Rice researchers at Texas A&M AgriLife Research Center in Beaumont have taken the selection and cultivation of rice varieties to the next level with an aircraft-using project (UAV). The team will use drones to take real-time images of rice crops, extract crop phenotypic traits from those images and analyze information to detect high-yielding rice genotypes, Texas-based A&M AgriLife said.
The researchers hope to avoid one of the main obstacles to data collection - a labor-intensive and time-consuming manual field data collection procedure with the help of a skilled workforce. Yubin Ian, a senior biosystems analyst at the Beaumont Center, will lead the project with funding provided by a three-year $ 650,000 grant from the U.S. National Institute of Food and Agriculture (NIFA).
Key research goals:
- Calculate key phenotypic traits for rice growth and development.
- Capture UAV images of rice genotypes at key stages of rice growth.
- Create advanced image processing algorithms to extract major phenological, morphological, and architectural features.
- Generate a digital rice selection system for screening for the best-performing genotypes using data integration with multi-trait decision-making.
A new wave 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.
Several drone flights will be performed during the rice harvest season to capture thousands of UAV images, as well as information about the truth on earth. Different camera angles will be used to analyze the setting of the stand, as well as the gaps between the plants.
“It will be necessary to integrate and analyze a significant amount of data,” Young added. “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. ”
The team will also work on developing machine learning algorithms that can identify key traits and determine the genotypes of rice with the best performance. The project will focus on key phenotypic traits including stand formation, biomass growth, final grain yield and phenological development.
“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.
Researchers believe that another feature of UAV technology could be monitoring plant growth to control nitrogen and detect disease, explained Fugen Doe, a fellow scientist at AgriLife Research.
“This proposed project represents a major effort to provide an integrated decision-making system based on UAV images to rice growers and researchers,” Young concluded. “It will be an indispensable tool for significantly improving rice cultivation and phenotyping efficiency.”
Read more about rice progress:
New medium density SNP panel developed for American rice
Researchers in Japan are discovering tools to improve rice production
Provivi and Syngenta Crop Protection launch pheromone-based Nelvium to control harmful rice pests
A Philippine researcher has discovered a gene for drought resistance in rice