Funded Projects (Sorted by project start date descending order)

NSCC-IRG Track 1: Connecting Farming Communities for Sustainable Crop Production and Environment Using Smart Agricultural Drainage Systems

Award #: 2125484
Liang Dong
Michael Castellano, Hongli Feng, Matthew Lechtenberg, Xiaobo Tan
Sotirios Archontoulis, Baskar Ganapathysubramanian, David Hennessy, Patrick S. Schnable, Jaqueline Comito
October 1, 2021
September 30, 2025

In the US, agricultural drainage infrastructure benefits >22.6 Mha of cropland and is valued at ~$100B. As a proportion of total croplands, drained croplands produce a disproportionately large amount of grain but also release a disproportionately large amount of eutrophying nutrients to aquatic ecosystems. Drainage systems include individually-owned field drains that depend on the function of community-owned main drains. Climate change and agricultural intensification are causing farmers to increase the extent and intensity of drainage leading to a pressing need to balance productivity, profitability, and environmental quality when making drainage decisions. Further, because drainage systems include individually-owned and community-owned drains, decision-making involves complex techno-economic social issues together with understanding biophysical processes and requires balancing the needs of individual farmers, drainage communities, and surrounding regions. This project will develop an integrated decision-making platform to facilitate community decision making for precise prediction and management of drainage effects on water flow, crop production, farm net returns, and nutrient loss. The platform data will be made possible by new agricultural sensors and robots, innovations in behavioral economics and analytics tools. Development of the drainage decision-making platform will be guided by farmer stakeholders—including, the Iowa and Illinois Drainage Districts Associations, a national-level agricultural drainage management coalition, and directly with farmers—forming a continuous learning environment across scientists and farmers that fosters adoption of new technologies and transfer of the research process to the next generation of scientists, engineers, and agricultural professionals.

The project will build upon a suite of biophysical and social science advances in multiple areas, including bioinspired robotic snake sensors, in-situ soil nutrient sensors, computational modeling, and socioeconomics. The snake sensors will navigate through agricultural drainage networks to generate a high spatial resolution data stream about flow rates and nitrate concentrations throughout the belowground network. The soil sensors will enable continuous monitoring of nitrate dynamics. Process-based ecohydrological models, subsurface water transport models, and multiple spatiotemporal sensor outputs will be integrated to obtain high-resolution information about distributions of water and nitrate. Biophysical scenario analyses will assist decision-making for different agricultural management scenarios to balance resource use efficiency, profitability, and environmental performance. Socioeconomic science innovations will be integrated by learning how current systems are managed in the context of various heterogeneities across individuals and drainage districts, such as demographics, farm size, and presence of wetlands, and how new information provided by the proposed infrastructure interacts with human incentives and choices and consequent policy making.

NIFA AG2PI Collaborative: seeding the future of agricultural genome to phenome research for crops and livestock

Award #: 2021-70412-35233
Patrick Schnable
Jack Dekkers, Chris Tuggle, Eric Lyons, Brenda Murdoch, Jennifer Clarke, Carolyn Lawrence-Dill
September 1, 2021
August 31, 2023

To achieve sustainable genetic improvement of agricultural species and thereby mitigate environmental impacts and enhance the sustainability and profitability of US agriculture, the expertise of a broad community of agricultural genome to phenome (AG2P) researchers must be engaged, drawing from both crop and livestock communities, as well as integrative disciplines (e.g., engineers, data scientists, economists, and social scientists). Towards this end an existing NIFA-funded project (2020-70412-32615) is assembling and preparing a transdisciplinary community to conduct AG2P research. This project is: Developing a vision for AG2P research by identifying research gaps and opportunities; fostering first steps towards the development of community solutions to these challenges and gaps; and rapidly disseminating findings to the broader community. The current project will leverage these activities by using a competitive process in coordination with NIFA to provide additional seed grants to the AG2PI community. These seed grants will identify bottlenecks and explore novel solutions to community challenges to AG2P research. The project features a robust project management plan, involving leaders with the requisite experience managing large complex projects, implementation plans based on best practices and the science of team science, coupled with a robust assessment plan to refine best practices. A comprehensive and inclusive group of scientific partner organizations (including those serving the global community), a renowned scientific advisory board, and an external stakeholder group will assist the executive team in meeting its objectives and ensuring that its activities coordinate and complement existing programs.

AI Institute: AIIRA: AI Institute for Resilient Agriculture

Award #: 2021-67021-35329
Baskar Ganapathysubramanian
Sotirios V. Archontoulis, Liang Dong, Cassandra J. Dorius, Shawn F. Dorius, Priyanka Jayashankar, Adarsh Krishnamurthy, Carolyn J. Lawrence-Dill, Ajay Nair, Sreevatsal Nilakanta, Yumou Qiu, Soumik Sarkar, Patrick S. Schnable, Arti Singh, Asheesh K. Singh, Lizhi Wang
September 1, 2021
August 31, 2022

Our planet faces a daunting challenge: By the end of the century, world population will increase by 45%, cropland will decrease by 20% and our climate will become increasingly variable, threatening crops and putting communities at risk. We need to increase agricultural productivity by 70% to meet our growing food security needs - a challenge we are not able to meet under our current rate of progress. Now imagine a truly game-changing technology that can greatly accelerate this progress. It already exists in the form of artificial intelligence (AI). Using advanced sensor technology, scientists can create digital twins - virtual simulations that mimic real-world plants, crops and farms. For every year of biological data, digital twin-based AI systems can create hundreds of reality-based simulations that can: Streamline and revolutionize plant breeding to help scientists develop improved crop varieties that can better withstand environmental, pest and disease challenges while delivering higher yields and quality. Help farmers and their advisors adopt improved farming techniques and technologies that can boost their profits and help improve the long-term care of their critical land and soil resources. Provide governments with the insight they need to encourage and incentivize adoption of policies and practices that deliver the most benefit with the least environmental cost. Give agricultural companies the data and knowledge needed to develop more effective precision management systems and improved plant varieties that thrive with less water, fertilizer and pesticides. Drive economic development across the rural landscape through AI-inspired ventures. The leaders of the AI Institute for Resilient Agriculture (AIIRA) believe these breakthroughs - and more - can be a reality in the very near future. The Institute is bringing together AI experts with plant breeders, agronomists, geneticists and social scientists to accelerate the adaptation and use of AI-based technologies to transform agriculture to meet the needs of our world's growing population and increasingly climate-challenged food systems.

ARANET: Wireless Living Lab for Smart and Connected Rural Communities

US Ignite (Funded in part by the NSF award CNS-1827940 and PAWR Industry Consortium)
Award #: CNS-1827940
Hongwei Zhang
Yong Guan, Ahmed E. S. Kamal, Daji Qiao, Mai Zheng
Thomas Daniels, A-Ram Kim, Sang W. Kim, James E. Koltes, Joshua M. Peschel, Patrick S. Schnable, Anuj Sharma, Lie Tang
June 1, 2021
May 31, 2025

Agriculture and Rural Communities (ARA) is funded in part by the NSF award CNS-1827940 and PAWR Industry Consortium. See project website (https://arawireless.org/) for details.

NIFA AG2PI Collaborative: Creating a shared vision across crop and livestock communities

Award #: 2020-70412-32615
Patrick Schnable
Jack Dekkers, Chris Tuggle, Eric Lyons, Brenda Murdoch, Jennifer Clarke, Carolyn Lawrence-Dill
September 1, 2020
August 31, 2023

To address the challenges and opportunities of achieving sustainable genetic improvement of agricultural species, thereby enhancing the sustainability and profitability of US agriculture, the expertise of a broad community of agricultural genome to phenome (AG2P) researchers must be engaged, drawing from both crop and livestock communities, as well as integrative disciplines (e.g., engineers, data scientists, economists, and social scientists). The overall objective of this AG2PI is to assemble and prepare a transdisciplinary community to conduct AG2P research. The project will: Develop a vision for AG2P research by identifying research gaps and opportunities; foster first steps towards the development of community solutions to these challenges and gaps; and rapidly disseminate findings to the broader community. Towards these ends, AG2PI will sponsor and coordinate field days, conferences, training workshops, and seed grants. AG2PI features a robust project management plan, involving leaders with the requisite experience managing large complex projects, implementation plans based on best practices and the science of team science, coupled with a robust assessment plan to refine best practices. A comprehensive and inclusive group of scientific partner organizations (including those serving the global community), a renowned scientific advisory board, and an external stakeholder group will assist the AG2PI in meeting its objectives and ensuring that its activities coordinate and complement existing programs in plant and livestock G2P. Development of a cross-kingdom community prepared to tackle AG2P research offers opportunities to develop novel and creative solutions to enhance our understanding of both kingdoms, for the benefit of US agriculture and society.

High intensity phenotyping sites: a multi-scale, multi-modal sensing and sense-making cyber-ecosystem for genomes to fields

Award #: 2020-68013-30934
Patrick Schnable
Michael J. Castellano, Liang Dong, Baskar Ganapathysubramanian, Carolyn J. Lawrence-Dill, Lie Tang
June 1, 2020
May 31, 2023

To date much of the focus of agricultural research has been on increasing yield rather than ensuring the stability of yields within and across regions and years. It is of course important to develop higher yielding crop varieties. However, increasingly variable weather patterns have already begun to negatively impact agriculture. We currently lack the knowledge and tools necessary to efficiently develop resilient crop varieties that will provide stable and economically viable yields across increasingly variable environments. This problem is exacerbated by the fact that breeding new crop varieties takes 7-10 years, and at many locations today's weather may not be an accurate representation of the spectrum of weather new varieties will experience at that same locations 10 years from now. To address the challenge of breeding next generation resilient crop varieties we require accurate and mechanistically based models that can predict phenotypic outcomes based on genetic, environmental, and crop management data. Fortunately, advances in the plant sciences, computational and data sciences, and engineering offer the potential to help us address this challenge and thereby create a more sustainable, resilient and profitable US agricultural system.Developing accurate predictive crop models requires an enhanced understanding of the combined effect of crop variety (G) and environment (9), GxE. This in turn requires large collections of plant traits and environmental data gathered from common sets of crop varieties grown in diverse environments. With support from state and national Corn Growers, the Genomes to Fields (G2F) initiative has been conducting community-based experiments to do just that. Since 2014, G2F participants have been generating and analyzing genotypic, environmental, and crop management data from commercially relevant maize germplasm to learn how GxE interactions influence plant traits.The proposed project, G2F-HIPS, will support and intensify G2F by deploying, evaluating and validating a combination of established, image-based sensing technologies and promising new field-based agricultural sensors, generating and sharing reference data to foster community innovation, developing and democratizing analysis pipelines for phenotypic data, conducting proof-of-principle research projects to identify genes responsible for crop responses to environmental variation, and contributing in a substantial manner to the training of current and future agricultural researchers to make use of these innovations. As such, G2F-HIPS will promote the widespread adoption of new sensing technologies, methods of data analysis and thinking across the many G2F sites. In combination, these activities have the potential to facilitate a more mechanistic understanding of how phenotypes respond to genotypic and environmental variation, thereby facilitating the development of more resilient crop varieties that make more efficient use of agricultural inputs such as nitrogen and water, with corresponding environmental benefits.

BTT EAGER: A Wearable Plant Sensor for Real-Time Monitoring of Sap Flow and Stem Diameter to Accelerate Breeding for Water Use Efficiency

Award #: 1844563
Liang Dong
Michael J. Castellano, Patrick S. Schnable
May 15, 2019
April 30, 2021 - Extended thru April 30, 2023

Breeding plants for increased drought resistance without sacrificing yield is a major goal of breeding efforts around the world. However, drought resistance and yield tend to be inversely correlated. The rate that water flows through the stalk of plants on its way to the leaves is a critical variable in explaining differences in drought tolerance between different varieties of plants. However, current technologies for measuring the rate of this flow are bulky and can damage the plant when they remain applied for long time periods; thus they are not able to monitor plants throughout a growing season. In addition, the data collected from current sensors requires measurements of stem size in order to accurately measure flow rates. If stems grow over the course of the experiment, these measurements can introduce error is. This project develops a wearable plant sensor that enables accurate long-term quantification of flow rates across many environments and genotypes. Large numbers of low-cost sensors can be deployed in breeding programs enabling direct evaluation of lines. From these lines specific genetic loci controlling variation in sap flow rates under different environmental conditions can be identified. Likewise data from these sensors can be used in genomic prediction models that prioritize new breeding lines prior to the investment of resources field trials. This research will enhance workforce development by providing research opportunities to next-generation researchers at the intersection of engineering and plant science.

This collaborative project will integrate advances in sensors, microsystems, nanomaterials, and plant sciences to realize a novel sap flow measurement method that ultimately advances functional genomics research and the breeding of drought tolerant crops. The objective is to develop a wearable plant sensor for long-term, accurate, and affordable monitoring of sap flow over an entire growing season. The sensor design allows efficient thermal insulation of the microscale sap flow sensing unit from external environments, thus eliminating the traditional need of additional bulky thermal insulation setup and increasing the response to sap flow. Spatial averaging of multiple sap flow measurements around the stem enhances measurement accuracy. By using stretchability of the sensor materials and structures, physical constraints of the sensor on plant growth is minimized for long-term monitoring. The proposed wearable sensors can be manufactured at large scale and low cost, allowing it to be incorporated into breeding programs tolerating drought tolerance. Lastly, the sensors are characterized, calibrated and validated over time using gravimetric measures of plant water use in the greenhouse. Initial pilot field measurements are performed, where the sensors are applied to several maize hybrids grown under irrigated and non-irrigated conditions as part of the Nebraska contribution to Genomes to Fields (an existing public-private partnership).

BTT EAGER: Improving crop yield prediction by integrating machine learning with process-based crop models

Award #: 1842097
Lizhi Wang
Sotirios V. Archontoulis, Baskar Ganapathysubramanian, Guiping Hu, Patrick S. Schnable
March 1, 2019
February 28, 2021 - Extended thru February 28, 2023

Predicting crop yield is central to addressing emerging challenges in food security, particularly in an era of global climate change. Currently, machine learning and crop modeling are among the most commonly used approaches for yield prediction. This award supports fundamental research to combine the strengths of machine learning and crop models. Machine learning algorithms will be used to predict intermediate plant traits, which will then be fed into a crop model to predict grain yields across different environment and field management practices. Both conception and execution of this EAGER project depend on collaborations across multiple disciplines, including high-throughput phenotyping, object recognition, machine learning, optimization, computer simulation, and crop modeling. If successful, this research is expected to improve not only accuracy but also interpretability of yield prediction models, which will open numerous opportunities for downstream research and discoveries. The interdisciplinary effort will enhance the impact of science and engineering education across disciplines, while providing a collaborative and inclusive environment for all students to engage in cutting edge research activities.

Underlying yield prediction is one of the grand challenges of biology: understanding how phenotype is determined by genotype, environment, and their interactions. Machine learning algorithms are able to predict crop phenotype to reasonable accuracy based on genotype information, but most models have a black box structure and their results are hard to interpret. On the other hand, crop models offer biological insights into causes of phenotypic variation by providing explicit explanations of the interactions between traits and environmental conditions in different phases of the crop growth cycle, but the collection of trait measurement data and calibration of model coefficients are labor intensive, time consuming, and costly. The proposed approach is a nested model. Deep learning algorithms will be trained to predict leaf appearance rate from genotype and empirically measured trait data. Training data will be extracted from images of plant leaves obtained via field experiments that employ novel phenotyping technique. Next, the resulting predicted traits and environment data will be fed into the crop model to predict yield. If proven effective, this approach can be applied to study other plant traits to improve crop yield prediction.

CC* Integration: End-to-End Software-Defined Cyberinfrastruture for Smart Agriculture and Transportation

Award #: 1827211
Hongwei Zhang
Anuj Sharma, Patrick Schnable, Arun Somani, Ahmed Kamal
October 1, 2018
September 30, 2020 - Extended thru September 30, 2022

Imaging and other sensor-based understanding of plant behavior is becoming key to new discoveries in plant genotypes leading to more productive and environment-friendly farming.

Similarly, distributed sensing is seen as a key component of a safe, efficient, and sustainable autonomous transportation systems.

Existing research and education in agriculture and transportation systems are constrained by the lack of connectivity between field-deployed testbed equipment and computing infrastructure. To realize that connectivity, this project proposes to deploy CyNet wireless networks to connect experimental science testbeds to high-performance cloud computing infrastructures.

The CyNet project will:

  1. Deploy Predictable, Reliable, Real-time, and high-Throughput (PRRT) wireless networking solutions using the standards-compliant, open-source Open Air Interface software framework and commodity Universal Software Radio Peripheral (USRP) hardware
  2. Integrate these wireless networks with software defined networks to seamlessly integrate outdoor cameras, sensors, and autonomous vehicles, and connect these components to high performance cloud computing systems
  3. Implement an infrastructure virtualization system that partitions CyNet into programmable, isolated experiments
  4. Create an infrastructure management system that performs admission and access control and establishes specified resource allocation policies

Miniature, Low-cost, Field-deployable Sensors to Advance High-throughput Phenotyping for Water Use Dynamics

Award #: 2018-67021-27845
Michael Castellano
Patrick Schnable, Liang Dong
April 15, 2018
April 14, 2021 - Extended thru April 14, 2023

NON-TECHNICAL SUMMARY: This proposal will develop and deploy "wearable" (i.e., non-destructive, leaf-mountable) sensors for the measurement of water transport dynamics in maize. The sensors will be used to enable a high-throughput phenotyping platform that demonstrates the sensors' ability to discriminate among maize genotypes for plant water transport dynamics. The new sensors will advance plant sciences and agricultural research in a manner similar to how wearable human body sensors have advanced human health and biomedical sciences.Two types of sensors to be developed and deployed in field research plots: a relative humidity (RH) sensor and leaf water content sensor. The RH sensor will measure humidity and temperature at the leaf surface, and can self-adjust its size and shape to adapt to the growth of leaves. The leaf water content sensor will be developed using advanced Micro-Electro-Mechanical Systems technology, and will measure leaf thickness and water content. In years one and two, the sensors will be calibrated and validated. In years two and three, 400 of each type of sensor will be deployed across 50 maize hybrids in replicated plots. Each hybrid, selected from the Genomes to Fields Initiative (G2F), includes 24+ site-years of yield, weather and phenotype data from locations spanning Arizona to NY. Using sensor and grain yield data generated during the project in combination with yield and weather data from the G2F site-years, we will test the association of variation in water transport dynamics with variation of yield and yield stability among hybrids and in relation to environmental parameters.

OBJECTIVES: Water is generally the greatest limitation on crop production. Our goal is to develop and deploy "wearable" (i.e., non-destructive, leaf-mountable) sensors for the measurement of water transport dynamics in maize. The sensors will be used to enable a high-throughput plant breeding platform that demonstrates the sensors' ability to discriminate among maize genotypes for plant water transport dynamics. The new sensors will advance plant sciences and agricultural research in a manner similar to how wearable human body sensors have advancedhuman health and biomedical sciences. We have three objectives:Develop, calibrate, and optimize two types of low-cost, leaf-mounted, wearable plant sensors for accurate measurements of plant water dynamics.Use the sensors to develop a water use phenotyping platform that demonstrates the ability of sensors to discriminate among maize genotypes according to plant water dynamics.Test whether differences in plant water dynamics are predictive of yield or stability of yield across environments. Using sensor and grain yield data generated during the project in combination with yield and weather data from the Genomes To Fields project, we will test the association of variation in water transport dynamics with variation of yield and yield stability among hybrids and in relation to environmental parameters.

APPROACH: Two 'wearable' (i.e., non-destructive, leaf-mountable) sensors developed in this project will advance plant sciences and agricultural research in a manner similar to how wearable human body sensors have advanced human health and biomedical sciences. One sensor will measure relative humidity at the leaf surface using an adhesive tape-based sensor technology. The device is a patent-pending gas and vapor permeable tape patterned with graphine and graphine oxide. The graphine serves as an electrical resistor whose resistance changes with varying moisture levels. The second sensor will measure leaf water content and thickness using advanced Micro-Electro-Mechanical Systems (MEMS) technology. Using the two new sensors, we will develop a phenotyping platform that will characterize maize water use efficiency across different weather and soil environments. This will be accomplished by leveraging the Genomes to Fields maize phenotyping program that spans multiple locations from Arizona to New York.

Development of a PhenoNet - an Integrated Robotic Network for Field-based Studies of Genotype x Environment Interactions

Award #: 1625364
Lie Tang
Patrick Schnable
Srikant Srinivasan
September 15, 2016
August 31, 2019 -- Extended thru August 31, 2022

An award is made to Iowa State University to develop and deploy PhenoNet - an integrated robotic network for field-based studies of genotype crossed with environment (GxE) interactions. The core component of PhenoNet is a set of PhenoBots; lightweight robots that are able to autonomously navigate between crop rows using GPS and local range sensors while employing advanced sensing technologies to phenotype crop plants. The PhenoBots can measure indicators such as stalk size, plant height, leaf angle and tassel/inflorescence properties over time. The robots will be optimized for maize research and can be easily adapted for other row crops. The network (PhenoNet) is a universal platform which enables comprehensive field-based research on genotype and environment interactions. The broader impacts of this project are threefold. First, PhenoNet will have an important impact on society as understanding genome X environment interactions will help address the need for sufficient food, feed, and fiber for the planet's growing population, which is vital in an ever-changing environment. PhenoNet will bring "big data" more deeply into agriculture by cementing connections between plant scientists and engineers in their efforts to reach this goal. Second, this project is synergistic with the NSF-NRT project, "Predictive Phenomics of Plants", recently awarded to Iowa State University. The research and engineering outlined in this Major Research Instrumentation project will provide an outstanding opportunity for students from engineering disciplines, computer science, statistics, and agronomy to collaborate and engage in state-of-the-art interdisciplinary research. This project will also advance the training of current engineers and plant scientists who are experienced with networking, robotics and agronomy. Third, this project will reach out to underrepresented groups by targeting minority-serving institutions for student recruitment and will work with the Society of Women Engineers and other similar groups in seeking women participants to help meet the NSF-NRT award's efforts to broaden participation.

The PhenoBots are an important and essential advancement in the fields of agriculture and technology because they more efficiently characterize tall plants over time to their maturity. Previous technology and platforms are either incapable of, or are greatly hindered by various constraints. The design improvements of the Phenobots enable the robots to be more robust, stable, lightweight, integrated and economical. This creates a pathway for transformative research as it enables in situ, non-invasive monitoring of the traits of tall crops, like maize, over time. PhenoNet will consist of a network of four PhenoBots, which will be deployed by plant scientists in Iowa, Kansas, Minnesota, Nebraska, and Wisconsin. The data generated from high throughput phenotyping will address whether it is possible to predict the phenotype of a given genotype in a specified environment.