Rice researchers at Texas A&M AgriLife Research Center in Beaumont have begun a project that uses drones, UAVs, data to speed up the selection and cultivation of rice varieties.
The team will use drones to capture real-time rice crop images, extract crop phenotypic traits from the images, and ultimately analyze that information to detect superior high-yielding rice genotypes.
Yubin Young, Ph.D., a senior biosystems analyst at the Beaumont Center, is managing a Texas A&M AgriLife research project funded by a three-year $ 650,000 grant from the U.S. Department of Agriculture-National Food and Agriculture Institute. The project seeks to circumvent the main obstacle to data collection - a labor-intensive and time-consuming process of manual data collection in the field using skilled labor.
Young in the project team is joined by fellow scientists from AgriLife Research Stanley Omar Samonte, Ph.D., a hybrid rice grower; Fugen Dou, Ph.D., crop nutrient management; Ted Wilson, Ph.D., director of the center and head of the Department of Rice Growing Jack B. Vendt; Tanumoi Bera, Ph.D., postdoctoral research associate, all in the Texas A&M Department of Soil and Crop Science; and Jing Zhang, Ph.D., Associate Professor of Computer Science, Lamar University, Beaumont.
Key research objectives include:
- Quantify the key phenotypic traits of rice growth and development.
- Capture UAV images of rice genotypes at key stages of rice growth.
- Develop advanced image processing algorithms to highlight key phenological, morphological, and architectural features for key stages of rice growth.
- Develop a digital rice selection system that performs genotype screening with the best performance through data integration and multi-trait decision making.
Advantages of UAV technology
“Traditional manual measurement of rice phenotypic traits is very, very time consuming,” Young said. “It is becoming an increasing challenge to hire qualified and experienced staff. UAV technology and advanced image processing can potentially provide a cost-effective and reliable alternative. We can use drones to capture images of rice at key stages of growth and develop algorithms to isolate different phenotypic traits for hundreds or even thousands of rice genotypes.
Thousands of UAV images will be collected, as well as truth data on the ground during the rice harvest season, Young said. Several UAV flights will be performed to capture rice images from different camera angles to help analyze stand establishment and gaps between plants.
“A significant amount of data will need to be integrated and analyzed,” Young said. “This is the first year of the project and for us it is a learning process. Timely shooting of UAV images for early rice growth was challenging due to the small size of the rice seedlings and windy weather. There is a limited period when you can fly. ”
Developing advanced image processing algorithms
While collecting UAV data, the team will also develop machine learning algorithms to identify key traits and select the most successful rice genotypes.
The research project will evaluate key phenotypic traits for breeding selection, such as stand formation, biomass growth, phenological development and final grain yield.
“We will develop automated algorithms that can extract phenotypic traits from UAV images taken in critical phases of rice, including seedlings, wrestling, flowering, grain filling and maturity,” Young said. “A digital rice selection system will be developed through the integration of multiple traits to identify the genotypes with the best performance.
Dou said that another potential aspect of the use of UAV technology will be monitoring the growth of plants for nitrogen management and disease detection.
“We have an ongoing project to assess the status of rice nitrogen from UAV images,” Dou said. “Diagnosis of plant nutrients and other stresses based on UAV has a huge potential, especially for rice with limited access to the field due to the flooded production system.
“This proposed project represents a major effort to provide an integrated decision-making system based on UAV images to rice growers and researchers,” Young said. “It will be an indispensable tool for significantly improving rice cultivation and phenotyping efficiency.”
-30-