Soybean production and profitability are impacted by crop achieving its yield potential. There are two main components of realizing the true genetic potential: (1) the assembly of favorable genetic combination of grain yield genes, and (2) the protection of yield from various deterrents including pests and diseases, and performance maximizing in a diverse set of growing and soil conditions. Our goals are to improve agricultural production output and positively impact IA farmers and the agricultural industry through the development of new products (cultivars and germplasm), gene discovery, research insights on pertinent topics of importance to farmers, processors, and consumers, and developing selection strategies that lead to higher yield and new products that will improve market penetration and expand export markets.

Our research projects combine hardware and software solutions to solve phenotyping bottleneck, which streamlines breeding and trait study pipeline for yield gain and improve protection traits. Our team uses digital phenotyping above- and below-ground traits and gleans insights using machine learning analytics. Each graduate student is given an opportunity to contribute in development or use of hardware tools and development of software solutions in a collaborative initiative; and are supported by scientific and professional staff to accomplish these goals. We mentor the next generation of plant breeders, develop and participate in teams that can work towards improved productivity and profitability of producers and processors, and provide enhanced nutritional quality for animal and human health. We integrate breeding and research activities with student mentoring and learning experiences. It is important to point out that most of incoming students came from a farming background with minimal or no computer programming knowledge, but have now developed expertise in this area making them valued in the job market, and also take this knowledge to their farms to help improve their crop production. They are the first generation of high-tech expert plant breeder employees building cultivars for our farmers geared toward technology driven higher profitability and sustainability. The fact that they come from farming background ensures that the future generation of US plant breeders will continue to be passionate about farmer issues and work for advancing their interests.

We utilize team based collaborations with faculty members from different disciplines, departments and colleges including engineering, social sciences, and statistics. Our group has become a research nucleus that brings together multiple researchers from several departments and industry. This creates wealth for the state and opportunities for IA farmers. We routinely receive requests from various stakeholders to access intellectual property we have created.

Our project goals are to develop superior soybean cultivars for Iowa farmers, to provide high yield and protection against crop stressors to keep Iowa farmers competitive and profitable. Our long-term team goal is to build highly desirable trait packages for our Iowa farmers. These will include an arsenal of performance genes and resistance against insects and diseases in soybean. This project will lead to new and improved varieties, new digital technology insights, and research in the area of aerial and ground robot based phenotyping. Our efforts to integrate performance using high throughput phenotyping (ground and aerial) continues to provide national and international prominence to our breeding and research activities and lead to benefits to Iowa farmers, farm economy and industries.

Research Goals: To develop superior soybean cultivars for Iowa farmers, to provide high yield and protection against biotic and abiotic factors to keep Iowa farmers competitive and profitable. Our long-term team goal is to build highly desirable trait packages for our Iowa farmers. Our efforts to integrate performance using high throughput phenotyping (ground and aerial) continues to provide national and international prominence to our breeding and research activities and lead to benefits to Iowa farmers, farm economy and industries.

Objectives: The main objectives of this project are to (1) increase soybean seed yield using genetic and phenomics tools, (2) improve seed quality (develop clear hilum, high oleic, high sucrose, improved oil and meal) varieties for increased market capture, and (3) develop breeding population to improve protection traits (biotic and abiotic stress tolerance). We will focus on infusion of engineering and data analytic tools, as well as work with a larger population pool.

• Short term: development of breeding populations for objectives listed in this project. We will release at least one high yielding new soybean variety in 2023/24 that is up to 5% higher yield than the mean of checks.
• Long term: cultivar and germplasm lines that meet the requirements of Iowa farmers and industry of high yield trait with desirable profile of traits.
• Proposed specific deliverables (long term; 2024): In our internal trials - checks used in MG 1 (IAS19C3), MG2 (IAS25C1), and MG3 (IAS31C1) will be used as benchmarks for yellow hilum soybean. These three varieties will be used as checks, as these are our recently developed varieties from ISU (with yellow hilum). Additionally, multi-location and -state testing will include conventional checks (except IA2102, all are non-yellow hilum). Uniform/Preliminary test checks will be used to show merit of the new ISU line to ensure farmers will have the ability to compare ISU lines with competitive checks. Commercialized entries will be entered in state wide testing, such as the Iowa Crop Improvement Association variety testing, which includes elite lines from major companies.

Update:
In the reporting period, a safe and successful harvest was completed in the fall of 2023. Post-harvest, seed processing, and trait data acquisition were also completed in late fall and winter. Selection decisions on advancements were made. Additionally, plant material was sent to the winter nursery to get the second crop cycle. Preparations for 2024 planting were initiated, and at the time of reporting, packaging for 2024 was in full swing.
Student updates on their research projects:
Matt Carroll graduated with a Ph.D. He is a research scientist in the Iowa Soybean Association's analytics team. Matt and co-investigators submitted a paper for peer review from a project that leverages soil mapping and machine learning to improve spatial adjustments in plant breeding trials. Spatial adjustments are routinely made in breeding trials to improve the estimate of plot seed yield. Moving mean and P-Spline are examples of spatial adjustment methods used in plant breeding trials to deal with field heterogeneity. Within trial spatial variability primarily comes from soil feature gradients. Therefore, information on soil nutrients and important soil factors must be included in breeding trials. We analyzed plant breeding progeny row and preliminary yield trial data of ISU's soybean breeding program across three years consisting of >43K plots. We compared several spatial adjustment methods: unadjusted (as a control), moving means adjustment, P-spline adjustment, and XGBoost. We established the usefulness of spatial adjustments at both progeny row and preliminary yield trial stages of field testing. We also provide ways to utilize interpretability insights of soil features in spatial adjustments. These results will empower breeders in public institutions and private companies to refine selection criteria to make more accurate selections and include soil variables to select for macro- and micro-nutrient stress tolerance in their breeding efforts.
Our team members were also involved in a project aimed at yield prediction. Soybean yield prediction is a challenging problem in plant breeding that is often simultaneously affected by many factors. Hyperspectral reflectance data from plants and soil data provide breeders with useful information about soybean plant health, and using these different types of data to predict yield is an active area of research. Furthermore, breeding programs encounter challenges such as data imbalance and external factors like genotype variability across different environments. These present significant hurdles in developing yield prediction models for large-scale breeding programs. In an interdisciplinary project, we predicted yield using hyperspectral reflectance and soil data to understand what scenarios offer the best chances to predict yield accurately. We reported an improved pipeline for yield prediction using hyperspectral reflectance data that performs well for large-scale breeding programs.
Matheus Krause, a Ph.D. student with me and Dr. Beavis, graduated with a Ph.D. from ISU and now works for Corteva. Matheus's published paper that examined models to estimate genetic gain of soybean seed yield from annual multi-environment field trials. In this study, we recommended multiple selected models to obtain a range of reasonable estimates. These results will be helpful to plant breeders.
Sarah Jones, Ph.D. student in the team, processed drone imagery from 3 years of drought stress screening of 450 PI lines and collaborated with an engineering colleague (from Dr. Sarkar's group) to develop a ML pipeline for drought severity classification and early detection.
Liza Van der Laan is preparing her thesis chapter on the screening a diverse panel of 450 soybean accession for heat stress tolerance. This project aims to identify heat tolerant accessions that will be useful for breeding for abiotic stress tolerance, as well as to understand the genetic mechanisms controlling heat stress tolerance. The protocol for screening heat stress tolerance and other abiotic stressors of drought and flood was expanded in our program this past year with work on developing a field based contained stress platform.
Sam Blair has continued researching drone-based relative maturity and ground robot yield estimations. Large-scale data collection using RGB imagery for the drone-based relative maturity estimation project was completed in 2023. ML models were trained to make automatic maturity ratings. This model has shown promising results, and we aim to deploy it in the 2024 field season. The results will be useful to other breeding and field research programs in the public and private sectors.
Based on multi-state testing for yield, agronomics, quality and yield protection traits, foundation seed increase was done for previous releases. Two new invention disclosures were made to ISURF during the reporting period. One of the new varieties is a conventional non-GM line with high yield and suitable for production in central and southern IA. The other variety is combines good yield and higher protein and yellow hilum for soybean food industry. This new variety is suitable for IA production regions. This variety provides farmers access to a higher protein line with protein levels of >42% on dry weight basis compared to generic beans that have ~37%.
We continued our partnership with the Iowa Soybean Association with funded projects, AIIRA, COALESCE, and SIRAC, that USDA and NSF supported. These unique linkages provide farmer-motivated solutions that enhance breeding and crop production through the use of machine learning and robotics.
In 2023, we entered ISU experimental lines in the Uniform Soybean tests, which are grown in locations across several mid-western states. Several candidate varieties performed well. Before commercialization, we will complete the testing of our most advanced and promising lines in multiple states.

Updated February 2, 2025:
Short summary
Two new varieties were disclosed to ISURF: IAS27C1 and IAS27HPHO1. Foundation seed increase was completed.
Seven journal research or review papers, one book chapter, one magazine article, and ten conference or pre-prints were published. Project objectives were successfully completed, including planting, data collection, plant selections, harvest, variety selection and data analysis.
Research advances were made in biotic and abiotic stress tolerance traits, with applications in variety development.

Full report:
NEW VARIETIES
IAS27C1 has high yield in multiple states, and resistance to sudden death syndrome, white mold and soybean cyst nematode, and good tolerance to iron deficiency chlorosis. It has improved tolerance to flooding. It is 2.7 RM soybean with black hilum. In MI-Central it ranked 3rd out of 73 entries in the test. In WI-South, it ranked 9th out of 32 entries in the test. In IA-North and IA-Central it ranked 17th out of 36 and 39 entries, respectively, in the tests. In Illinois (regions 1, MG2.7-3.4), it ranked 6th out of 29 entries. In Illinois (region 2, MG2.4-3.2), it ranked 21 out of 26 entries.
IAS27HPHO1 is a high protein line (42-43% dw) with oleic acid >75%. It has yellow hilum and 2.7 RM. It’s seed yield was comparable to yellow hilum check, IA2102.

RESEARCH REALTED PAPERS
Several papers were published that relate to the Iowa Soybean Association supported projects.
Journal Articles
1. Chiozza, M. V., Parmley, K. A., Schapaugh, W. T., Asebedo, A. R., Singh, A. K., & Miguez, F. E. (2024). Changes in the leaf area-seed yield relationship in soybean driven by genetic, management, and environments: Implications for high-throughput phenotyping. in silico Plants, 6(2), diae012. https://doi.org/10.1093/insilicoplants/diae012
2. Chiranjeevi, S., Saadati, M., Deng, Z. K., Koushik, J., Jubery, T. Z., Mueller, D. S., O’Neal, M. E., Merchant, N., Singh, A., Singh, A. K., Sarkar, S., Singh, A., & Ganapathysubramanian, B. (2024). InsectNet: Real-time identification of insects using an end-to-end machine learning pipeline. PNAS Nexus. https://doi.org/10.1093/pnasnexus/pgae575
3. Feuer, B., Joshi, A., Cho, M., Chiranjeevi, S., Deng, Z. K., Balu, A., Singh, A. K., Sarkar, S., Merchant, N., Singh, A., Ganapathysubramanian, B., & Hegde, C. (2024). Zero-shot insect detection via weak language supervision. Plant Phenome Journal, 7(1), e20107. https://doi.org/10.1002/ppj2.20107
4. Fotouhi Ardakani, F., Menke, K., Prestholt, A., Gupta, A., Carroll, M. E., Yang, H. J., Skidmore, E. J., O’Neal, M. E., Merchant, N., Das, S. K., Kyveryga, P., Ganapathysubramanian, B., Singh, A. K., Singh, A., & Sarkar, S. (2024). Persistent monitoring of insect pests on sticky traps through hierarchical transfer learning and slicing-aided hyper inference. Frontiers in Plant Science, 15, 1484587. https://doi.org/10.3389/fpls.2024.1484587
5. Saadati, M., Balu, A., Chiranjeevi, S., Jubery, T. Z., Singh, A. K., Sarkar, S., Singh, A., & Ganapathysubramanian, B. (2024). Out-of-distribution detection algorithms for robust insect classification. Plant Phenomics, 6, 0170. https://doi.org/10.34133/plantphenomics.0170
6. Singh, A. K., Balabaygloo, B. J., Bekee, B., Blair, S. W., Fey, S., Fotouhi Ardakani, F., Gupta, A., Jha, A., Martinez-Palomares, J. M., Menke, K., Prestholt, A., Tanwar, V. K., Tao, X., Vangala, A., Carroll, M. E., Das, S. K., Depaula, G., Kyveryga, P., Sarkar, S., … Valdivia, C. (2024). Smart connected farms and networked farmers to improve crop production, sustainability, and profitability. Frontiers in Agronomy, 6, 1410829. https://doi.org/10.3389/fagro.2024.1410829
7. Young, T. J., Chiranjeevi, S., Elango, D., Sarkar, S., Singh, A. K., Singh, A., Ganapathysubramanian, B., & Jubery, T. Z. (2024). Soybean canopy stress classification using 3D point cloud data. Agronomy, 14(6), 1181. https://doi.org/10.3390/agronomy14061181
Book Chapters
1. Ayanlade, T., Jones, S. E., Van der Laan, L., Chattopadhyay, S., Elango, D., Raigne, J., Saxena, A., Singh, A., Ganapathysubramanian, B., Singh, A. K., & Sarkar, S. (2024). Multi-modal AI for ultra-precision agriculture. In Harnessing Data Science for Sustainable Agriculture and Natural Resource Management, Studies in Big Data (Vol. 161, pp. 299–334). https://doi.org/10.1007/978-981-97-7762-4_13
Pre-Prints & Conference Papers
1. Arshad, M. A., Jubery, T. Z., Roy, T., Nassiri, R., Singh, A. K., Singh, A., Hegde, C., Ganapathysubramanian, B., Balu, A., Krishnamurthy, A., & Sarkar, S. (2024). AgEval: A benchmark for zero-shot and few-shot plant stress phenotyping with multimodal LLMs. arXiv. https://arxiv.org/abs/2407.19617
2. Feng, J., Blair, S. W., Ayanlade, T., Balu, A., Ganapathysubramanian, B., Singh, A., Sarkar, S., & Singh, A. K. (2024). Robust soybean seed yield estimation using high-throughput ground robot videos. arXiv. https://arxiv.org/abs/2412.02642
3. Jones, S. E., Ayanlade, T., Fallen, B., Jubery, T. Z., Singh, A., Ganapathysubramanian, B., Sarkar, S., & Singh, A. K. (2024). Multi-sensor and multi-temporal high-throughput phenotyping for monitoring and early detection of water-limiting stress in soybean. arXiv. https://arxiv.org/abs/2402.18751
4. Khosravi, M., Carroll, M. E., Tan, K. L., Van der Laan, L., Raigne, J., Mueller, D. S., Singh, A., Balu, A., Ganapathysubramanian, B., Singh, A. K., & Sarkar, S. (2024). AgGym: An agricultural biotic stress simulation environment for ultra-precision management planning. arXiv. https://arxiv.org/abs/2409.00735
5. Kim, B., Blair, S. W., Jubery, T. Z., Sarkar, S., Singh, A., Singh, A. K., & Ganapathysubramanian, B. (2024). Soybean maturity prediction using 2D contour plots from drone-based time series imagery. arXiv. https://arxiv.org/abs/2412.09696
6. Saleem, N., Balu, A., Jubery, T. Z., Singh, A., Singh, A. K., Sarkar, S., & Ganapathysubramanian, B. (2024). Class-specific data augmentation for plant stress classification. arXiv. https://arxiv.org/abs/2406.13081
7. Van der Laan, L., Elango, D., Ferela, A., O'Rourke, J. A., & Singh, A. K. (2024). High temperature and microbiome conditions affect gene expression in soybean. bioRxiv. https://doi.org/10.1101/2024.11.04.620947
8. Van der Laan, L., Parmley, K. A., Saadati, M., Torres Pacin, H., Panthulugiri, S., Sarkar, S., Ganapathysubramanian, B., Lorenz, A. J., & Singh, A. K. (2024). Genomic and phenomic prediction for soybean seed yield, protein, and oil. bioRxiv. https://doi.org/10.1101/2024.11.01.621550
9. Van der Laan, L., Peixoto, L. D. A., & Singh, A. K. (2024). Genetic dissection of heat stress tolerance in soybean through genome-wide association studies and the use of genomic prediction to enhance breeding applications. bioRxiv. https://doi.org/10.1101/2024.04.27.591454
10. Yang, C. H., Feuer, B., Jubery, T. Z., Deng, Z. K., Nakkab, A., Hasan, M. Z., Chiranjeevi, S., Marshall, K. O., Baishnab, N., Singh, A. K., Singh, A., Sarkar, S., Merchant, N., Hegde, C., & Ganapathysubramanian, B. (2024). Arboretum: A large multimodal dataset enabling AI for biodiversity. arXiv. https://arxiv.org/abs/2406.17720
Magazine Article
1. Ganapathysubramanian, B., Bell, J. M. P., Kantor, G. A., Merchant, N., Sarkar, S., Schnable, P. S., Segovia, M. S., Singh, A., & Singh, A. K. (2024). AIIRA: AI Institute for Resilient Agriculture. AI Magazine, 45(1), 94–98. https://doi.org/10.1002/aaai.12151

RESEARCH PROJECT REPORT
Soybean [Glycine max L. (Merr.)] is grown globally and is an important source of food, fuel, and commercial products. Efforts in soybean improvement have long focused on developing highly productive cultivars with high yield potentials. Less focus has been placed on developing soybean cultivars with improved seed composition, or improved stress tolerance. As omics methods have evolved, many new approaches are being developed which allow breeders to apply new tools as part of the breeding process and to better understand the genetic architecture for established and novel traits of interest.
Research on Seed oil and Protein (Liza Van der Laan; Ph.D. project; partially supported by Iowa Soybean Association and Plant Sciences Institute): Soybean seed protein and oil are important traits due to the use of soybean as a primary source of food and fuel around the world. Because of the importance of seed yield and composition traits in soybean, in-season prediction of experimental accessions has potential uses in breeding programs by allowing for earlier selections and more rapid cycling of breeding material. We explored the use of genomic and phenomic prediction models for soybean seed yield, protein, and oil, and compared the predictive abilities between the two models on 292 soybean accessions. We show that phenomic prediction can outperform genomic prediction for seed yield, but not for the seed composition traits. These different models give breeders flexibility for what types of data should be collected and used in prediction models. It gives options for soybean breeders to select which tool is most feasible for their unique budgets and constraints, allowing for maximization of their prediction resources.
Research on Heat stress (Liza Van der Laan; Ph.D. project; partially supported by Iowa Soybean Association and Iowa Soybean Research Center, and Plant Sciences Institute): Heat stress is increasingly becoming a limiting stress factor in plant species as global temperatures continue to rise. Soybean response to heat stress has been minimally studied, and an understanding of how soybean responds to heat stress is necessary for breeding heat stress tolerance. The genetic control of heat stress tolerance in soybean is particularly understudied, and an understanding of these genetic mechanisms underpinning heat stress responses can aid in accelerating the development of accessions with heat stress tolerance. By taking advantage of a soybean diversity panel with 450 accessions and GWAS methodologies, we characterized how different soybean traits were affected by heat stress, as well as the genetic control of these responses. Different markers were detected between optimal and heat stress growing conditions, which indicates a genetic divergence in soybean response to temperature. One marker was significant for an index of soybean response to heat, with putative candidate genes include laccase proteins and a NAC transcription factor. Genomic prediction was found to perform moderately for prediction of soybean biomass traits in heat stress, and this should be further expanded for testing yield predictions in stress conditions. Additionally, heat tolerant accessions were identified to be used as parents in the breeding program, allowing for development of more heat tolerant cultivars to be available to farmers.
Along with studying the genomics of soybean heat stress, we also used transcriptomics to further investigate the genetic response of soybean to heat stress. This was additionally paired with studying the effect that the soil microbiome has on the response to heat stress. Recent studies indicate that the soil microbiome may play a role in how plants respond to stress, and the microbiome may help mitigate the effects of the stress. Using transcriptomic tools to study the effect of heat stress and a soil microbiome, we provided insights into how genes are regulated by these different factors. Different genes were expressed under heat stress due to changes in the soil microbiome, indicating that the microbiome does play a role in how soybean responds to stress. Of the differentially expressed genes, photosynthetic and heat shock protein (HSP) genes were especially affected by heat stress. We identified a gene encoding for a heat shock factor (HSF) that seems to play a role in regulating the response to heat stress, regardless of soil microbiome and indicate this as a gene for further study. This gene should be further investigated and validated and could serve as a promising marker for developing heat tolerant soybeans via traditional tools or genome editing.

Research on soybean drought tolerance (Sarah Jones; Ph.D. project; partially supported by Iowa Soybean Association and United Soybean Board, and Plant Sciences Institute):
Drought stress can be a significant yield-limiting factor in soybean production, necessitating improved drought-tolerant genetics in soybean to protect yield and promote resiliency under stress and underscoring the need for advancements in stress monitoring for crop breeding and production. A diverse panel of 450 maturity group 0 - III soybean PI accessions and checks were screened in a non-irrigated drought nursery for three years in 2020 - 2022 in Muscatine, Iowa. Select lines were also screened in a near-field abiotic stress tolerance system for more controlled drought testing in 2023 in Ames, Iowa. And two recombinant inbred lines populations were developed for joint flood and drought tolerance and were also screened in multi-state trials in Kansas and North Carolina. Visual and sensor-based measurements were collected via RGB, hyperspectral, and multispectral sensors via ground and UAV based platforms. This project combines multi-modal information to identify the most effective and efficient automated methods to study drought response and developed a machine learning based pipeline for rapid classification of soybean drought stress symptoms and pre-visual early detection of drought stress. During germplasm screening, a wide range of phenotypic diversity was observed and slow canopy wilting accessions were identified for introduction into upper Midwest breeding programs. Using more controlled field-based screening, differential patterns of recovery were observed using hyperspectral reflectance. Finally, five genomic regions were identified by at least two methods of GWAS. Three quantitative trait loci (QTL) identified in QTL mapping of the two recombinant inbred line populations were also identified in GWAS. These regions identified across analyses, backgrounds, and environments could hold potential candidate genes for further exploration.

The use of drones and ground robots with sensors in a breeding program (Sam Blair; M.S. project; partially supported by Iowa Soybean Association and Plant Sciences Institute):
In a soybean breeding program, seed yield and days to maturity are very important traits. The need to test thousands and potentially tens of thousands of plots makes the data collection process for both of these tasks time-consuming and labor-intensive. The goal for each of these projects was to make an automated relative maturity rating and seed yield estimate system using an unpiloted aerial system (UAS) or ground robot system, respectively, along with machine learning (ML).
Soybean breeding programs, in the early stages of the breeding pipeline, assign relative maturity ratings to experimental varieties that indicate their suitable maturity zones. The goal for our relative maturity rating system was to introduce a tool that can be utilized by soybean breeders to save time normally dedicated to maturity note-taking. Current methods for taking maturity notes require human raters to go out to the fields and take notes on every plot in the fields multiple times a week for several weeks. For a field with 10,000 plots, this can take up to 228 labor hours. Our research introduces a method for using UAS to capture time series imagery, which is then used to train an ML model to make relative maturity classifications automatically, drastically reducing the time and labor needed for note-taking. Data collected for this project consists of 22,043 plots imaged from 2021-2023 from six fields. We utilize 2-dimensional contour plots extracted from the imagery to train our ML model. This model then classifies plots into either four, five, or seven distinct maturity groups with up to 85% accuracy. The use of this system has shown a 95% decrease in time needed for note taking allowing for the reallocation of labor resources to other tasks.
Yield data is likely the most critical data to collect for a soybean breeder to make decisions on which soybean lines to continue for further testing and cultivar release. In order to get an accurate assessment of a new soybean line’s yield, it must be tested in multiple locations. Current methods of collecting this data require plot harvesters to be deployed to these outside locations requiring specialized transportation equipment and licensing. In this project, we introduce a method for estimating yield data based on side-view ground robot videos of mature soybean plants. Operating small ground robots requires less training and is safer than traditional harvesting equipment. Break down costs are also far cheaper on small robots and they are much easier to transport. In this project, we deployed the Terrasentia robot equipped with fisheye lens cameras mounted to either side of the robot to capture comprehensive video of the entire plant from bottom to top. We then used imagery extracted from the video to train our P2PNet-Yield model. This model utilizes the Feature Extraction Module from P2PNet-Soy to detect individual soybean seeds and make yield estimates in tons/hectare. Our data consists of video taken at all times of day from a wide variety of genotypes representing different pubescence and seed coat colors. We report a genotype yield ranking accuracy of up to 83%. This project introduces a new tool for breeders to use to make yield data collection easier and more efficient.
We continued our partnership with the Iowa Soybean Association with funded projects, AIIRA, COALESCE, and SIRAC, that USDA and NSF supported. These unique linkages provide farmer-motivated solutions that enhance breeding and crop production using machine learning and robotics. These also leverage ISA support with other agency support enabling research.

Two new varieties were disclosed to ISURF: IAS27C1 and IAS27HPHO1. Foundation seed increase was completed.
Seven journal research or review papers, one book chapter, one magazine article, and ten conference or pre-prints were published. Project objectives were successfully completed, including planting, data collection, plant selections, harvest, variety selection and data analysis.
Research advances were made in biotic and abiotic stress tolerance traits, with applications in variety development.

The technology developed from this project, including varieties, germplasm, phenomic tools, phenotyping and screening methods will help the IA farmers, private and public breeders, and research community looking for outputs on increased yield, protection traits, and seed quality. Varieties developed for this project are dual purpose: generic and food grade therefore create and cater to a premium paying market. ISU varieties provide a seed cost advantage due to their lower price, and yield competitive with commercial varieties. The ISU lines do not have a traited herbicide gene, therefore can be used by small or large seed companies to integrate any herbicide trait for a more competitive market. Our varieties have been actively taken up by Iowa and mid-western seed companies through MTAs. The training of high caliber workforce to work as breeders and scientist in seed, chemical and agricultural companies is immeasurable but highly valued. ISA funding is also bringing in federal investments through research funding agencies, including new partnership projects between our team and ISA, which benefits ISA and ISU to advance farmer interests and profitability.