Source: TEXAS A&M UNIVERSITY submitted to NRP
A DIGITAL RICE SELECTION SYSTEM THAT INTEGRATES UAV IMAGING, MACHINE LEARNING, AND MULTI-TRAIT DECISION-MAKING
Sponsoring Institution
National Institute of Food and Agriculture
Project Status
ACTIVE
Funding Source
AFRI COMPETITIVE GRANT
Reporting Frequency
Annual
Accession No.
1028246
Grant No.
2022-67021-36584
Cumulative Award Amt.
$649,955.00
Proposal No.
2021-11533
Multistate No.
(N/A)
Project Start Date
Jan 15, 2022
Project End Date
Jan 14, 2026
Grant Year
2022
Program Code
[A1541]- Food and Agriculture Cyberinformatics and Tools
Recipient Organization
TEXAS A&M UNIVERSITY
750 AGRONOMY RD STE 2701
COLLEGE STATION,TX 77843-0001
Performing Department
Beaumont
Non Technical Summary
Traditional crop breeding relies on time-consuming and inefficient manual field observations or samplings. Unmanned aerial vehicle (UAV)-based high-throughput phenotyping promises to alleviate the phenotyping bottleneck and provide the capability for repeated non-destructive measurement of thousands of genotypes grown in field experiment plots in crop selection cycles. Major challenges remain to enable more sophisticated analyses and development of integrated decision-making systems that can greatly accelerate crop improvement and phenotyping. We propose to develop a Digital Rice Selection System that integrates UAV imaging, machine learning, and multi-trait decision-making. Objectives are: 1) Quantify key phenological, morphological and architectural traits that capture rice growth and development; 2) Acquire multi-viewpoint UAV images of rice genotypes during critical growth stages; 3) Develop advanced image analysis algorithms to derive key phenological, morphological and architectural traits for critical rice growth stages, and 4) Develop a digital rice selection system that screens for best-performing genotypes through data integration and multi-trait decision making.Ground truth data for key traits during critical rice growth stages will be collected along with high-resolution RGB/multispectral UAV images from multiple camera angles. We will develop (1) advanced machine learning algorithms to extract key traits, (2) multi-trait-based machine learning models to estimate final aboveground biomass and grain yield, and (3) a multi-criteria decision-making system to select best-performing rice genotypes. The proposed project represents a major effort in delivering an integrated UAV imagery-based decision-making system to rice breeders and researchers and will be an indispensable tool to greatly improve rice breeding and phenotyping efficiency.
Animal Health Component
40%
Research Effort Categories
Basic
60%
Applied
40%
Developmental
(N/A)
Classification

Knowledge Area (KA)Subject of Investigation (SOI)Field of Science (FOS)Percent
2061530106080%
2061530108120%
Knowledge Area
206 - Basic Plant Biology;

Subject Of Investigation
1530 - Rice;

Field Of Science
1060 - Biology (whole systems); 1081 - Breeding;
Goals / Objectives
We propose to develop a Digital Rice Selection System that integrates UAV imaging, machine learning, and multi-trait decision-making. Specific objectives areQuantify key phenological, morphological and architectural traits that capture rice growth and developmentAcquire multi-viewpoint UAV images of rice genotypes during critical growth stagesDevelop advanced image analysis algorithms to derive key phenological, morphological and architectural traits for critical rice growth stagesDevelop a digital rice selection system that screens for best-performing genotypes through data integration and multi-trait decision making The overall goal of the proposed project is to transform traditional rice crop research towards a digital- and technology-centered integrated research paradigm for greatly improved breeding and production efficiency and help maintain the competitive edge of US agriculture.
Project Methods
We propose to develop a Digital Rice Selection System that integrates UAV imaging, machine learning, and multi-trait decision-making. Objectives are: 1) Quantify key phenological, morphological and architectural traits that capture rice growth and development; 2) Acquire multi-viewpoint UAV images of rice genotypes during critical growth stages; 3) Develop advanced image analysis algorithms to derive key phenological, morphological and architectural traits for critical rice growth stages, and 4) Develop a digital rice selection system that screens for best-performing genotypes through data integration and multi-trait decision making.Ground truth data for key traits during critical rice growth stages will be collected along with high-resolution RGB/multispectral UAV images from multiple camera angles. We will develop (1) advanced machine learning algorithms to extract key traits, (2) multi-trait-based machine learning models to estimate final aboveground biomass and grain yield, and (3) a multi-criteria decision-making system to select best-performing rice genotypes.

Progress 01/15/24 to 01/14/25

Outputs
Target Audience:The main target audiences are crop breeders, researchers, consultants, and producers. Changes/Problems: Nothing Reported What opportunities for training and professional development has the project provided?The project supported one post-doctoral research associate, a part-time research technician, and a part-time student worker. They get training on rice plant sampling, UAV image acquisition, and UAV image analysis. The post-doc was directly involved in project management, data integration and analysis as well as in grant proposal writing. How have the results been disseminated to communities of interest?Results were disseminated via the International Rice Conference, ASA, CSSA, SSSA International Annual Meeting, and the research center's field day publication and field day tour talk. What do you plan to do during the next reporting period to accomplish the goals?Conduct data analysis and prepare more manuscripts for publication. Refine and deliver the research results and web-based digital rice selection system to the rice research and producing communities, and the general public via conference meetings, field day tours, and publications

Impacts
What was accomplished under these goals? Collected ground-truth data on rice stand density, plant height, days to flowering, biomass, and grain yield for 40 rice genotypes over 3 years (2022-2024). Acquired multi-viewpoint UAV images of rice genotypes during critical rice growth stages over 3 years (2022-2024) Developed algorithms for rice seedling gap analysis and estimation on seedling stand density, tiller angle, biomass, and yields. Presented research results in international conferences, and field day highlights and tours Publish a manuscript by Li et al. 2025 UAV image analysis for detecting rice seedling gaps and gap effect on grain yield in Smart Agricultural Technology 10 (https://doi.org/10.1016/j.atech.2024.100753). A second manuscript will be ready to be submitted by the end of April 2025 to Computers and Electronics in Agriculture "Pham et al. 2025 Automatic Measurement of Rice Tiller Angle from UAV Images" A preliminary version of a web-based digital rice selection system has been developed integrating image processing, machine learning, and multi-trait decision making.

Publications

  • Type: Other Status: Other Year Published: 2025 Citation: Tan-Hanh Pham, Yubin Yang, Jing Zhang, Stanley Omar PB. Samonte, Fugen Dou, Lloyd T. Wilson, Darlene Sanchez, Tanumoy Bera, Jing Wang, Kim-Doang Nguyen. 2025. Automatic Measurement of Rice Tiller Angle from UAV Images. Computers and Electronics in Agriculture (in Preparation).
  • Type: Conference Papers and Presentations Status: Published Year Published: 2024 Citation: Li, S., Y. Yang, J. Zhang, S. O. P. Samonte, F. Dou, L. T. Wilson, T. Bera, Z. Xin-Gen, D. L. Sanchez, and J. & Wang. 2024. Assessing Rice Growth and Yield through UAV Images. 2024 ASA, CSSA, SSSA International Annual Meeting. November 10-13, 2024. San Antonio, Texas, USA
  • Type: Peer Reviewed Journal Articles Status: Published Year Published: 2025 Citation: Li, S., Y. Yang, J. Zhang, L. T. Wilson, S. O. P. B. Samonte, F. Dou, T. Bera, X. G. Zhou, D. Sanchez, and J. Wang. 2024. UAV image analysis for detecting rice seedling gaps and gap effect on grain yield. Smart Agricultural Technology, 10 109544. Doi: https://doi.org/10.1016/j.atech.2024.100753


Progress 01/15/23 to 01/14/24

Outputs
Target Audience:The main target audiences are crop breeders, researchers, consultants, and producers. Changes/Problems: Nothing Reported What opportunities for training and professional development has the project provided?The project currently supports one post-doctoral research associate, a part-time research technician, and a part-time student worker. They get training on rice plant sampling, UAV image acquisition, and UAV image analysis. The post-doc was directly involved in project management, data integration and analysis as well as in grant proposal writing. How have the results been disseminated to communities of interest?Results were disseminated via the International Rice Conference, ASA, CSSA, SSSA International Annual Meeting, and the research center's field day publication and field day tour talk. What do you plan to do during the next reporting period to accomplish the goals? Collect ground-truth data on rice stand density, plant height, days to flowering, biomass, and grain yield for 40 rice genotypes Acquire multi-viewpoint UAV images of rice genotypes during critical rice growth stages Develop and evaluate advanced algorithms for rice seedling gap analysis, seedling stand density count, and plot segmentation, and other growth characteristics Develop a web-based digital rice selection system that integrates results from objectives 1-3 Deliver the results and digital rice selection system to the rice research and producing communities, and the general public via conference meetings, field day tours, and publications

Impacts
What was accomplished under these goals? Collected ground-truth data on rice stand density, plant height, days to flowering, biomass, and grain yield for 40 rice genotypes Acquired multi-viewpoint UAV images of rice genotypes during critical rice growth stages Developed algorithms for rice seedling gap analysis, seedling stand density count, and plot segmentation A manuscript was prepared on rice seedling gap analysis Presented research results in international conferences, and field day highlights and tours

Publications

  • Type: Conference Papers and Presentations Status: Published Year Published: 2023 Citation: Li, S., Y. Yang, S. O. P. B. Samonte, F. Dou, L. T. Wilson, T. Bera, X. Zhou, D. Sanchez, J. Wang, and J. Zhang. 2023. Estimation of Rice Seedling Gaps and Seedling Density from UAV Images. 6th International Rice Congress, Manila, Philippines. Https://zenodo.org/records/10400175. Li, S., Y. Yang, J. Zhang, F. Dou, L. T. Wilson, S. O. P. B. Samonte, T. Bera, X. Zhou, and J. Wang. 2023. Application of UAV Images for Estimating Seedling Gaps in Rice. ASA, CSSA, SSSA International Annual Meeting, St. Louis, MO (https://scisoc.confex.com/scisoc/2023am/meetingapp.cgi/Paper/148579) Li, S., Y. Yang, S. O. P. B. Samonte, F. Dou, L. T. Wilson, T. Bera, X. G. Zhou, J. Wang, and J. Zhang. 2023. Estimation of rice seedling gaps and seedling density from UAV images. Texas Rice Special Section 2023:27-28.


Progress 01/15/22 to 01/14/23

Outputs
Target Audience:Rice researchers, rice producers and the general public through the research center field day publication and talk. Changes/Problems: Nothing Reported What opportunities for training and professional development has the project provided?The project currently supports one post-doctoral research associate, a part-time research technician, and a part-time student worker. They get training on rice plant sampling, UAV image acquisition, and UAV image analysis. How have the results been disseminated to communities of interest?Results were diseminated via the research center's field day publiation and field day tour talk. What do you plan to do during the next reporting period to accomplish the goals? Collectground-truth data onrice stand density, plant height, days to flowering, biomass, and grain yield for 40 rice genotypes Acquirmulti-viewpoint UAV images of rice genotypes during critical rice growth stages Developand evaluateadvancedalgorithms for rice seedling gap analysis, seedling stand density count, and plot segmentation, and other growth characteristics. Develop a web-baseddigital rice selection system that integrates results from objectives 1-3. Deliver the results and digital rice seleciton system to the rice research and producing communiteis, and the general public via conference meetings, field day tours, and publications.

Impacts
What was accomplished under these goals? Collectedground-truth data onrice stand density, plant height, days to flowering, biomass, and grain yield for 40 rice genotypes Acquiredmulti-viewpoint UAV images of rice genotypes during critical rice growth stages Developedpreliminaryalgorithms for rice seedling gap analysis, seedling stand density count, and plot segmentation

Publications