quickly adjusted or combined with others, making the process more adaptable.Moreover, while there are detailed simulations available that can help predict the outcomes of certain inputs, these simulations take a lot of computational power and time. This project proposes an innovative solution: creating a simplified version of these simulations (Reduced-Order Modeling, ROM) which is faster but still reasonably accurate.The ultimate goal is to make thermal food processing smarter and more energy efficient. By using these new models and systems, webelieves they can optimize the processing conditions in real-time. The models and systems will be validatedusing specialized equipment at Michigan State University, focusing on how well the systemscan handle drying food with hot air.In summary, this project is about making our food processing greener and more efficient. It combines knowledge from food science, engineering, and technology to make a difference in the industry and, ultimately, our environment.
Sanghyup Jeong
Performance Period: 12/01/2023 - 11/30/2026
Institution: Michigan State University
Sponsor: USDA
Award Number: 2310591
On-Line Control and Soft-Sensing for Thermal Food Processing Based on a Reduced-Order Modeling Approach
Lead PI:
Cheol Lee
Abstract
Thermal processing operations including drying, cooking, and pasteurization rely on heat (mostly obtained by burning fossil fuels) and fluid motion to raise the temperature and reduce the moisture content of food. These processing operations are widely employed for food preservation and sterilization, directly affecting the food supply chain. Thermal processing operations are also infamously known for their low energy efficiency (defined as the minimum theoretical energy required divided by the actual energy consumed) ranging from 10% to 60% in case of drying. A 10% improvement in efficiency for process heating in the food and beverage industry would reduce carbon emission by 1.1 million tons, equivalent to 2.7 billion miles driven by a gasoline-powered car annually. It has been shown in earlier studies that both yield and energy efficiency can be substantially improved via control and optimization of processing conditions. For example, the throughput or production rate will be set as high as possible while balancing the need to reduce energy loss (e.g., by lowering air temperature) and satisfying food quality and safety constraints. This project will take the next step toward the optimal control of thermal food processing -development, validation, and implementation of the approach to maintain optimality in daily operations under the inevitable influences from strong process variability.A thermal food processing operation is subject to many variations. First, there continues to be a need for scale-up, equipment changes, and food-stock switchover. Although these discrete variations are directly measurable and quantifiable, any of such changes renders existing control parameters including set processing conditions completely irrelevant. Abrand-new model for process control has to be built from the ground up requiring extensive experiments and causing a serious disruption to regular production.Therefore, amodular and physics-based modeling approachrequiring minimal production disruptions is highly desirable.Second, there are the unmeasurable disturbances and variations, such as changes in moisture contents of incoming food stocks, unmonitored ambient conditions, and aging of equipment. Unlike in the case of the discrete and measurable variations, minor tuning of the control parameters would suffice to maintain the optimal operation. This would be a straightforward task if direct feedback of the product state were available. However, it is almost impossible to acquire real-time values of the moisture content and other qualities in food, because installation of a physical sensor in each individual productunder the harsh processing environment is impractical. Therefore, anew on-line approach based on integration of a high-fidelity process model with indirect feedbackis required to accurately estimate the product state.The research objective of this project is to build and evaluate a novel cyber-physical system (CPS) for real-time management of the process variability from both measurable and unmeasurable sources in optimal control of thermal food processing.The first-principle models,representing the complex spatio-temporal dynamics of thermal food processing,can potentially help achieving such a goal. The model parameters of first-principle models, such as the thermal conductivity of food, have physical meanings. Therefore, the food model, once developed in a lab setting without causing any production disruptions, will remain valid regardless of changes in processing scale and equipment.This opens the way to modular structure built on separate models of food and equipment, so a cumulative model can be deployed rapidly via plug-and-play coupling of pre-built components. Moreover, high-fidelity simulation of thermal food processing can be accomplished via Computational Fluid Dynamics (CFD) analysis. However, the high computational cost of CFD models renders their use for any time-critical applications intractable. A key task and the major novelty of the proposed work will be overcoming this obstacle via employment of aReduced-Order Modeling (ROM)approach, in which a high-order CFD model is replaced with a lower-order model, thereby drastically lowering the computational cost with little loss in accuracy. Taking advantage of the computational efficiency of the developed ROM,estimation of unmeasurable variationsand on-line optimization of processing conditions will be implemented. The proposed CPS for smart food processing will be implemented and validated usingthe pilot-scale equipment atthe Michigan State University (MSU)for continuous hot-air drying of food as a test case. The developed procedures and algorithm from this project are expected to be broadly applicable to a wide range of thermal processing operations for food and agricultural products. Improved yield and energy efficiency of thermal food processingwill contribute to societal benefit through innovative and sustainable food production.
Cheol Lee
Performance Period: 12/01/2023 - 11/30/2026
Institution: University of Michigan
Sponsor: USDA
Award Number: 2310590
CPS: Medium: FogAg: A Novel Fog-Assisted Smart Agriculture Framework for Multi-Layer Sensing and Real-Time Analytics of Water-Nitrogen Colimitations in Field Crops
Lead PI:
Arslan Munir
Abstract
This research project aims to fill the gaps in contemporary smart agriculture (SmartAg) technologies by proposing a fog-assisted framework, FogAg, that integrates multi-layer sensing and real-time analytics of a plant-soil system to help solve the complex biological puzzle of linking the effect and interaction of two important crop inputs, viz., water and nitrogen, affecting crop yield. FogAg will also help provide near-real time diagnosis of crop stresses and translate the data into usable agronomic decisions not only to boost crop productivity but also to increase overall yield per unit of resource used in farming systems.To meet the project goals and develop the proposed FogAg framework, scientific innovations in core cyber-physical systems (CPS) areas will be made on architecture, sensing, data analytics and machine learning, and modeling fronts. On the system-level CPS architecture front, the proposed FogAg architecture enables near real-time handling of latency-sensitive events in agriculture. On the device-level architecture, the project proposes Neuro-Sense, which will greatly support real-time signal/image processing by reconfiguration of data acquisition, computation, and communication parameters to assure energy-efficient performance for dynamically changing workloads. On the sensing front, the project proposes a sensing and imaging system for in-soil, above, below, and within plant canopy sensing. The proposed light emitting diode (LED) based multispectral imaging system will not only be economical but will also provide considerable flexibility by allowing different wavelengths to be used or substituted depending on measurement requirements as opposed to using filter-based methods common in multispectral systems or very expensive hyperspectral cameras. The proposed near-infrared (NIR) point measurement sensor will not only be an order of magnitude cheaper than a conventional diode array spectrometer but will also provide several options for interfacing and customizable optics. For in-soil sensing, a novel frequency response (FR)-based dielectric sensor and a mobile wireless sensor network are proposed that can simultaneously provide more accurate and real-time readings of soil nutrients and water content as compared to other commercially available soil sensors. On the data analytics and machine learning front, the proposed Neuro-Sense integrates a convolutional neural network (CNN) accelerator that will provide a higher throughput, utilization, area, and energy efficiency as compared to existing CNN accelerators by expoiting advances in deep learning acceleration.The proposed three-tier data analytics FogAg framework will enable processing of sensing data at three levels: Internet of things (IoT), fog, and cloud. On the modelingfront, tree-based predictive agronomic models will be developed that will utilize multi-layer sensed data along with historical yield and weather data to provide a variable-rate fertilizer and irrigation prescription map in near real-time to boost productivity and yield per unit of resource used in the farming system.The proposed FogAg framework with spatial and temporal scalability will find many applications in rural and urban development. The proposed technologies will help in efficient usage of resources and improvement in crop health, quality, and yield thus creating significant social and economic benefits in food security. The joint consideration of water-nitrogen colimitations will have positive environmental impacts by reducing the nitrogen footprint and environmental pollution. The investigators will incorporate significant research results obtained during this project into undergraduate and graduate education. For participation of underrepresented multicultural students in the project, the PIs will collaborate with KSU Multicultural Engineering Program (MEP)for supporting broadening participation in computing (BPC) and engineering (BPE) activities.
Arslan Munir
Performance Period: 07/01/2023 - 06/30/2026
Institution: Kansas State University
Sponsor: USDA
Award Number: 2225870
CPS: Medium: Integrated Real-time Monitoring, Diagnosis, and Predictive Data Analytics for Early Decision-Making and Treatment of Prevalent Diseases in Precision Dairy Farming
Lead PI:
Charles Qing Cao
Abstract
One of the significant challenges confronting our society today is ensuring the health and productivity of dairy herds which are vital to our food supply. Diseases such as mastitis and lameness pose a continuous threat to the economic viability of dairy farms. In response to these challenges, our project aims to harness the potential of modern Cyber-Physical Systems (CPS), advanced data analytics, AI/Machine Learning technologies to deliver a comprehensive solution for disease control in dairy farming. We aim to develop an innovative, integrated system to manage and improve dairy herd health effectively and sustainably. Our approach leverages state-of-the-art biosensors for real-time disease detection and a unique social network model that monitors animal-environment and animal-animal interactions. We also develop a digital twin platform for the farm to answer what-if questions for disease control decisions. This not only improves our understanding of disease transmission but also empowers dairy farm personnel with timely information for optimized herd management. This project is realized in collaboration with a dairy farm in the state of Tennessee and is anticipated to have nationwide implications.The proposed research engages in several critical areas of data analytics, disease control, and farm management, such as: (1) the development and optimization of innovative biosensors for real-time disease detection, (2) the creation of a farm-wide, real-time cow-based social network to track the mobility patterns of cows and their interactions, (3) the application of AI and big-data analytics to process, interpret and learn from the extensive data generated, and (4) the implementation and validation of the proposed system on real-world dairy farms, facilitating the transition from research to practice. Our close collaboration with farm management facilitates the broader impacts of the proposed work. Our findings will be disseminated across various platforms, targeting the scientific community, precision agriculture researchers, and the general public. Our educational initiatives and community engagement efforts will target the new generation of scientists and researchers, particularly encouraging participation from underrepresented groups, including African-Americans, Native Americans, Hispanics, and female students. The outcomes of our research, as well as all relevant educational resources produced during this project, will be accessible to the public via our project's online website.
Charles Qing Cao
Performance Period: 07/01/2021 - 06/30/2026
Institution: University of Tennessee Knoxville
Sponsor: USDA
Award Number: 2149788
CPS: Medium: Mitigating Heat Stress in Dairy Cattle using a Physiological Sensing-Behavior Analysis-Microclimate Control Loop
Lead PI:
Younghyun Kim
Abstract
Heat stress costs the US dairy industry an estimated $1.5 billion annually due to decreases in milk production and reproductive efficiency and, in periods of extreme heat stress, an increase in fatalities. Heat stress can also threaten animal welfare, putting at risk the long-term social acceptability of dairy farming. Despite the efficiencies that accompany high milk yield, high-producing cows in particular present challenges for the dairy farmer in terms of their vulnerability to heat stress. Heat stress is expected to remain a critical issue for the dairy industry in the coming decades as climate change models predict further increases in average temperatures and the frequency of heat waves. Unfortunately, in many of the currently operating dairy barns, cooling systems are designed and controlled without proper sensing and decision-making capabilities, and thus often fail to deliver effective cooling.This project seeks to solve this inefficiency and address the imminent challenge by developing a control system that measures and predicts the level of heat stress and maintains an optimal microclimate inside a dairy barn to minimize the impact of heat stress. The developed system will largely automate the decisions typically associated with heat-stress management and provide farmers with actionable information while relieving them of the dilemmas created by a surfeit of often contradictory options. More specifically, we propose to combat heat stress in dairy cattle by using a novel engineering system that relies on continuous physiological and micro-environmental sensing, real-time thermal-induced behavior analysis, and computational fluid dynamics (CFD)-based microclimate control. We will develop sensors that can continuously monitor cows' physiological and behavioral responses in real time. The physiological and behavioral data, augmented by real-time micro-environmental measurement, will be used to measure the overall level of heat stress in real time. A real-time analysis of the heat-stress inducing factors will then be used to adjust the barn's cooling system and prevent the animals' heat-induced stress from worsening. To achieve effective cooling with a minimum amount of energy and water consumption, CFD-based analysis and optimization will be used to find the optimal design and most efficient runtime control. A prototype will be implemented and deployed in UW-Madison dairy barns with different housing and ventilation systems in order to evaluate performance and cost effectiveness.The proposed research is expected to initiate a new direction in the drive to develop CPS for closed-loop control of dairy barns, one that should also advance the use of real-time data analytics and control in other precision-agriculture domains. This research will greatly improve modern dairy barns' ability to cope with heat stress while also reducing energy and water resource consumption and enhancing the welfare of dairy cattle. Moreover, the proposed research should prove highly relevant to other livestock industries that must deal with the effects of heat stress in indoor-housed animals (e.g., poultry, swine). The diversity of the research team we have created and the highly interdisciplinary nature of the research will involve a broad range of underrepresented students in computing and engineering, and by engaging the wider community through UW-Madison Extension programs and various outreach programs, we will be able to raise public awareness of sustainable farming and animal welfare.
Younghyun Kim
Performance Period: 07/01/2021 - 06/30/2024
Institution: University of Wisconsin - Madison
Sponsor: USDA
Award Number: 2038452
CPS: Medium: CPS-Enabled Variable Rate Technology
Lead PI:
Yeyin Shi
Abstract
The conventional management approach in agricultural production is applying water and chemicals at a fixed rate throughout the whole field. This practice did not consider the existence of in-field variability in spatial and temporal domains and results in over- and under-applications on crop and serious environment issues such as nitrogen leaking to and contamination of groundwater. Variable-rate technology is the key technology in agricultural production to address the in-field variability, maximize yield and profit, and minimize the agricultural inputs or footprints on the environment. Hence, this project pulls a multidisciplinary effort to address challenges in today's variable-rate technology (VRT) in agricultural production by tightly integrating sensing, networking, AI-based and process-based data analytics, and control systems with classic plant and soil biophysical principles and well-recognized management practices, to provide a generalizable and scalable framework for the real-time in-season variable-rate application. Meanwhile, it also improves the data analytics and decision-making models by turning the massive amount of data generated in daily agricultural production into a dynamic and distributed training process for model self-improving while keeping the farmers' privacy and computational efficiency.
Yeyin Shi
Dr. Yeyin Shi is currently an associate professor of agricultural intelligence in the Department of Biological Systems Engineering at the University of Nebraska-Lincoln. Her research and teaching program aims to use advanced sensing and information technology as well as data analytics to automate and improve the decision making and application processes in agricultural production and natural resource management. A major platform that Dr. Shi has been extensively working on is the unmanned aircraft systems (or drones). She and her group have developed data analytics with state-of-the-art computer vision and machine and deep learning techniques to monitor vegetation growth, biomass, and abiotic and biotic stresses, or predict yield. They also go beyond sensing but incorporate sensing and actuation for intelligent aerial applications. Dr. Shi’s research has been mainly funded by federal and state agencies. Dr. Shi is also passionate about college education and has been part of the thrust in the development of precision and digital agriculture curriculums. She teaches Site-Specific Crop Management (Precision Agriculture), Technologies and Techniques in Digital Agriculture, and Aerial Imagery Processing and Analysis to undergraduate and graduate students. Dr. Shi received her Ph.D. and M.S. degrees both from Oklahoma State University and worked as postdoctoral researchers at the Texas A&M University and the University of Florida prior to join in UNL.
Performance Period: 04/01/2021 - 05/31/2024
Institution: University of Nebraska-Lincoln
Sponsor: USDA
Award Number: 2039055
Subscribe to