Advanced searches left 3/3

Random Variable - Europe PMC

Summarized by Plex Scholar
Last Updated: 12 September 2022

* If you want to update the article please login/register

Random forest regression for optimizing variable planting rates for corn and soybean using topographical and soil data

By leveraging on a variety of plant growth, hybrid/variety, topography, soil characteristics, weather conditions, and yield improvements, 28 sites in New York between 2014 and 2018 were conducted, using a random forest regression model developed by the New York Corn and Soybear Growers Association. In terms of random forest regression variable importance, plantation rate ranked highly in terms of deterministic interactions with complex plant growth characteristics, indicating that yield response to planting rate is likely dependent on complex interactions with agriu2010landscape features. Moderate yield within the site's u2010years were expected, but the ability to predict yield in untested location's u2010years was poor. These findings, taken together, show that local testing may have the most accurate optimized planting rate designs due to each site's unique combination of conditions.

Source link: https://europepmc.org/article/MED/IND607863312

* Please keep in mind that all text is summarized by machine, we do not bear any responsibility, and you should always check original source before taking any actions

* Please keep in mind that all text is summarized by machine, we do not bear any responsibility, and you should always check original source before taking any actions