The enormous potential of big data has already been demonstrated in areas such as financial services and telecommunications. For the first time, an international team of researchers, led by the IPK Leibniz Institute, has taken advantage of the large-scale big data potential for plant research. To this end, we used data from three projects to improve the accuracy of wheat hybrid yield predictions.
“We were able to take advantage of the largest dataset ever published, which contains information from nearly a decade of wheat research and development,” said IPK’s Breeding Research Division. Said Dr. Jochen Reif, who is responsible for.Results that herald the arrival of a new era Plant breeding, Now published in magazines Science Advances..
Finally, data on more than 13,000 genotypes tested on 125,000 yield plots were analyzed. For comparison: In breeding programs, plant Tested on 20,000 yield plots each year. “It was clear that we needed to increase populations to ultimately develop a robust predictive model of yield,” said Dr. Jochen Reif. It’s a long way to go, “he said. “Our study was able to double the accuracy of yield prediction.”
The research team used data from two previous projects, HYWHEAT (funded by the Federal Ministry of Research and Education) and Zuchtwert (funded by the Federal Ministry of Food and Agriculture), and a program from the Seed Producer KWS. Basically, the challenge in such research is to prepare the information at a uniform quality level and enable common analysis. “Since we were responsible for the design of the experiment from the beginning, we could plan to always test a small portion of the same genotype throughout the project, which would allow for integrated analysis in the first place. That’s what Dr. Jochen Reif says.
Scientists are convinced that it is beneficial to use big data for plant breeding and research. “We have ultimately worked on the future of all of us,” says IPK scientists. “We have succeeded in showing the potential of big data for breeding stable yield varieties in the era of climate change.”
According to Professor Jochen Reif, current model studies are far more important than a single crop type and are expected to herald cultural changes in breeding. “We were able to demonstrate the great benefits of big data in plant breeding, but this possibility is credible for all stakeholders to share data and overcome future challenges together. Only possible with cooperation. “
Ultimately, this is also the gateway to the use of artificial intelligence (AI). “Successful use of AI also depends on successful plant breeding and research using carefully selected and comprehensive data. Our current research opens an important door to this path. Thing.”
Big data elucidation has doubled the accuracy of hybrid wheat grain yield forecasts. Science Advances (2021). DOI: 10.1126 / sciadv.abf9106
Provided by Leibniz Plant Genetics and Crop Plant Research Institute
Quote: Big Data: IPK Researchers Doubled Wheat Yield Prediction Accuracy (June 11, 2021), June 11, 2021 https://phys.org/news/2021-06-big- Obtained from ipk-accuracy-wheat-yields.html
This document is subject to copyright. No part may be reproduced without written permission, except for private research or fair trade for research purposes. The content is provided for informational purposes only.
IPK researchers double the accuracy of wheat yield forecasts
Source link IPK researchers double the accuracy of wheat yield forecasts