Cyber-physical systems (CPS) have now started to play an increasingly important role in autonomous sensing, analysis, and tasking in a variety of agricultural settings ranging from sustainable farming to livestock monitoring. Many of these settings demand real-time analytics, at varying timescales, and the CPS devices have to coordinate among themselves over a variety of wireless networks. As various actors in these settings---from farmers to big agro companies---have much to gain from manipulating the results of these distributed systems, it is important to make these systems fault-tolerant and secure. This project, COPIA, seeks to provide the fundamental secure distributed computing primitives tailored for real-time agro-analytics in the face of malicious faults and network failures. Despite more than four decades of work on secure distributed computing, this CPS domain introduces new requirements that COPIA will address through fundamental innovations. First, COPIA will incorporate a principled framework for comparing energy costs of protocols and deriving optimal choices of cryptographic primitives to optimize energy use. This framework will permit leveraging CPS-specific opportunities, e.g., the difficulty for an adversary to equivocate (or offer two conflicting statements to two different neighbours) due to the omnidirectional nature of wireless links. Second, COPIA will achieve consensus in dynamic networks, i.e., where CPS nodes are mobile (e.g., drones). The technical challenge here is that the communication graph of nodes dynamically changes; most existing work assumes graph connectivity is unchanging throughout the execution of the protocol. Third, COPIA will address privacy in these distributed computing protocols, as the farmers are increasingly worried about companies extracting trade secrets from sensor data. This thrust involves hardening distributed computing protocols so that a limited number of node compromises does not divulge secrets. Overall, COPIA will make vital steps toward building novel, secure distributed CPS solutions for real-time analytics by addressing significant sources of safety, privacy, and availability vulnerabilities with the current CPS solutions. The project formulates an integrated research agenda that couples a strong theoretical component with an ambitious systems research component. As the importance of precision agriculture and the associated cybersecurity threat and potential vulnerabilities grow, the proposed principled approach will become a necessity for secure real-time agro-analytics.The team will demonstrate the innovations on experimental farms at Purdue University, secure embedded testbeds consisting of heterogenous embedded nodes at lab-scale, and on data from commercial livestock IoT monitoring deployments. Through these demonstrations, COPIA will energize a student community working on security of distributed embedded systems, and a community of farmers who realize profitability and environmental sustainability, e.g., reduced fertilizer use, early detection of livestock anomalies, and improved reliability and security of their monitoring systems.

Cyber-physical systems (CPS) have now started to play an increasingly important role in autonomous sensing, analysis, and tasking in a variety of agricultural settings ranging from sustainable farming to livestock monitoring. Many of these settings demand real-time analytics, at varying timescales, and the CPS devices have to coordinate among themselves over a variety of wireless networks. As various actors in these settings---from farmers to big agro companies---have much to gain from manipulating the results of these distributed systems, it is important to make these systems fault-tolerant and secure. This project, COPIA, seeks to provide the fundamental secure distributed computing primitives tailored for real-time agro-analytics in the face of malicious faults and network failures. Despite more than four decades of work on secure distributed computing, this CPS domain introduces new requirements that COPIA will address through fundamental innovations. First, COPIA will incorporate a principled framework for comparing energy costs of protocols and deriving optimal choices of cryptographic primitives to optimize energy use. This framework will permit leveraging CPS-specific opportunities, e.g., the difficulty for an adversary to equivocate (or offer two conflicting statements to two different neighbours) due to the omnidirectional nature of wireless links. Second, COPIA will achieve consensus in dynamic networks, i.e., where CPS nodes are mobile (e.g., drones). The technical challenge here is that the communication graph of nodes dynamically changes; most existing work assumes graph connectivity is unchanging throughout the execution of the protocol. Third, COPIA will address privacy in these distributed computing protocols, as the farmers are increasingly worried about companies extracting trade secrets from sensor data. This thrust involves hardening distributed computing protocols so that a limited number of node compromises does not divulge secrets. Overall, COPIA will make vital steps toward building novel, secure distributed CPS solutions for real-time analytics by addressing significant sources of safety, privacy, and availability vulnerabilities with the current CPS solutions. The project formulates an integrated research agenda that couples a strong theoretical component with an ambitious systems research component. As the importance of precision agriculture and the associated cybersecurity threat and potential vulnerabilities grow, the proposed principled approach will become a necessity for secure real-time agro-analytics.The team will demonstrate the innovations on experimental farms at Purdue University, secure embedded testbeds consisting of heterogenous embedded nodes at lab-scale, and on data from commercial livestock IoT monitoring deployments. Through these demonstrations, COPIA will energize a student community working on security of distributed embedded systems, and a community of farmers who realize profitability and environmental sustainability, e.g., reduced fertilizer use, early detection of livestock anomalies, and improved reliability and security of their monitoring systems.

Plant diseases pose an increasing threat to the nation's food supply and biosecurity in a changing environment. There is a growing risk of plant pathogens spreading through shipments of stock plants between production facilities, and from production facilities to growers or to retailers and consumers. Recent failures to prevent plant disease emergence and spread in the US has resulted in major economic losses (20-40% of total yield) for growers. One central challenge to preventing accidental pathogen dissemination and disease outbreaks is that many plant diseases are difficult to detect at an early stage and infected (possibly asymptomatic) plants can spread pathogens undetected when being shipped from one location to another. Once an emerging disease takes foothold in a new environment, eradicating such disease is extremely challenging.As our model system, we focus on disease detection and control in transplant facilities, which produce seedlings that will later be planted in production fields. These facilities are an amplifier of diseases in the agriculture production chain because of the use of greenhouses with limited environmental control and high plant density (average 800 plants per square meter, growing on plastic trays), that facilitate disease spread. A typical transplant facility grows over 500,000 plants at a time; therefore, manual scouting of the facility is time consuming and ineffective. Poor training in plant pathology and tight schedules of employee limit sensitivity of disease detection and spatial-temporal resolution. In summary, the transplant industry is a major source of disease outbreaks and can thus be a key point for disease control in the agriculture supply chain. To reduce the contribution of transplant facilities to disease outbreaks, we plan to develop a novel disease detection and control CPS to provide closed-loop disease control at a very early stage.This project includes three main objectives. First, an open-source robotic gantry system will be developed to automate the process of greenhouse scouting, plant sampling and plant removal to prevent disease spread. Second, a microfluidic device will be implemented to automate the process of library preparation from bacterial DNA extraction, amplification to metagenomic sequencing. Third, controlled experiments will be performed to determine the best methods for disease detection via nanopore, meta-genomic sequencing, machine learning, and computer vision. Different control strategies will be tested to determine the best approach that integrates data from metagenomic sequencing and the analysis of images of infected plants.The immediate goal of our project is to reduce the spread of plant diseases in the agriculture production chain by focusing on reducing disease instances in the transplant facilities and greenhouses. Our approach is to reduce the loss of plant products by optimization of disease detection and control strategies through robotics and automated genetic sequencing. In the long run, our project will contribute to the improvement of automation and reduction of the labor cost in agriculture. Our system, if successful, will reduce the loss of plants due to diseases for greenhouse operations and in plant production systems that utilizes transplant facilities.

This has the specific goal of significantly shortening the time to measure apple fruitlet growth, which will enable apple growers to manage crop load more precisely and efficiently. The technology developments used to do this will make fundamental advances in robotics and sensing for agriculture, and will take important steps toward using intelligent robots as labor saving devices in specialty crop production. The project will train graduate and undergraduate students in plant science and computer science, giving them important cross-disciplinary research experiences early in their careers. Ideas from the research project will be incorporated into a popular K-12 program that focuses on providing girls and young women with hands-on activities in robotics and agricultural science.1. Develop a 3-D camera, a robotic arm, and robot that and related software that can identify and measure fruit clusters, producing data for use in the current apple fruit thinning model MaluSim.2. Develop a cell phone application that can be used to measure fruit clusters, producing data for use in the current apple fruit thinning model MaluSim.3. Combine recent advances in 2D semantic image segmentation with 3D computer vision and mapping techniques to create robust perception systems that work in the unstructured clutter common in agricultural environments.4. Investigate the use of deep reinforcement learning approaches to solve manipulation tasks in these environments, and, specifically, it will explore the use of auxiliary reward functions to speed up the training process and transfer the result into real-world applications.5. Develop a template for development of similar imaging methods in other crop systems, solving other management problems where rapid, accurate measurement are required to more precisely manage inputs.6. Work with graduate, undergraduate and K-12 students showing the value of interdisciplinary work in agriculture and computer science.

Commercial apple growers must remove a portion of new apple fruitlets every year in order maintain fruit size, and prevent trees from develop a pattern of alternative year bearing, where some years there are many fruit, and other years very few. The challenge for a commercial grower is to remove a number fruitlets in the first three to four weeks after they form so as to optimize size and number of harvested fruit later in the year. To do this, commercial growers spray chemicals, generally two to four applications per year. The impact of a chemical thinner depends on weather and other factors. Thinning has historically been as much art as science, and growers often remove too few fruit, or occasionally, too many. In either case, production and profitability are less than they might be.Recently, horticultural researchers have developed a way for growers to more precisely determine if and when to apply chemical thinners. Basically, it requires that the new fruitlets be measured to see how fast they are growing. Some grow more slowly than others, or not at all, and these are the fruitlets that will drop. The method requires that the same fruitlets be measured two or more times over a two- to three-week period, and that many fruitlets be evaluated for each apple variety and block. The measurements are done by hand, with calipers, and each measurement has to be carefully recorded. While it makes thinning much more accurate, it takes a great deal of time, and growers are reluctant to do it.Computer technology in the form of smart-phones or robotically manipulated cameras offer a solution. This project will use pictures taken with phones and other cameras as a substitute for caliper measurements. Initially, many images will be used to build a measuring program using artificial intelligence. It's a challenge, as the computer has to pick out small apple fruitlets from among leaves, branches and other objects. It then has to determine how big the fruitlet is, and finally, make sure that measurements are taken from the same fruitlets when needed. However, if successful, growers will be able to quickly evaluate the need to thin using a set of cell-phone photos. This in turn, should improve production, and potentially reduce chemical use.

High throughput field phenotyping is a relatively new but rapidly growing research area, and it will remain a top agricultural research priority in the next decade. Remote sensing technologies, proximal sensors, platforms such as unmanned aerial vehicles (UAVs) and ground vehicles, and statistical data-driven analytics are being rapidly customized and deployed for high throughput phenotyping and used as plant performance measurement tools for crop improvement/breeding and precision agriculture systems for agronomy, soil science, and farm management. However, high costs, weather-dependent data collection (e.g., human-operated UAV's), data processing lag from complicated and/or inefficient analysis procedures, and a lack of standardization in sensor-based technologies are just a few of the recurring issues preventing these technologies from being more accessible. Additionally, each newly developed phenotyping technology or tool can measure only one or a few facets of highly quantitative and multi-variable traits in agriculture, such as yield, environmental stressors, or drought resistance.Therefore, the loop needed to make concrete advances in improving our food, fuel, and feed crops remains open with the current agricultural technology platforms. Here, we aim to close the loop by developing and deploying an integrated cyber-physical system for connecting plant phenotypes to genotypes with real-time crop management. With a robust wireless environmental sensor network, this integrated cyber-physical system, or "FieldDock", will deploy and manage daily UAV flights over target fields to automate crop modeling and genetic mapping to accelerate breeding efforts for energy efficient, nutritious, and high-yielding crops while tracking farm inputs to potentially guide crop management.Integrated cyber-physical systems like the proposed FieldDock are vital so that high throughput phenotyping tools are streamlined to be accessible for broad and applied agricultural use. With onboard GWAS and crop model processing, researchers will receive a constant stream of remote data that will allow them to focus on analysis and breeding strategies, rather than manually collecting data throughout the growing season. Breeding efforts across the country, both private and academic, employing the minds of many talented researchers and computer engineers could further fine-tune such a device for many different environments within an ever-changing climate. A standardized all-in-one platform like FieldDock could potentially unify global efforts to accelerate some of the most critical breeding goals of our time by making it affordable and lowering the barrier to entry for such a high end, advanced cyber-physical technology.For farmers, the FieldDock platform aims to connect spatial, temporal and multi-layered environmental data in real time while generating powerful predictive analytics and machine learning models that will drive reliable commands to automate field equipment throughout the growing season. A cyber-physical farm will self-learn with such a system in place and adapt to keep pace with the rapidly changing climate and the unpredictable challenges it will bring. FieldDock will act as an all-encompassing platform to gather all crucial field data needed to offer decision support for farmers in the short term while developing machine learning models from detailed datasets for the autonomous farm of the future.Ultimately, the proposed project will collect plot level data at a spatial and temporal resolution necessary for researchers and growers to develop and improve high-yielding, energy efficient crops that are resilient to variable climates, and also benchmark an integrated closed-loop smart farm system that can help agricultural growers reduce their energy inputs in real time.

Water and nitrogen represent two of the most expensive inputs to agricultural systems, and two of the critical constraints on overall agricultural productivity. Today, farmers generally over apply nitrogen fertilizer, because the potential cost of over application is less than the potential cost of achieving suboptimal yields. Similarly, in farm settings water is often over applied, particularly when studies are conducted at high resolution within individual center-pivot fields. We willdesignand validatean integrated cyber-physical system to collect and integrate data from remote sensing and low-cost field deployed wearable sensors and use machine learningand mathematical modeling to guide precision water and nutrient interventions in farmer's fields. This would mean that agricultural productivity can be sustained or increased while reducing overall nitrogen fertilizer and irrigation applications. Among the many beneficial effects to society as a whole would be 1) a decrease the environmental impact of agriculture; 2) decreased competition for scarce water supplies between agriculture and growing urban centers; and 3) increased farmer profitability, improving the economic viability of rural economies.The CPS will enable fusion of a large volume of spatio-temporally distributed multi-modal information to create a data-driven decision support platform that provides actionable information on optimal agricultural managementstrategies.The team will continue to leverage and develop extensive outreach and educational activities to train the next generation of scientists, through many existing STEM programs in Iowa State University and University of Nebraska-Lincoln.

Water and nitrogen represent two of the most expensive inputs to agricultural systems, and two of the critical constraints on overall agricultural productivity. Today, farmers generally over apply nitrogen fertilizer, because the potential cost of over application is less than the potential cost of achieving suboptimal yields. Similarly, in farm settings water is often over applied, particularly when studies are conducted at high resolution within individual center-pivot fields. We willdesignand validatean integrated cyber-physical system to collect and integrate data from remote sensing and low-cost field deployed wearable sensors and use machine learningand mathematical modeling to guide precision water and nutrient interventions in farmer's fields. This would mean that agricultural productivity can be sustained or increased while reducing overall nitrogen fertilizer and irrigation applications. Among the many beneficial effects to society as a whole would be 1) a decrease the environmental impact of agriculture; 2) decreased competition for scarce water supplies between agriculture and growing urban centers; and 3) increased farmer profitability, improving the economic viability of rural economies.The CPS will enable fusion of a large volume of spatio-temporally distributed multi-modal information to create a data-driven decision support platform that provides actionable information on optimal agricultural managementstrategies.The team will continue to leverage and develop extensive outreach and educational activities to train the next generation of scientists, through many existing STEM programs in Iowa State University and University of Nebraska-Lincoln.

Harnessing recent progresses on wastewater treatment, food security, data analytics, and machine intelligence, we propose to study novel optimized technology-driven controlled-environment agriculture (CEA) systems that can achieve high areal vegetable productivity to increase the food and nutritional security in urban areas with low operating cost and reduced energy consumption.Our project focuses on two core CPS research areas, i.e., control and data analytics, inspired by the design and operations of a pilot testbed at Georgia Tech for coupling the water and nutrients in domestic wastewater (DWW) to high-productivity CEAs. Food production in the CEAs must warrant the high cost of land in urban areas, which makes it necessary to reduce the total DWW-CEA operating cost and increase productivity. However, it is highly challenging to control and optimize this complex system of subsystems. In our case, we need to coordinate the Pilot-Plant and Pilot-Farm, examine their inter-correlation, and support dynamic and robust optimal decisions to achieve the highest production yield, while simultaneously satisfying various performance specifications on nutrient compositions, operating cost and energy consumption, and meeting other safety requirements of DWW-CEAs. Moreover, the profound impact of numerous operating conditions and parameters on the vegetable phenotype, yield and nutrient compositions during different growth periods need to be thoroughly understood. We have to move from model-driven CPS fundamentals to an integrated data-driven model-based approach. The objective of this 3-year interdisciplinary project is to maximize food productivity and nutrition while minimizing cost, energy and waste. The research is organized as four thrusts, each objective-driven and delineated as follows.InThrust 1, first-principles water models are adapted to the physical system and calibrated before on-site experimental validation. As first-principles models are not available for hydroponic agriculture, inThrust 2we adopt a hybrid approach where parameter-dependent biochemical reactions are supported by machine-learning algorithms with the purpose of parameter estimation and capture of possible un-modeled dynamics. A distinguishing feature ofThrust 2is the implementation of non-invasive spectroscopy and imaging to gain additional plant morphology and nutrition information. The subsystems (e.g., water and hydroponics) are then integrated as a system-wide model and validated experimentally. InThrust 3, we devise control algorithms with the purpose of achieving desired closed-loop performance despite the presence of disturbances and/or uncertain dynamics. As a part ofThrust 4, the resulting CPS is implemented in simulation software and experimentally validated to determine a feasible deployment scale. We expect that our novel, foundational research contributions will be immediately transferable to the water, waste, agriculture and remote sensing industries, but benefit other complex system control applications entirely.

The goal of this project is to use proprioception, localized sensing, and observed forces to develop robust, autonomous fruit picking methods. Fresh market tree fruit growers still rely on a large seasonal labor force for harvesting operations. Despite extensive research over the past thirty years, robotic harvesters are not yet commercially available. Prior work has considered manipulation a robot position control problem, disregarding the need for sensor input after physical contact with the fruit. However, when picking fruit such as apples and pears, professional pickers use active perception, incorporating both visual and tactile input about fruit orientation, stem location, and the fruit's immediate surroundings. We propose to embrace this physical contact by incorporating a rich set of in-hand sensors in an extended manipulation feedback loop with the goal of providing fine control over how the fruit is separated from the tree. To overcome the constraints of data collection in the field, we will develop a learning framework for compartmentalizing the tasks and design an instrumented proxy to serve as a training environment.While our primary focus in this project is fresh market apple and pear harvesting, we believe that this framework will be useful for numerous other agricultural applications that involve physical manipulation. For example, harvesting methods used for greenhouse sweet peppers and tomatoes are highly dependent on knowledge of peduncle orientation. However, automating production has been difficult due to similar challenges with occlusions and determining crop orientation. Another potential area of application for this learning framework is plant phenotyping, using soft tactile sensors, in addition to other sensor types, to measure a plant's physical properties.