A 3D printed reference model for sugar beet is included in the field experiments. Credit: Institute of Sugar Beet Research, Göttingen
Scientists use laser scanning to create 3D models of the top of a sugar beet plant from a crop field, a step forward in AI-assisted crop pipeline improvement.
A demonstration of how new technologies can be used in 21st century crop breeding comes from newly published research that combines laser scanning and 3D printing to create a detailed 3D model of a sugar beet plant. Is. Taking the next step beyond genetic information to guide intelligent breeding, 3D plant models here capture the essential characteristics of the above-ground parts of a sugar beet plant and feed them into AI-assisted crop improvement pipelines. can be used for Sugar beet plant models are reproducible and suitable for field use. All research information, data, procedures, as well as 3D printing files are freely available. Crop management is getting much needed tools, and of course, everyone can now 3D print their own sugar beet plant! (Minimum maintenance required.)
Improving crops with laser beams and 3D printing
Modern plant breeding is a data-centric enterprise, involving Machine learning Algorithms and advanced imaging technology to select desired traits. “Plant phenotyping”—the science of collecting accurate information and measurements on plants—has seen massive improvements over the past few years.
In the past, phenotyping relied on measurements taken by humans through fatigue. Today, phenotyping pipelines are becoming increasingly automated, often aided by the use of sophisticated sensor technology. Artificial intelligence. Measurements taken may include size, fruit quality, leaf shape and size, and other growth parameters. In addition to the efficiency benefits of delegating the measurement task to automated pipelines, computer-aided sensors can often capture complex information about a plant that would be too difficult for humans to collect on a large scale.
Importance of accurate reference material
A critical aspect in this new, sensor-driven world of crop breeding is the availability of accurate reference material.
Sensors need to be presented with data on a “standard plant” that includes all relevant features, including more complex, 3-dimensional traits such as the angle at which leaves are oriented. Having an actual “artificial plant” as a real-size reference is therefore better than having the data in a computer, or a flat, 2D representation. For example, a real model can be added to real plants in a greenhouse or test field as a reference and internal control.
3D printed models for research
The new 3D printed model of the sugar beet plant has been developed with these applications in mind and has the added advantage that the printing files are available for free download and reuse. This allows other scientists (and any sugar beet enthusiast, really) to recreate an exact copy of the reference sugar beet, further comparing research done by different labs in different parts of the world. can go. The affordability of 3D printing also means that this approach can be adapted to resource-poor settings, for example in developing countries.
Data collection with LIDAR
To collect accurate data for their realistic model, the authors—Jonas Bömer and colleagues from the Institute of Sugarbeet Research (Göttingen) and the University of Bonn—used LIDAR (Light Detection and Ranging) technology.
Briefly, a real sugar beet plant was scanned by laser to generate 3D data from 12 different viewing angles. After the processing steps, this data was then fed into a commercial-grade 3D printer to create a life-size model of the sugar beet. The authors then tested the model for its intended use in the lab and in the field.
Jonas Bömer explains: “In the field of three-dimensional plant phenotyping, referencing the used sensor systems, computer algorithms, and captured morphological parameters represents a challenging but fundamentally important task. The generation of reproducible reference models Therefore, the application of additive manufacturing technologies provides a new opportunity to develop standard procedures for objective and accurate references, thus benefiting both scientific research and practical plant breeding.
Future applications and benefits
The approach is not limited to Chinese beets, and new Giga Science The study shows how a combination of artificial intelligence, 3D printing, and sensor technology could contribute to the future of plant breeding — helping to feed the world's population with healthy, delicious crops.
GigaScience data scientist Chris Armit added: “The value of a printable 3D model is that you can print multiple copies, one per crop field. As a low-cost phenotyping strategy, where the most As a high-cost LIDAR scanner, this approach would be great to test on other crops such as rice or African orphan crops, where a low-cost phenotyping solution is needed.
references:
“A 3D Printed Plant Model for Accurate and Reliable 3D Plant Phenotyping” 19 Jun 2024, Giga Science.
DOI: 10.1093/gigascience/giae035
“Supporting Data for a 3D Printed Plant Model for Accurate and Reliable 3D Plant Phenotyping”” 19 Jun 2024, GigaScience Database.
DOI: 10.5524/102530