Source: WASHINGTON STATE UNIVERSITY submitted to
GENOMICS-ENABLED SATELLITE PHENOMICS FOR WHEAT BREEDING IN THE PALOUSE
Sponsoring Institution
National Institute of Food and Agriculture
Project Status
COMPLETE
Funding Source
AFRI COMPETITIVE GRANT
Reporting Frequency
Annual
Accession No.
1018562
Grant No.
2019-67013-29171
Cumulative Award Amt.
$500,000.00
Proposal No.
2018-06261
Multistate No.
(N/A)
Project Start Date
Feb 15, 2019
Project End Date
Feb 14, 2023
Grant Year
2019
Program Code
[A1141]- Plant Health and Production and Plant Products: Plant Breeding for Agricultural Production
Project Director
Zhang, Z.
Recipient Organization
WASHINGTON STATE UNIVERSITY
240 FRENCH ADMINISTRATION BLDG
PULLMAN,WA 99164-0001
Performing Department
Crop and Soil Sciences
Non Technical Summary
Phenotyping remains the major cost of wheat breeding, even with genomic selection incorporated. Variety assessments are restricted to limited locations at the maximum scale of experimental plots. Developing a high-throughput phenomics system is critically needed to comprehensively evaluate wheat varieties under real environments at the production scale. Abundantly available satellite imagery has the potential to fit this need. However, the path is currently blocked by a technical one difficulty: how to identify varieties growing in particular fields at specific times. To tackle this difficulty, we propose grow the relevant wheat varieties and image them with satellite-like spectrometers by unmanned aerial vehicles (UAVs) at experimental plots. Then we match the know varieties in experimental plots with the varieties in production fields from satellite imagery. The majority of wheat varieties adapted to the Palouse have been genotyped and phenotyped on their agronomic traits. We will use the genetic markers to supervise the alignment of varieties on UAV and satellite imagery. The alignment will be validated by the seed production fields which have enough satellite pixels. The existing agronomic trait phenotypes on the experimental plots will aid in identifying the heritable satellite imagery features. All data together will be used to predict agronomic traits for particular varieties at particular fields to evaluate the main effects of varieties, the main effects of fields, and variety-field interactions. Because the Palouse is a region with extensive variation in precipitation levels and landscape forms, this project's methods and results should be transferable to other crops and regions.
Animal Health Component
20%
Research Effort Categories
Basic
70%
Applied
20%
Developmental
10%
Classification

Knowledge Area (KA)Subject of Investigation (SOI)Field of Science (FOS)Percent
20115491081100%
Knowledge Area
201 - Plant Genome, Genetics, and Genetic Mechanisms;

Subject Of Investigation
1549 - Wheat, general/other;

Field Of Science
1081 - Breeding;
Goals / Objectives
Our overall goal is to boost wheat production by improving breeding efficiency. To achieve our overall goal, we propose the following specific objectives:Objective 1: Automatic identification of wheat varieties grown in the Palouse.A previous study estimated (see preliminary results) that the southern Palouse area is divided into 13,505 fields, with boundaries delineated by factors such as land ownership, crop rotation, or farming operation. According to the WGC, over 100 winter and spring wheat varieties have been recommended to growers. These varieties encompass almost every wheat market class, including soft white winter, soft white spring, hard white winter, hard white spring, hard red winter, hard red spring, and durum. Unfortunately, knowing which variety is growing in each field at any given time is practically impossible. Manually collecting such information not only demands intensive coordination, but is also subject to human error. Thus, a method to automatically identify the wheat variety growing in each field at a specific moment in time is critically needed. Direct benefits would include the ability to assess the distribution and amount of area planted to a specific variety and to determine which varieties were chosen for particular fields. Over the long-term, indirect benefits would include variety performance evaluations in real production environments for enhancing wheat breeding efficiency.Objective 2: Identify imagery features that explain agronomic traits.Satellite imagery is available for wheat varieties grown in production fields where agronomic trait data are unavailable or traits are difficult to measure at the production scale. UAVs can collect imagery, at a resolution similar to satellites, on experimental plots that are growing varieties with known agronomic traits. If these known agronomic traits can be accurately represented by the features contained in the imagery, then predicting agronomic traits on varieties grown in production fields using satellite imagery is possible. The sensing imagery from either UAVs or satellites measures the interaction between electromagnetic radiation and matter. Electromagnetic radiation that is emitted, absorbed, or scattered by materials can be measured to identify, and quantify those materials. Visible light is just a small fraction of the entire electromagnetic spectrum that is formed by a stream of photons, each traveling in a wave-like pattern, carrying energy, and moving at the speed of light. The spectrum is arranged according to energy level, from radio waves (lowest energies) to infrared, followed by visible, ultraviolet, X-rays, and then gamma rays (highest energies). The bands relevant to plant the most in satellite and UAV are Red, Blue, Green, Red-Edge, and NIR, which are the most plants.Objective 3: Predict agronomic traits for particular varieties in particular production fields.The performance of an agronomic trait is the sum of the average field effect, average variety effect, and variety-field interaction. Average field effect is of particular interest to farmers. Average variety effect and variety-field interaction are of interest to farmers, seed producers, and breeders. Farmers can maximize their total income by choosing the variety that will perform the best in a particular field.Objective 4: Identify genetic loci associated with predicted agronomic traitsAlthough a strong correlation is desired between observed and predicted agronomic traits from imagery features, the correlation coefficient will rarely reach 100%. In such cases, gene mapping on predicted phenotypes may identify genetic loci not previously identified by using the observed agronomic traits. In the situation where agronomic trait measurements are unavailable for production fields, the predicted agronomic traits are of particular interest. These predicted traits may provide valuable candidates that can help narrow down possible targets of causal genes to map the remaining genes.The relationship between project objectives and program area prioritiesOur overall goal to boost wheat production by improving breeding efficiency supports the program area priority "Plant Breeding for Agricultural Production" (Code-A1141). Successfully accomplishing our three objectives will help wheat breeders achieve increased efficiency by providing them innovative tools to evaluate and/or predict variety performance at the scale of production fields. In turn, breeders can select for high-yielding, high-quality cultivars that perform well under specific field conditions, which can be highly variable across complex landscapes with a diversity of soil, topography, and climate. In practice, farmers will be able to choose a wheat variety that is more likely to perform the best in a particular field, boosting their efficiency, production, and income. Among the five priority topics listed for this program area priority, our project particularly involves "applied quantitative genetics and phenomics". The project also involves both conventional/classical and genomics-enabled plant breeding, which are also supported under this priority area. The success of the proposed project will not only integrate production field data into the breeding process, but will also strengthen the connection between breeding and real production-scale performance. Breeders will be able to expand and accelerate their opportunities to improve cultivars by assessing both average variety performance and specific performance at particular production field locations (please see letter of support from Washington State Crop Improvement Association).
Project Methods
Experimental designSatellite imagery over the Palouse area has already been collected and will continue to be collected by PD Zhang. Over the three years of the project, 300 winter wheat varieties (by COPD Carter) and 300 spring wheat varieties (by COPD Pumphrey) will be grown over two summers in two locations (Pullman and Lind, WA). Each location will have three replicates per variety. Each replicate plot will measure 1.5 meter in width by 6 meters in length with an estimated 200 plants perm2, surrounded by a 0.5-meter margin. During the summer growing season (20 weeks), UAV imagery will be collected bi-weekly by COPD Sankaran at a resolution of 2 cm/pixel. The existing agronomic trait phenotypes and genotypes and the collected satellite and UAV imagery will be analyzed by PD Zhang. Analyses will include identifying wheat varieties growing in each field during each of the 2 years, detecting QTL controlling heritable satellite imagery features, and predicting agronomic traits from the heritable satellite imagery features.Method 1: Satellite imageryWe have collected and will continue to collect satellite imagery on the Palouse area, specifically defined by the triangle area with boundaries of Rock Creek Area on the left, Saint Joe National Forest on the right, and Snake River and Clearwater River at the bottom. We have access to satellite imagery data on the Palouse from two sources, Landsat and Planet. Landsat provides free access for the public. Since the early 1970s, the National Aeronautics and Space Administration (NASA) and the US Geological Survey (USGS) have jointly managed the Landsat Project to collect and provide image data to support earth observation research among various fields and industries worldwide. The Landsat data became freely available in 2009. All Landsat data archived by the USGS is publicly accessible through the USGS Earth Explorer website (https://earthexplorer.usgs.gov/) and reaches back to 1972. The long operation time and global coverage make Landsat a good data resource for worldwide land cover research. The Landsat 7 and Landsat 8 data contain multi-spectral bands in the visible and NIR range with a spatial resolution of 30 meters, which is particularly useful for vegetation monitoring.Method 2: Grow Palouse-related wheat varieties on experimental plotsEach year, about 100 wheat varieties are available for commercial production in the three states (Washington, Idaho, and Oregon). These varieties cover multiple market classes, including the majority class of soft white winter. The number of spring varieties are similar among the top three classes: hard red, hard white, and soft white. Over the last three years, 153 unique varieties were commercially available. Although a large number of varieties are commercially available, only about 30 varieties comprise about 85% of the commercially planted acreage in the three states.In addition to the 164 varieties planted or available, we will add 195 winter varieties and 252 spring varieties to form a 600-wheat variety panel. The added varieties will include the varieties planted between 2000 and 2015, plus the current breeding lines in the respective breeding programs. The 600-variety panel will contain 300 winter varieties and 300 spring varieties, focusing on soft white wheat only. Each variety will be planted on a 1.5 by 6-meter plot with three replicates at two locations in Washington (Pullman and Lind, WA) for two years.Along with collection of agronomic and spectral data, this panel will be used to help train the machine learning algorithms (described in Method 4) to identify varieties in commercially growing wheat fields. This panel is similar in size to panels we have been growing previously for associated GWAS studies for agronomic traits, biotic and abiotic stress resistance, and canopy spectral reflectance. Therefore, COPDs Carter and Pumphrey are capable of managing large trial sizes and accompanying agronomic data collection, such as plant height, heading date, and yield.Method 3: Satellite-like UAV imageryThe experimental plots will be imaged by the Double 4k multi-spectral sensor with 12M pixels. The image frame has multiple settings, including 3000 by 4000pixels. One picture will be taken at a 2cm/pixel resolution. Each plot will receive a minimum of 1,000 pixels. The sensor has five bands used by the satellites, including Red, Blue, Green, Red-Edge, and NIR bands. This setting is important to agricultural sensing because chlorophyll in the plant absorbs them differently. Chlorophyll photosynthesis absorbs mostly red and blue light while it reflects green and NIR.Method 4: 3D convolutional neural networkConvolutional neural network (CNN) is commonly used for imagery data analyses. The satellite and UAV imagery data collected from the experiment plots and production fields have at least three dimensions: spectrum, spatial, and time series.The relative change of absorption rate across the spectrum reflects the characteristics of a substance. The first-level indication is the relative difference between any two bands, followed by complex indices of three or more bands. There are n(n-1)/2 combinations of choosing two band Bi and Bj from n bands. The corresponding index is (Bi- Bj)/(Bi+Bj). One of these combinations, NIR and Red, is particular informative for vegetation. Chlorophyll in plants exhibits strong absorption of NIR, but not Red. Therefore, this index is named as Normalized Difference Vegetation Index (NDVI) for the combination of NIR and Red bands.Spatial features are the major information for facial recognition. Agricultural fields are expected to have a uniform appearance, but variations could result from either different varieties, different field conditions, or both. The spatial information includes mean, standard deviation, median, the minimum, the maximum, and different percentiles.Wheat fields go through a number of different stages during the growing season such as germination, vegetative growth, anthesis, grain filling, and drying. These processes result in unique spectral patterns over time. Unique genetic cultivars will have their own unique timing for growth stages, such as anthesis, and therefore, unique spectral responses. Although all growth curves have the uniform "S" shape, varieties will vary on features such as the range from bottom to the top, time elapsed for acceleration, and acceleration rate.Method 5: Validation through seed production fieldsWe will validate the training model with the seed production fields operated by Washington State Crop Improvement Association (WSCIA). WSCIA was established in 1946, a non- profit organization working with Washington State University,Washington State Department of Agriculture, Washington seed growers and conditioners to develop, produce and distribute certified seed in order to improve crop yields in Washington. The seed production fields not only have varieties identified, but also are big enough to gain over thousand pixels on satellite imagery with 0.8 meter resolution provided by SkySat.WSCIA has provide the historical data. We also expect to receive new data during the proposed research period (see letter of support from Certified Seed manager at WSCIA).Method 6: Gene mapping and genomic predictionAfter applying methods 1-4 to data collected on experimental plots and production fields, imagery features will be identified that explain agronomic traits collected previously in experimental plots. These features will then used to predict agronomic traits for the production fields. The identification of varieties in production fields also makes it possible to conduct GWAS to map genes underlying the predicted agronomic traits.

Progress 02/15/19 to 02/14/23

Outputs
Target Audience:The project reached stakeholders in the full range from researchers to breeders and from farmers to public audiences.? Changes/Problems:No major changes. What opportunities for training and professional development has the project provided?The project provided support for the training and professional development at both graduate and postdoc levels. These supports include their salary and travel for domestic and international conferences in the US to present their discoveries to reach stakeholders. Presentations were made at workshops and conferences. 2019 Yang Hu and Zhiwu Zhang, GridFree: A Python Package of Image Analysis for Object Counting and Measuring without Grid Restriction, International Conference of Plant and Animal Genome, January 11-15, 2020, San Diego, USA, presentation ID: C09,https://plan.core-apps.com/pag_2020/abstract/5c52d1f40a3fcfaa8a49d33b1d217ad7. Yang Hu, Chenpeng Chen, Zhou Tang, Long-Xi Yu, and Zhiwu Zhang, High Throughput Image Techniques in Breeding, International Conference of Plant and Animal Genome, January 11-15, 2020, San Diego, USA, presentation ID: W25,https://plan.core-apps.com/pag_2020/abstract/ea84b8f3-cc24-48e9-b438-31c716c780d1 Chenpeng Chen and Zhiwu Zhang, A Python Package for Aerial High-Throughput Phenotyping, International Conference of Plant and Animal Genome, January 11-15, 2020, San Diego, USA, presentation ID: C10,https://plan.core-apps.com/pag_2020/event/a7ab291d8f29eb8d2f5e5b8aa400c27f Zhou Tang and Zhiwu Zhang, Majority of Biomass Variation Explained by Drone Images One Day Prior to Harvesting, January 11-15, 2020, San Diego, USA, presentation ID: PO0077,https://plan.core-apps.com/pag_2020/abstract/5c52d1f40a3fcfaa8a49d33b1d2129b3 2020 Sankaran, S. 2020. Phenomics using advanced sensing techniques in support of crop breeding programs. Webinar on Plant-Environment Interactions and Sustainable Production Manipal School of Life Sciences (MSLS), Manipal Academy of Higher Education (MAHE), Manipal, India, 10 February, 2021. [Virtual] [Participants: 135] Sankaran, S. 2020. Sensing technologies guided phenotyping to support crop improvement programs. 2020 AgroBIT Evolution, Brazil, 10 November, 2020. [Virtual] [Participants: 3000] Sankaran, S. 2020. Advances in phenomics tools in support of crop improvement programs. Session on Sensors and Sensing for Precision Agriculture (V16H1S1), Vaishwik Bharatiya Vaigyanik Summit (VAIBHAV), New Delhi, India, 5 October 2020. [Virtual] [Participants: 627] Sankaran, S. 2020. Use of proximal and remote sensing data in crop phenotyping to support breeding programs. Online International Training on Agriculture 4.0 Precision and Automated Ag Technologies, Mahatma Phule Krishi Vidyapeeth (MPKV), Rahuri, India, 1 October, 2020. [Virtual] [Participants: 778] Sankaran, S. 2020. Sensor applications in phenomics for impact in crop improvement programs. Online International Training on Present and Futuristic Trends in Agricultural Mechanization, Center of Excellence for Digital Farming Solutions for Enhancing Productivity by Robots, Drones and AGVs. Vasantrao Naik Marathwada Krishi Vidyapeeth, Parbhani, India, 23 June, 2020. [Webinar] [Participants: 192] Andrew Herr and Arron Carter. 2020. Multispectral imaging in winter wheat variety improvement. Poster Presentation at the 2020 ASA-CSSA-SSSA Annual Meeting, Virtual. Andrew Herr and Arron Carter. 2020. Multispectral imaging in winter wheat variety improvement. Poster Presentation at the 2020 National Association of Plant Breeders annual meeting, Virtual. 2021 James Chen, A paradigm shift in breeding: from genomics to phenomics. Department seminar for Crop and Soil Sciences at Washington State University, April 12, 2021, Pullman, Washington (https://css.wsu.edu/spring-2021-virtual-seminars). Matthew McGowan, Matthew McGowan, Into the 3rd dimension: Integrating chromatin structure into multi-omic analysis. Molecular Plant Science at Washington State University, Dec 8, 2021 (https://mps.wsu.edu/seminar-series-2). Molecular Plant Science at Washington State University, April 28, 2021 (https://s3.wp.wsu.edu/uploads/sites/170/2021/07/Spring-2021-seminar-schedule.pdf). Matthew McGowan, Into the 3rd dimension: Integrating chromatin structure into multi-omic analysis. Molecular Plant Science at Washington State University, Dec 8, 2021 (https://mps.wsu.edu/seminar-series-2). Sankaran, S. 2021. Crops for Future: Role of sensing technologies to promote sustainable crop production. 2021 University of Guelph Corteva Agricultural Science Symposium on 'Moving Towards Sustainable Agriculture: Leveraging Scientific Innovations to Improve Current Farming Systems', Ontario, Canada, 19 November 2021 Sankaran, S. 2021. Phenomics techniques and machine learning approaches to support crop breeding programs at Washington State University. Heilongjiang Academy of Agricultural Sciences, Nangang, Harbin, Heilongjiang, China, 11 October 2021. Sankaran, S. 2020. Sensing technologies guided phenotyping to support crop improvement programs. 2020 AgroBIT Evolution, Brazil, 10 November, 2020. Marzougui, A., McGee, R.J., Van Vleet, S., and Sankaran, S. 2021. Improved field-phenomics protocol for selecting superior pea breeding lines using UAV and satellite-based remote sensing. Paper No. 2100469, 2021 ASABE AIM (Virtual), 12-16 July 2021. Sangjan, W., Carpenter-Boggs, L., Hudson, T.D., and Sankaran, S. 2021. Pasture productivity assessment under mob grazing and fertility management using remote sensing techniques. Paper No. 2100695, 2021 ASABE AIM (Virtual), 12-16 July 2021. Herr, Andrew; Carter, Arron "Drought Tolerance Prediction with UAS Imagery" ASA-CSSA-SSSA International Annual Meeting, November 2021 Herr, Andrew; Carter, Arron "Multispectral Imaging in Winter Wheat Variety Improvement" National Association of Plant Breeders Annual Meeting, August 2021 Herr, Andrew; Carter, Arron "Towards Increased Genetic Gain: Utilizing Spectral Data in a Large Scale Wheat Breeding Program under a Drought Year" North American Plant Phenotyping Network Annual Meeting, February 2022 2022 Andrew Herr, Lance Merrick, Arron Carter (2022) Towards increased genetic gain: utilizing spectral data in wheat to improve prediction performance under a drought year. 7th International Plant Phenotyping Symposium, Wageningen, Netherlands Marzougui, A., McGee, R.J., Van Vleet, S., and Sankaran, S. 2022. Multi-scale image and feature field pea dataset fusion for remote sensing applications in phenomics. S18: III International Symposium on Mechanization, Precision Horticulture, and Robotics: Precision and Digital Horticulture in Field Environments, 2022 International Horticultural Congress, Angers, France, 17-19 August 2022. Sangjan, W., Carter, A.H., Pumphrey, M.O., Jitkov, V., and Sankaran, S. 2022. Effect of plot pixel resolution on crop performance assessment using features extracted from UAV and high?resolution satellite imagery. Paper No. 2201235, 2022 ASABE AIM, Houston, TX, 18-20 July 2022. Marzougui, A., McGee, R.J., Van Vleet, S., and Sankaran, S. 2022. Field?based phenomics using UAS and high-resolution satellite imagery to support pea cultivar selection, Paper No. 2201173, 2022 ASABE AIM, Houston, TX, 18-20 July 2022. Sankaran, S., Sangjan, W., Pumphrey, M. O., Carter, A. H., Jitkov, V., and Hagemeyer, K.E. 2022. Multi-scale multispectral imaging for crop phenotyping applications. 2022 The Asian Federation for Information Technology in Agriculture (AFITA)/ The World Congress on Computer in Agriculture (WCCA), Hanoi, Vietnam, 24-26 November 2022 [Keynote Speaker] Sankaran, S. 2022. Capturing crop agronomic traits across different spatial and temporal scales. Joint WSU-Germany's Cluster of Excellence on Plant Sciences (CEPLAS) Seminar Series on Complex Plant Traits, 12 July 2022. Sankaran, S. 2022. Concepts related to sensing and associated technologies applicable to small hold farmers [Presentation and Panel Discussion], Innovative Technologies for Small-Scale Farmers, Fruit and Vegetable Small-Scale Farming Webinar Series, Organized by Food and Agriculture Organization (FAO) of the United Nations and International Society for Horticultural Science (ISHS), 21 June 2022. How have the results been disseminated to communities of interest?The research results have been disseminated through multiple platforms, including publication, extension articles, project website, and conferences. 2019 Zhiwu, Zhang, Party game ignites satellite, drone research effort, Wheat Life, October, 2019, P50-51(https://wheatlife.org/wp-content/uploads/2022/03/09_WLOct19web.pdf) Zhiwu, Zhang, Watch for stripe rust with smartphones, Wheat Life, February, 2022, P51,https://wheatlife.org/wp-content/uploads/2022/03/02_WL_Feb22web.pdf Seth Truscott, Images from space could help farmers grow better wheat varieties, WSU Insider, May 29, 2019,https://news.wsu.edu/news/2019/05/29/images-space-help-farmers-grow-better-wheat-varieties. 2020 Zhang, C., Marzougui, A., and Sankaran, S. 2020. High-resolution satellite imagery applications in crop phenotyping: An overview. Computers and Electronics in Agriculture, 175, 105584.https://doi.org/10.1016/j.compag.2020.105584 James Chen andZhiwu Zhang.GRID: A Python Package for Field Plot Phenotyping Using Aerial Images.Remote Sensing, 2020,https://www.mdpi.com/2072-4292/12/11/1697. Wei Huang, Ping Zheng, Zhenhai Cui, Zhuo Li, Yifeng Gao, Helong Yu, You Tang, Xiaohui Yuan, andZhiwu Zhang*.MMAP: A Cloud Computing Platform for Mining the Maximum Accuracy of Predicting Phenotypes from Genotypes.Bioinformatics, 2020.https://doi.org/10.1093/bioinformatics/btaa824 Lu Liu, Meinan Wang,Zhiwu Zhang, Deven R See, Xianming Chen.Identification of Stripe Rust Resistance Loci in US Spring Wheat Cultivars and Breeding Lines Using Genome-wide Association Mapping and Yr Gene Markers.Plant Disease, 2020,https://doi.org/10.1094/PDIS-11-19-2402-RE. 2021 Yang Hu, andZhiwu Zhang*,GridFree: a python package of imageanalysis for interactive grain counting and measuring.Plant Physiology, 2021,https://doi.org/10.1093/plphys/kiab226 2. Zhou Tang, Atit Parajuli, Chunpeng James Chen, Yang Hu, Samuel Revolinski, Cesar Augusto Medina, Sen Lin,Zhiwu Zhang*.Validation of UAV-based alfalfa biomass predictability using photogrammetry with fully automatic plot segmentation.Scientific Reports, 2021,doi: 10.1038/s41598-021-82797-x. Jiabo Wang* andZhiwu Zhang*,GAPIT Version 3: Boosting Power and Accuracy for Genomic Association and Prediction.Genomics, Proteomics and Bioinformatics, 2021,https://doi.org/10.1016/j.gpb.2021.08.005 Matthew T. McGowan,Zhiwu Zhang& Stephen P. Ficklin,Chromosomal characteristics of salt stress heritable gene expression in the rice genome. BMCGenomic Data, 2021,https://doi.org/10.1186/s12863-021-00970-7. Sankaran, S., Marzougui, A., Hurst, J. P., Zhang, C., Schnable, J. C., & Shi, Y. (2021). Can High-Resolution Satellite Multispectral Imagery Be Used to Phenotype Canopy Traits and Yield Potential in Field Conditions? Transactions of the ASABE, 64(3), 879-891.https://elibrary.asabe.org/abstract.asp?aid=52185 Matthew McGowan, Jiabo Wang, Haixiao Dong, Xiaolei Liu, Yi Jia, Xianfeng Wang, Hiroyoshi Iwata, Yutao Li, Alexander E Lipka, andZhiwu Zhang*.Ideas in Genomic Selection with the Potential to Transform Plant Molecular Breeding: A Review.Plant Breeding Review Vol 45(eds. Irwin Goldman), John Wiley & Sons, Inc. 2021. pp. 273-320,https://doi.org/10.1002/9781119828235.ch7, also available asPreprint,Publication, andGoogle Book. 2022 Zhou Tang, Yang Hu, and Zhiwu Zhang*, ROOSTER: An image labeler and classifier through interactive recurrent annotation. F1000Researchy, 2023,https://doi.org/10.12688/f1000research.127953.1 Chunpeng Chen,Jessica Rutkoski ,James Schnable ,Seth Murray ,Lizhi Wang ,Xiuliang Jin, Benjamin Stich ,Jose Crossa ,Ben Hayes,andZhiwu Zhang*.Role of the Genomics-Phenomics-Agronomy Paradigm in Plant Breeding.Plant Breeding Review Vol 46(eds. Irwin Goldman), John Wiley & Sons, Inc. 2022.https://doi.org/10.1002/9781119874157.ch10. Also available atPreprintandPublication. Jiabo Wang, Jianming yu, Alex Lipka, andZhiwu Zhang*.Interpretation of Manhattan Plots and Other Outputs of Genome-Wide Association Studies.Genome Wise Association StudiesMethods in Molecular Biology, vol 2481, 2022. Humana, New York, NY.https://doi.org/10.1007/978-1-0716-2237-7_5 Jiabo Wang, You Tan, andZhiwu Zhang*.Performing Genome-Wide Association Studies with Multiple Models Using GAPIT.In: Torkamaneh, D., Belzile, F. (eds) Genome-Wide Association Studies. Methods in Molecular Biology, vol 2481, 2022. Humana, New York, NY.https://doi.org/10.1007/978-1-0716-2237-7_13 5. Zhou Tang, Meinan Wang, Michael Schirrmann, Karl-Heinz Dammer, Xianran Li, Robert Brueggeman, Sindhuja Sankaran, Arron Carter, Michael Pumphrey, Yang Hu, Xianming Chen, Zhiwu Zhang, Affordable High Throughput Field Detection of Wheat Stripe Rust Using Deep Learning with Semi-Automated Image Labeling, Computers and Electronics in Agriculture, 2023 (Accepted for publication) 6. Andrew W. Herr, Alper Adak, Matthew E. Carroll, Dinakaran Elango, Soumyashree Kar, Changying Li, Sarah E. Jones, Arron H. Carter, Seth C. Murray, Andrew Paterson, Sindhuja Sankaran, Arti Singh, Asheesh K. Singh. UAS imagery for phenotyping in cotton, maize, soybean, and wheat breeding. Crop Science, 2023 (under review) 7. Osval A. Montesinos-López, Andrew W. Herr, José Crossa, Arron H. Carter. Genomics combines with UAS data enhances prediction of grain yield in winter wheat. Frontiers in Genetics, 2023 (under review) What do you plan to do during the next reporting period to accomplish the goals?This is the final report.

Impacts
What was accomplished under these goals? The overall goal of this project is to boost wheat production by improving breeding efficiency. The specific objectives are 1) variety identification on satellite images; 2) identification of image features related to agronomy traits; 3) genomic selection, and 4) genome-wide association studies. Year 4 focused on software development, algorithm development, data analyses and publications, training for graduate and postdocs, and outreach stakeholders. An interactive recurrent annotation method was developed to semi-automatically create training images for artificial intelligence (AI). One article was published for the method, and one article was accepted for publication to demonstrate the applications. To help the research community, with most of the researchers without AI expertise, we developed software (AI4Everyone) to allow users to build AI systems by clicking and dragging graphic components without programming. The software is freely available to the public (https://zzlab.net/AI4EVER). In year 4, two more manuscripts were submitted and currently, the are under peer review. Seven presentations were made at workshops and conferences domestically and internationally. One extension article was published by Wheat Life to reach broader stakeholders. We obtained satellite images of five years on Palouse wheat production area, collected drone images of two years on variety test program experimental fields, developed three software packages for image analyses, update one existing software package for genomic selection and genome wide association studies. We published 15 peer review articles, submitted two manuscripts which are currently under peer review. We published two extension articles, made 29 presentation at domestic and international conferences. By February 14, 2023, our peer reviewed articles have received 288 citations by the researchers in the scientific community. The most cited article is on the update of our existing software (GAPIT, Wang et al., 2021, https://doi.org/10.1016/j.gpb.2021.08.005) to conduct gene mapping and genomic prediction on complex traits such as the conventional agronomy traits and digital traits collected by satellite and drones. The second most cited article is a review article on high-resolution satellite imagery applications in crop phenotyping (Zhang et al., 2020, https://doi.org/10.1016/j.compag.2020.105584). The article has received 50 citations. We released a software with graphic user interface to help breeders to conduct plot segmentation on their field images. The software is named GRID and is freely available for public (https://zzlab.net/GRID). Multiple plot patterns are acceptable by the software, including the zig-zag plot design commonly used in wheat research. The article on GRID software has received 14 citations (https://www.mdpi.com/2072-4292/12/11/1697). We published two extension articles for farmers to use new technologies such as drones. One article introduces the impact of imaging technology in plant breeding. The article was published by Wheat Life in October, 2019, P50-51 (https://wheatlife.org/wp-content/uploads/2022/03/09_WLOct19web.pdf). The other article introduces the technology to detect wheat stripe rust using computer vision. The article was published by Wheat Life in February, 2022, P51 (https://wheatlife.org/wp-content/uploads/2022/03/02_WL_Feb22web.pdf). Farmers can process their images with our free software, ROOSTER (https://zzlab.net/ROOSTER). The technical details of ROOSTER is available in format of preprint (https://www.preprints.org/manuscript/202204.0177/v1). The article is recently reviewed and accepted by Computers and Electronics in Agriculture. Our impact is beyond wheat originally designed for the project. Our method and software of automatic segmentation of experimental plots have been used in other crops, including alfalfa. We demonstrated that alfalfa biomass can be predicted by the vegetation area segmented by our GRID software (doi: 10.1038/s41598-021-82797-x) on drone images. This opens a path of conducting high throughput phenotyping on biomass, which is labor intensive. We outreached broader public audience with artificial intelligence technologies developed by the project. Deep learning, a branch of artificial intelligence using neural networks with multi-layered representations of data, has improved the state-of-the- art in various machine learning tasks such as image classification and object detection. Many of the achievements have been reached by experts with advanced programming skills, including using popular deep learning frameworks such as TensorFlow and PyTorch. All applications use individual solutions that are highly specialized for particular tasks. The development of a deep learning system has proven challenging. There is a lack of easy-to-use, adaptable, and open-source software to end users without computational expertise. We developed AI4EVER, which enables prediction-assisted image labeling, training models, applying trained or pre-trained models on new data, and obtaining performance matrices through a graphical user interface (GUI). The package uses deep learning as its backend, provides GPU support, export final models to different formats, and generate command line transcript. AI4EVER is compatible with 20 pre-defined architectures and equipped with utility for developers to create new architectures. Hence, nonexperts can easily perform deep learning for tasks such as image segmentation and object classification. The details of the platform design and implementation are accompanied by the two use cases conducted by field-specific experts without programming. AI4EVER is freely available on the AI4EVER website

Publications

  • Type: Journal Articles Status: Published Year Published: 2022 Citation: Zhiwu, Zhang, Watch for stripe rust with smartphones, Wheat Life, February, 2022, P51, https://wheatlife.org/wp-content/uploads/2022/03/02_WL_Feb22web.pdf
  • Type: Websites Status: Published Year Published: 2019 Citation: Seth Truscott, Images from space could help farmers grow better wheat varieties, WSU Insider, May 29, 2019, https://news.wsu.edu/news/2019/05/29/images-space-help-farmers-grow-better-wheat-varieties.
  • Type: Journal Articles Status: Published Year Published: 2020 Citation: James Chen and Zhiwu Zhang. GRID: A Python Package for Field Plot Phenotyping Using Aerial Images. Remote Sensing, 2020, https://www.mdpi.com/2072-4292/12/11/1697
  • Type: Journal Articles Status: Published Year Published: 2020 Citation: Wei Huang, Ping Zheng, Zhenhai Cui, Zhuo Li, Yifeng Gao, Helong Yu, You Tang, Xiaohui Yuan, and Zhiwu Zhang*. MMAP: A Cloud Computing Platform for Mining the Maximum Accuracy of Predicting Phenotypes from Genotypes. Bioinformatics, 2020. https://doi.org/10.1093/bioinformatics/btaa824
  • Type: Journal Articles Status: Published Year Published: 2021 Citation: Yang Hu, and Zhiwu Zhang*, GridFree: a python package of imageanalysis for interactive grain counting and measuring. Plant Physiology, 2021, https://doi.org/10.1093/plphys/kiab226
  • Type: Journal Articles Status: Published Year Published: 2020 Citation: Zhang, C., Marzougui, A., and Sankaran, S. 2020. High-resolution satellite imagery applications in crop phenotyping: An overview. Computers and Electronics in Agriculture, 175, 105584. https://doi.org/10.1016/j.compag.2020.105584
  • Type: Journal Articles Status: Published Year Published: 2021 Citation: Zhou Tang, Atit Parajuli, Chunpeng James Chen, Yang Hu, Samuel Revolinski, Cesar Augusto Medina, Sen Lin, Zhiwu Zhang*. Validation of UAV-based alfalfa biomass predictability using photogrammetry with fully automatic plot segmentation. Scientific Reports, 2021, doi: 10.1038/s41598-021-82797-x.
  • Type: Journal Articles Status: Published Year Published: 2021 Citation: Jiabo Wang* and Zhiwu Zhang*, GAPIT Version 3: Boosting Power and Accuracy for Genomic Association and Prediction. Genomics, Proteomics and Bioinformatics, 2021, https://doi.org/10.1016/j.gpb.2021.08.005
  • Type: Journal Articles Status: Published Year Published: 2021 Citation: Matthew T. McGowan, Zhiwu Zhang & Stephen P. Ficklin, Chromosomal characteristics of salt stress heritable gene expression in the rice genome. BMC Genomic Data, 2021, https://doi.org/10.1186/s12863-021-00970-7.
  • Type: Journal Articles Status: Published Year Published: 2021 Citation: Sankaran, S., Marzougui, A., Hurst, J. P., Zhang, C., Schnable, J. C., & Shi, Y. (2021). Can High-Resolution Satellite Multispectral Imagery Be Used to Phenotype Canopy Traits and Yield Potential in Field Conditions? Transactions of the ASABE, 64(3), 879-891. https://elibrary.asabe.org/abstract.asp?aid=52185
  • Type: Journal Articles Status: Published Year Published: 2023 Citation: Zhou Tang, Yang Hu, and Zhiwu Zhang*, ROOSTER: An image labeler and classifier through interactive recurrent annotation. F1000Researchy, 2023, https://doi.org/10.12688/f1000research.127953.1
  • Type: Journal Articles Status: Awaiting Publication Year Published: 2023 Citation: Zhou Tang, Meinan Wang, Michael Schirrmann, Karl-Heinz Dammer, Xianran Li, Robert Brueggeman, Sindhuja Sankaran, Arron Carter, Michael Pumphrey, Yang Hu, Xianming Chen, Zhiwu Zhang, Affordable High Throughput Field Detection of Wheat Stripe Rust Using Deep Learning with Semi-Automated Image Labeling, Computers and Electronics in Agriculture, 2023 (Accepted for publication)
  • Type: Journal Articles Status: Under Review Year Published: 2023 Citation: Andrew W. Herr, Alper Adak, Matthew E. Carroll, Dinakaran Elango, Soumyashree Kar, Changying Li, Sarah E. Jones, Arron H. Carter, Seth C. Murray, Andrew Paterson, Sindhuja Sankaran, Arti Singh, Asheesh K. Singh. UAS imagery for phenotyping in cotton, maize, soybean, and wheat breeding. Crop Science, 2023
  • Type: Journal Articles Status: Under Review Year Published: 2023 Citation: Osval A. Montesinos-L�pez, Andrew W. Herr, Jos� Crossa, Arron H. Carter. Genomics combines with UAS data enhances prediciton of grain yield in winter wheat. Frontiers in Genetics, 2023
  • Type: Book Chapters Status: Published Year Published: 2022 Citation: Benjamin Stich , Jose Crossa , Ben Hayes, and Zhiwu Zhang. Role of the Genomics-Phenomics-Agronomy Paradigm in Plant Breeding. Plant Breeding Review Vol 46 (eds. Irwin Goldman), John Wiley & Sons, Inc. 2022. https://doi.org/10.1002/9781119874157.ch10.
  • Type: Book Chapters Status: Published Year Published: 2022 Citation: Jiabo Wang, Jianming yu, Alex Lipka, and Zhiwu Zhang. Interpretation of Manhattan Plots and Other Outputs of Genome-Wide Association Studies. Genome Wise Association Studies Methods in Molecular Biology, vol 2481, 2022. Humana, New York, NY. https://doi.org/10.1007/978-1-0716-2237-7_5
  • Type: Book Chapters Status: Accepted Year Published: 2022 Citation: Jiabo Wang, You Tan, and Zhiwu Zhang. Performing Genome-Wide Association Studies with Multiple Models Using GAPIT. In: Torkamaneh, D., Belzile, F. (eds) Genome-Wide Association Studies. Methods in Molecular Biology, vol 2481, 2022. Humana, New York, NY. https://doi.org/10.1007/978-1-0716-2237-7_13
  • Type: Book Chapters Status: Published Year Published: 2021 Citation: Matthew McGowan, Jiabo Wang, Haixiao Dong, Xiaolei Liu, Yi Jia, Xianfeng Wang, Hiroyoshi Iwata, Yutao Li, Alexander E Lipka, and Zhiwu Zhang*. Ideas in Genomic Selection with the Potential to Transform Plant Molecular Breeding: A Review. Plant Breeding Review Vol 45 (eds. Irwin Goldman), John Wiley & Sons, Inc. 2021. pp. 273-320, https://doi.org/10.1002/9781119828235.ch7,
  • Type: Journal Articles Status: Published Year Published: 2020 Citation: Lu Liu, Meinan Wang, Zhiwu Zhang, Deven R See, Xianming Chen. Identification of Stripe Rust Resistance Loci in US Spring Wheat Cultivars and Breeding Lines Using Genome-wide Association Mapping and Yr Gene Markers. Plant Disease, 2020, https://doi.org/10.1094/PDIS-11-19-2402-RE.
  • Type: Conference Papers and Presentations Status: Published Year Published: 2020 Citation: Yang Hu and Zhiwu Zhang, GridFree: A Python Package of Image Analysis for Object Counting and Measuring without Grid Restriction, International Conference of Plant and Animal Genome, January 11-15, 2020, San Diego, USA, presentation ID: C09, https://plan.core-apps.com/pag_2020/abstract/5c52d1f40a3fcfaa8a49d33b1d217ad7.
  • Type: Conference Papers and Presentations Status: Published Year Published: 2020 Citation: Yang Hu, Chenpeng Chen, Zhou Tang, Long-Xi Yu, and Zhiwu Zhang, High Throughput Image Techniques in Breeding, International Conference of Plant and Animal Genome, January 11-15, 2020, San Diego, USA, presentation ID: W25, https://plan.core-apps.com/pag_2020/abstract/ea84b8f3-cc24-48e9-b438-31c716c780d1
  • Type: Conference Papers and Presentations Status: Published Year Published: 2020 Citation: Chenpeng Chen and Zhiwu Zhang, A Python Package for Aerial High-Throughput Phenotyping, International Conference of Plant and Animal Genome, January 11-15, 2020, San Diego, USA, presentation ID: C10, https://plan.core-apps.com/pag_2020/event/a7ab291d8f29eb8d2f5e5b8aa400c27f
  • Type: Conference Papers and Presentations Status: Published Year Published: 2020 Citation: Zhou Tang and Zhiwu Zhang, Majority of Biomass Variation Explained by Drone Images One Day Prior to Harvesting, January 11-15, 2020, San Diego, USA, presentation ID: PO0077, https://plan.core-apps.com/pag_2020/abstract/5c52d1f40a3fcfaa8a49d33b1d2129b3
  • Type: Conference Papers and Presentations Status: Published Year Published: 2021 Citation: Sankaran, S. 2020. Phenomics using advanced sensing techniques in support of crop breeding programs. Webinar on Plant-Environment Interactions and Sustainable Production Manipal School of Life Sciences (MSLS), Manipal Academy of Higher Education (MAHE), Manipal, India, 10 February, 2021
  • Type: Conference Papers and Presentations Status: Published Year Published: 2020 Citation: Sankaran, S. 2020. Sensing technologies guided phenotyping to support crop improvement programs. 2020 AgroBIT Evolution, Brazil, 10 November, 2020.
  • Type: Conference Papers and Presentations Status: Published Year Published: 2020 Citation: Sankaran, S. 2020. Advances in phenomics tools in support of crop improvement programs. Session on Sensors and Sensing for Precision Agriculture (V16H1S1), Vaishwik Bharatiya Vaigyanik Summit (VAIBHAV), New Delhi, India, 5 October 2020.
  • Type: Conference Papers and Presentations Status: Published Year Published: 2020 Citation: Sankaran, S. 2020. Use of proximal and remote sensing data in crop phenotyping to support breeding programs. Online International Training on Agriculture 4.0 Precision and Automated Ag Technologies, Mahatma Phule Krishi Vidyapeeth (MPKV), Rahuri, India, 1 October, 2020.
  • Type: Conference Papers and Presentations Status: Published Year Published: 2020 Citation: Sankaran, S. 2020. Sensor applications in phenomics for impact in crop improvement programs. Online International Training on Present and Futuristic Trends in Agricultural Mechanization, Center of Excellence for Digital Farming Solutions for Enhancing Productivity by Robots, Drones and AGVs. Vasantrao Naik Marathwada Krishi Vidyapeeth, Parbhani, India, 23 June, 2020.
  • Type: Conference Papers and Presentations Status: Published Year Published: 2020 Citation: Andrew Herr and Arron Carter. 2020. Multispectral imaging in winter wheat variety improvement. Poster Presentation at the 2020 National Association of Plant Breeders annual meeting
  • Type: Conference Papers and Presentations Status: Published Year Published: 2021 Citation: James Chen, A paradigm shift in breeding: from genomics to phenomics. Department seminar for Crop and Soil Sciences at Washington State University, April 12, 2021, Pullman, Washington (https://css.wsu.edu/spring-2021-virtual-seminars).
  • Type: Conference Papers and Presentations Status: Published Year Published: 2021 Citation: Sankaran, S. 2021. Phenomics techniques and machine learning approaches to support crop breeding programs at Washington State University. Heilongjiang Academy of Agricultural Sciences, Nangang, Harbin, Heilongjiang, China, 11 October 2021.
  • Type: Conference Papers and Presentations Status: Published Year Published: 2021 Citation: Matthew McGowan, Matthew McGowan, Into the 3rd dimension: Integrating chromatin structure into multi-omic analysis. Molecular Plant Science at Washington State University, Dec 8, 2021 (https://mps.wsu.edu/seminar-series-2). Molecular Plant Science at Washington State University, April 28, 2021 (https://s3.wp.wsu.edu/uploads/sites/170/2021/07/Spring-2021-seminar-schedule.pdf).
  • Type: Conference Papers and Presentations Status: Published Year Published: 2021 Citation: Matthew McGowan, Into the 3rd dimension: Integrating chromatin structure into multi-omic analysis. Molecular Plant Science at Washington State University, Dec 8, 2021 (https://mps.wsu.edu/seminar-series-2).
  • Type: Conference Papers and Presentations Status: Published Year Published: 2021 Citation: Sankaran, S. 2021. Crops for Future: Role of sensing technologies to promote sustainable crop production. 2021 University of Guelph Corteva Agricultural Science Symposium on Moving Towards Sustainable Agriculture: Leveraging Scientific Innovations to Improve Current Farming Systems, Ontario, Canada, 19 November 2021
  • Type: Conference Papers and Presentations Status: Published Year Published: 2021 Citation: Sankaran, S. 2020. Sensing technologies guided phenotyping to support crop improvement programs. 2020 AgroBIT Evolution, Brazil, 10 November, 2020.
  • Type: Conference Papers and Presentations Status: Published Year Published: 2021 Citation: Herr, Andrew; Carter, Arron Multispectral Imaging in Winter Wheat Variety Improvement National Association of Plant Breeders Annual Meeting, August 2021
  • Type: Conference Papers and Presentations Status: Published Year Published: 2022 Citation: Herr, Andrew; Carter, Arron Towards Increased Genetic Gain: Utilizing Spectral Data in a Large Scale Wheat Breeding Program under a Drought Year North American Plant Phenotyping Network Annual Meeting, February 2022
  • Type: Conference Papers and Presentations Status: Published Year Published: 2022 Citation: Andrew Herr, Lance Merrick, Arron Carter (2022) Towards increased genetic gain: utilizing spectral data in wheat to improve prediction performance under a drought year. 7th International Plant Phenotyping Symposium, Wageningen, Netherlands
  • Type: Conference Papers and Presentations Status: Published Year Published: 2021 Citation: Marzougui, A., McGee, R.J., Van Vleet, S., and Sankaran, S. 2021. Improved field-phenomics protocol for selecting superior pea breeding lines using UAV and satellite-based remote sensing. Paper No. 2100469, 2021 ASABE AIM (Virtual), 12-16 July 2021.
  • Type: Conference Papers and Presentations Status: Published Year Published: 2021 Citation: Sangjan, W., Carpenter-Boggs, L., Hudson, T.D., and Sankaran, S. 2021. Pasture productivity assessment under mob grazing and fertility management using remote sensing techniques. Paper No. 2100695, 2021 ASABE AIM, 12-16 July 2021.
  • Type: Conference Papers and Presentations Status: Published Year Published: 2021 Citation: Herr, Andrew; Carter, Arron Drought Tolerance Prediction with UAS Imagery ASA-CSSA-SSSA International Annual Meeting, November 2021
  • Type: Conference Papers and Presentations Status: Published Year Published: 2022 Citation: Marzougui, A., McGee, R.J., Van Vleet, S., and Sankaran, S. 2022. Multi-scale image and feature field pea dataset fusion for remote sensing applications in phenomics. S18: III International Symposium on Mechanization, Precision Horticulture, and Robotics: Precision and Digital Horticulture in Field Environments, 2022 International Horticultural Congress, Angers, France, 17-19 August 2022.
  • Type: Conference Papers and Presentations Status: Published Year Published: 2022 Citation: Sangjan, W., Carter, A.H., Pumphrey, M.O., Jitkov, V., and Sankaran, S. 2022. Effect of plot pixel resolution on crop performance assessment using features extracted from UAV and high?resolution satellite imagery. Paper No. 2201235, 2022 ASABE AIM, Houston, TX, 18-20 July 2022.
  • Type: Conference Papers and Presentations Status: Published Year Published: 2022 Citation: Marzougui, A., McGee, R.J., Van Vleet, S., and Sankaran, S. 2022. Field?based phenomics using UAS and high-resolution satellite imagery to support pea cultivar selection, Paper No. 2201173, 2022 ASABE AIM, Houston, TX, 18-20 July 2022.
  • Type: Conference Papers and Presentations Status: Published Year Published: 2022 Citation: Sankaran, S., Sangjan, W., Pumphrey, M. O., Carter, A. H., Jitkov, V., and Hagemeyer, K.E. 2022. Multi-scale multispectral imaging for crop phenotyping applications. 2022 The Asian Federation for Information Technology in Agriculture (AFITA)/ The World Congress on Computer in Agriculture (WCCA), Hanoi, Vietnam, 24-26 November 2022 [Keynote Speaker]
  • Type: Conference Papers and Presentations Status: Published Year Published: 2022 Citation: Sankaran, S. 2022. Capturing crop agronomic traits across different spatial and temporal scales. Joint WSU-Germanys Cluster of Excellence on Plant Sciences (CEPLAS) Seminar Series on Complex Plant Traits, 12 July 2022.
  • Type: Conference Papers and Presentations Status: Published Year Published: 2022 Citation: Sankaran, S. 2022. Concepts related to sensing and associated technologies applicable to small hold farmers [Presentation and Panel Discussion], Innovative Technologies for Small-Scale Farmers, Fruit and Vegetable Small-Scale Farming Webinar Series, Organized by Food and Agriculture Organization (FAO) of the United Nations and International Society for Horticultural Science (ISHS), 21 June 2022.
  • Type: Journal Articles Status: Published Year Published: 2019 Citation: Zhiwu, Zhang, Party game ignites satellite, drone research effort, Wheat Life, October, 2019, P50-51, https://wheatlife.org/wp-content/uploads/2022/03/09_WLOct19web.pdf


Progress 02/15/21 to 02/14/22

Outputs
Target Audience:The project reached stakeholders in the full range from scientists to farmers. In total, eleven presentations were delivered at national conferences, five peer-reviewed articles were published in scientific journals, and one extension was published in extension magazine. One software package has been developed to process image data, GRID (http://zzlab.net/GRID). Changes/Problems:The pandemic restrictions of COVID19 in 2020 and 2021 severely delayed our progress for field experiments and data analyses. A no-cost extension of one year was granted (February 15, 2022 to February 14, 2023) to complete the objectives.? What opportunities for training and professional development has the project provided?The project provided support for the training and professional development at both graduate and postdoc levels. These supports include their salary and travel for domestic and international conferences in the US to present their discoveries to reach stakeholders. Eight presentations were made at workshops and conferences. James Chen, A paradigm shift in breeding: from genomics to phenomics. Department seminar for Crop and Soil Sciences at Washington State University, April 12, 2021, Pullman, Washington (https://css.wsu.edu/spring-2021-virtual-seminars). Matthew McGowan, Matthew McGowan, Into the 3rd dimension: Integrating chromatin structure into multi-omic analysis. Molecular Plant Science at Washington State University, Dec 8, 2021 (https://mps.wsu.edu/seminar-series-2). Molecular Plant Science at Washington State University, April 28, 2021 (https://s3.wp.wsu.edu/uploads/sites/170/2021/07/Spring-2021-seminar-schedule.pdf). Matthew McGowan, Into the 3rd dimension: Integrating chromatin structure into multi-omic analysis. Molecular Plant Science at Washington State University, Dec 8, 2021 (https://mps.wsu.edu/seminar-series-2). Sankaran, S. 2021. Crops for Future: Role of sensing technologies to promote sustainable crop production. 2021 University of Guelph Corteva Agricultural Science Symposium on 'Moving Towards Sustainable Agriculture: Leveraging Scientific Innovations to Improve Current Farming Systems', Ontario, Canada, 19 November 2021 Sankaran, S. 2021. Phenomics techniques and machine learning approaches to support crop breeding programs at Washington State University. Heilongjiang Academy of Agricultural Sciences, Nangang, Harbin, Heilongjiang, China, 11 October 2021. Sankaran, S. 2020. Sensing technologies guided phenotyping to support crop improvement programs. 2020 AgroBIT Evolution, Brazil, 10 November, 2020. Marzougui, A., McGee, R.J., Van Vleet, S., and Sankaran, S. 2021. Improved field-phenomics protocol for selecting superior pea breeding lines using UAV and satellite-based remote sensing. Paper No. 2100469, 2021 ASABE AIM (Virtual), 12-16 July 2021. Sangjan, W., Carpenter-Boggs, L., Hudson, T.D., and Sankaran, S. 2021. Pasture productivity assessment under mob grazing and fertility management using remote sensing techniques. Paper No. 2100695, 2021 ASABE AIM (Virtual), 12-16 July 2021. Herr, Andrew; Carter, Arron "Drought Tolerance Prediction with UAS Imagery" ASA-CSSA-SSSA International Annual Meeting, November 2021 Herr, Andrew; Carter, Arron "Multispectral Imaging in Winter Wheat Variety Improvement" National Association of Plant Breeders Annual Meeting, August 2021 Herr, Andrew; Carter, Arron "Towards Increased Genetic Gain: Utilizing Spectral Data in a Large Scale Wheat Breeding Program under a Drought Year" North American Plant Phenotyping Network Annual Meeting, February 2022 How have the results been disseminated to communities of interest?The research results have been disseminated through multiple platforms, including publication, extension articles, website, and conferences. Four articles on the method and software development has been published. 1. Yang Hu, and Zhiwu Zhang*, GridFree: a python package of imageanalysis for interactive grain counting and measuring. Plant Physiology, 2021, https://doi.org/10.1093/plphys/kiab226 2. Zhou Tang, Atit Parajuli, Chunpeng James Chen, Yang Hu, Samuel Revolinski, Cesar Augusto Medina, Sen Lin, Zhiwu Zhang*. Validation of UAV-based alfalfa biomass predictability using photogrammetry with fully automatic plot segmentation. Scientific Reports, 2021, doi: 10.1038/s41598-021-82797-x. 3. Jiabo Wang* and Zhiwu Zhang*, GAPIT Version 3: Boosting Power and Accuracy for Genomic Association and Prediction. Genomics, Proteomics and Bioinformatics, 2021, https://doi.org/10.1016/j.gpb.2021.08.005 4. Matthew T. McGowan, Zhiwu Zhang & Stephen P. Ficklin, Chromosomal characteristics of salt stress heritable gene expression in the rice genome. BMC Genomic Data, 2021, https://doi.org/10.1186/s12863-021-00970-7. 5. Sankaran, S., Marzougui, A., Hurst, J. P., Zhang, C., Schnable, J. C., & Shi, Y. (2021). Can High-Resolution Satellite Multispectral Imagery Be Used to Phenotype Canopy Traits and Yield Potential in Field Conditions? Transactions of the ASABE, 64(3), 879-891. What do you plan to do during the next reporting period to accomplish the goals? Software development Algorithm development Data analyses and Publications Training for graduate and postdoc Outreach stakeholders

Impacts
What was accomplished under these goals? The overall goal of this project is to boost wheat production by improving breeding efficiency. The specific objectives are 1) variety identification on satellite images; 2) identification of image features related to agronomy traits; 3) genomic selection, and 4) genome-wide association studies. In year 3 (Feb 15, 2021, to Feb 14, 2022), the major activities included 1) growing winter and spring varieties; 2) phenotyping agronomy traits; 3) collecting drone images; 4) collecting satellite images, and 5) method and software development. The conventional agronomy traits, including heading dates and plant height, were measured in 2021 for both winter and spring wheat. Drone images were collected weekly or bi-weekly in 8 locations at Palouse, accumulating one TB image data. The locations include Lind, Pullman, Colton, Union Center, Fairfield, Farmington, Palouse, Plaza, and St. John, Lamont. One software package has been developed to process image data, GridFree (https://zzlab.net/GridFree). Four articles have been published in peer-reviewed journals.

Publications

  • Type: Journal Articles Status: Published Year Published: 2021 Citation: Yang Hu, and Zhiwu Zhang*, GridFree: a python package of imageanalysis for interactive grain counting and measuring. Plant Physiology, 2021, https://doi.org/10.1093/plphys/kiab226
  • Type: Journal Articles Status: Published Year Published: 2021 Citation: Zhou Tang, Atit Parajuli, Chunpeng James Chen, Yang Hu, Samuel Revolinski, Cesar Augusto Medina, Sen Lin, Zhiwu Zhang*. Validation of UAV-based alfalfa biomass predictability using photogrammetry with fully automatic plot segmentation. Scientific Reports, 2021, doi: 10.1038/s41598-021-82797-x.
  • Type: Journal Articles Status: Published Year Published: 2021 Citation: Jiabo Wang* and Zhiwu Zhang*, GAPIT Version 3: Boosting Power and Accuracy for Genomic Association and Prediction. Genomics, Proteomics and Bioinformatics, 2021, https://doi.org/10.1016/j.gpb.2021.08.005
  • Type: Journal Articles Status: Published Year Published: 2021 Citation: Matthew T. McGowan, Zhiwu Zhang & Stephen P. Ficklin, Chromosomal characteristics of salt stress heritable gene expression in the rice genome. BMC Genomic Data, 2021, https://doi.org/10.1186/s12863-021-00970-7.
  • Type: Journal Articles Status: Published Year Published: 2021 Citation: Sankaran, S., Marzougui, A., Hurst, J. P., Zhang, C., Schnable, J. C., & Shi, Y. (2021). Can High-Resolution Satellite Multispectral Imagery Be Used to Phenotype Canopy Traits and Yield Potential in Field Conditions? Transactions of the ASABE, 64(3), 879-891. https://elibrary.asabe.org/abstract.asp?aid=52185


Progress 02/15/20 to 02/14/21

Outputs
Target Audience:The overall goal of this project is to boost wheat production by improving breeding efficiency. The specific objectives are 1) variety identification on satellite images; 2) identification of image features related to agronomy traits; 3) genomic selection, and 4) genome-wide association studies. In year 1 (Feb 15, 2019, to Feb 14, 2020), the major activities included 1) growing winter and spring varieties; 2) phenotyping agronomy traits; 3) collecting drone images; 4) collecting satellite images, and 5) method and software development. The conventional agronomy traits, including heading dates and plant height, were measured in 2020 for both winter and spring wheat. Drone images were collected weekly or bi-weekly in 11 locations at Palouse, accumulating one TB image data. The locations include Lind, Pullman, Colton, Union Center, Fairfield, Farmington, Palouse, Plaza, St. John, Lamont, and Ritzville. One software package has been developed to process image data, GRID (http://zzlab.net/GRID). Four articles have been published in peer reviewed journals. Changes/Problems:There was no major change in approach. What opportunities for training and professional development has the project provided?The project provided support for the training and professional development at both graduate and postdoc levels. These supports include their salary and travel for domestic and international conferences in the US to present their discoveries to reach stakeholders.Eight presentations were made at workshops and conferences. Sankaran, S. 2020. Phenomics using advanced sensing techniques in support of crop breeding programs. Webinar on Plant-Environment Interactions and Sustainable Production Manipal School of Life Sciences (MSLS), Manipal Academy of Higher Education (MAHE), Manipal, India, 10 February, 2021. [Virtual] [Participants: 135] Sankaran, S. 2020. Sensing technologies guided phenotyping to support crop improvement programs. 2020 AgroBIT Evolution, Brazil, 10 November, 2020. [Virtual] [Participants: 3000] Sankaran, S. 2020. Advances in phenomics tools in support of crop improvement programs. Session on Sensors and Sensing for Precision Agriculture (V16H1S1), Vaishwik Bharatiya Vaigyanik Summit (VAIBHAV), New Delhi, India, 5 October 2020. [Virtual] [Participants: 627] Sankaran, S. 2020. Use of proximal and remote sensing data in crop phenotyping to support breeding programs. Online International Training on Agriculture 4.0 Precision and Automated Ag Technologies, Mahatma Phule Krishi Vidyapeeth (MPKV), Rahuri, India, 1 October, 2020. [Virtual] [Participants: 778] Sankaran, S. 2020. Sensor applications in phenomics for impact in crop improvement programs. Online International Training on Present and Futuristic Trends in Agricultural Mechanization, Center of Excellence for Digital Farming Solutions for Enhancing Productivity by Robots, Drones and AGVs. Vasantrao Naik Marathwada Krishi Vidyapeeth, Parbhani, India, 23 June, 2020. [Webinar] [Participants: 192] Andrew Herr and Arron Carter. 2020. Multispectral imaging in winter wheat variety improvement. Poster Presentation at the 2020 ASA-CSSA-SSSA Annual Meeting, Virtual. Andrew Herr and Arron Carter. 2020. Multispectral imaging in winter wheat variety improvement. Poster Presentation at the 2020 National Association of Plant Breeders annual meeting, Virtual. Andrew Herr and Arron Carter. 2020. Picture This: Using a Bird's-Eye View to Improve Genetic Gain in a Wheat Breeding Program. p. 61.InCrow, S. and Schillinger W. (eds). "2020 Dryland Field Day Abstracts: Highlights of Research Progress". Cooperative Extension, Washington State University, Dept. of Crop and Soil Sciences, Technical Report 20-1. How have the results been disseminated to communities of interest?The research results have been disseminated through multiple platforms, including publication, extension articles, website, and conferences. Four articles on the method and software development has been published. Zhang, C., Marzougui, A., and Sankaran, S. 2020. High-resolution satellite imagery applications in crop phenotyping: An overview. Computers and Electronics in Agriculture, 175, 105584.https://doi.org/10.1016/j.compag.2020.105584 Zhou Tang, Atit Parajuli, Chunpeng James Chen, Yang Hu, Samuel Revolinski, Cesar Augusto Medina, Sen Lin,Zhiwu Zhang*.Validation of UAV-based alfalfa biomass predictability using photogrammetry with fully automatic plot segmentation.Scientific Reports,doi: 10.1038/s41598-021-82797-x. James Chen andZhiwu Zhang.GRID: A Python Package for Field Plot Phenotyping Using Aerial Images.Remote Sensing, 2020,https://www.mdpi.com/2072-4292/12/11/1697. Wei Huang, Ping Zheng, Zhenhai Cui, Zhuo Li, Yifeng Gao, Helong Yu, You Tang, Xiaohui Yuan, andZhiwu Zhang*.MMAP: A Cloud Computing Platform for Mining the Maximum Accuracy of Predicting Phenotypes from Genotypes.Bioinformatics, 2020.https://doi.org/10.1093/bioinformatics/btaa824 What do you plan to do during the next reporting period to accomplish the goals? UAV data collection in 2021 (1TB) Satellite images in 2021 (1TB) Software development Algorithm development Publications Training for graduate and postdoc Outreach stakeholders

Impacts
What was accomplished under these goals? The overall goal of this project is to boost wheat production by improving breeding efficiency. The specific objectives are 1) variety identification on satellite images; 2) identification of image features related to agronomy traits; 3) genomic selection, and 4) genome-wide association studies. In year 1 (Feb 15, 2019, to Feb 14, 2020), the major activities included 1) growing winter and spring varieties; 2) phenotyping agronomy traits; 3) collecting drone images; 4) collecting satellite images, and 5) method and software development. The conventional agronomy traits, including heading dates and plant height, were measured in 2020 for both winter and spring wheat. Drone images were collected weekly or bi-weekly in 11 locations at Palouse, accumulating one TB image data. The locations include Lind, Pullman, Colton, Union Center, Fairfield, Farmington, Palouse, Plaza, St. John, Lamont, and Ritzville. One software package has been developed to process image data, GRID (http://zzlab.net/GRID). Four articles have been published in peer reviewed journals.

Publications

  • Type: Journal Articles Status: Published Year Published: 2020 Citation: James Chen and Zhiwu Zhang. GRID: A Python Package for Field Plot Phenotyping Using Aerial Images. Remote Sensing, 2020, https://www.mdpi.com/2072-4292/12/11/1697
  • Type: Journal Articles Status: Published Year Published: 2021 Citation: 2. Zhou Tang, Atit Parajuli, Chunpeng James Chen, Yang Hu, Samuel Revolinski, Cesar Augusto Medina, Sen Lin, Zhiwu Zhang*. Validation of UAV-based alfalfa biomass predictability using photogrammetry with fully automatic plot segmentation. Scientific Reports, doi: 10.1038/s41598-021-82797-x.
  • Type: Journal Articles Status: Published Year Published: 2020 Citation: 3. James Chen and Zhiwu Zhang. GRID: A Python Package for Field Plot Phenotyping Using Aerial Images. Remote Sensing, 2020, https://www.mdpi.com/2072-4292/12/11/1697 .
  • Type: Journal Articles Status: Published Year Published: 2020 Citation: Wei Huang, Ping Zheng, Zhenhai Cui, Zhuo Li, Yifeng Gao, Helong Yu, You Tang, Xiaohui Yuan, and Zhiwu Zhang*. MMAP: A Cloud Computing Platform for Mining the Maximum Accuracy of Predicting Phenotypes from Genotypes. Bioinformatics, 2020. https://doi.org/10.1093/bioinformatics/btaa824
  • Type: Websites Status: Published Year Published: 2020 Citation: http://zzlab.net/GRID
  • Type: Websites Status: Published Year Published: 2020 Citation: http://zzlab.net/MMAP


Progress 02/15/19 to 02/14/20

Outputs
Target Audience:Wheat breeders, genetics, and farmers Changes/Problems:There was no major change in approach. What opportunities for training and professional development has the project provided?The project provided support for the training and professional development at both graduate and postdoc levels. These supports include their salary and travel for domestic and international conferences in the US to present their discoveries to reach stakeholders. The project has supported multiple people to attend the International Conference of Plant and Animal Genome in January of 2020. Their presentations include following. https://plan.core-apps.com/pag_2020/abstract/5c52d1f40a3fcfaa8a49d33b1d217ad7 https://plan.core-apps.com/pag_2020/abstract/ea84b8f3-cc24-48e9-b438-31c716c780d1 https://plan.core-apps.com/pag_2020/event/a7ab291d8f29eb8d2f5e5b8aa400c27f https://plan.core-apps.com/pag_2020/abstract/5c52d1f40a3fcfaa8a49d33b1d2129b3 How have the results been disseminated to communities of interest?The research results have been disseminated through multiple platforms, including publication, extension articles, website, and conferences. The manuscript on the method and software development has been submitted to Remote Sensing, which is currently under review. One extension article was published by Wheat Life, October 2019, page 50-51(https://wheatlife.org/Issues/09_WLOct19web.pdf). One website was published by the College of Agricultural, Human, and Natural Resource (CAHNRS) at Washington State university, entitled "Images from space could help farmers grow better wheat varieties" (https://news.wsu.edu/2019/05/29/images-space-help-farmers-grow-better-wheat-varieties/). What do you plan to do during the next reporting period to accomplish the goals?In year 2 (Feb 15, 2020 to Feb 14, 2021), we will continue data collection for agronomy traits, drone images, and satellite. Another major activity is development of methods and software. The key ellements are as following: UAV data collection in 2020 (1TB) Satellite images in 2020 (1TB) Software development Algorithm development Publications Training for graduate and postdoc Outreach stakeholders

Impacts
What was accomplished under these goals? The overall goal of this project is to boost wheat production by improving breeding efficiency. The specific objectives are 1) variety identification on satellite images; 2) identification of image features related to agronomy traits; 3) genomic selection, and 4) genome-wide association studies. In year 1 (Feb 15, 2019, to Feb 14, 2020), the major activities included 1) growing winter and spring varieties; 2) phenotyping agronomy traits; 3) collecting drone images; 4) collecting satellite images, and 5) method and software development. In the fall of 2018, 320 winter varieties were planted through existing projects. In the spring of 2019, 310 spring varieties were planted. The agronomy traits, including heading dates and plant height, were measured in 2019 for both winter and spring wheat. Drone images were collected weekly or bi-weekly in 11 locations at Palouse, accumulating one TB image data. The locations include Lind, Pullman, Colton, Union Center, Fairfield, Farmington, Palouse, Plaza, St. John, Lamont, and Ritzville. Membership was purchased from Planet, and a total of 10 TB satellite images (60,000) were obtained for the Palouse area (6,279 km square) covering 2009 to 2019. These images have a 3x3 meter resolution with a time interval of one day. The bands include red, green, blue, NIR, and SWIR. One software package has been developed to process image data, GRID (http://zzlab.net/GRID). The manuscript has been submitted for publication.

Publications

  • Type: Other Status: Published Year Published: 2019 Citation: https://wheatlife.org/Issues/09_WLOct19web.pdf
  • Type: Websites Status: Published Year Published: 2019 Citation: https://news.wsu.edu/2019/05/29/images-space-help-farmers-grow-better-wheat-varieties/
  • Type: Journal Articles Status: Under Review Year Published: 2020 Citation: Remote Sensing