Premium
Random forest regression for optimizing variable planting rates for corn and soybean using topographical and soil data
Author(s) -
Krause Margaret R.,
Crossman Savanna,
DuMond Todd,
Lott Rodman,
Swede Jason,
Arliss Scott,
Robbins Ron,
Ochs Daniel,
Gore Michael A.
Publication year - 2020
Publication title -
agronomy journal
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.752
H-Index - 131
eISSN - 1435-0645
pISSN - 0002-1962
DOI - 10.1002/agj2.20442
Subject(s) - sowing , yield (engineering) , agronomy , regression analysis , context (archaeology) , random forest , mathematics , variables , agricultural engineering , environmental science , statistics , biology , computer science , engineering , paleontology , materials science , machine learning , metallurgy
In recent years, planting machinery that enables precise control of the planting rates has become available for corn ( Zea mays L.) and soybean ( Glycine max L.). With increasingly available topographical and soil information, there is a growing interest in developing variable rate planting strategies to exploit variation in the agri‐landscape in order to maximize production. A random forest regression‐based approach was developed to model the interactions between planting rate, hybrid/variety, topography, soil characteristics, weather variables, and their effects on yield by leveraging on‐farm variable rate planting trials for corn and soybean conducted at 27 sites in New York between 2014 and 2018 (57 site‐years) in collaboration with the New York Corn and Soybean Growers Association. Planting rate ranked highly in terms of random forest regression variable importance while explaining relatively minimal yield variation in the linear context, indicating that yield response to planting rate likely depends on complex interactions with agri‐landscape features. Random forest models explained moderate levels of yield within site‐years, while the ability to predict yield in untested site‐years was low. Relatedly, variable importance measures for the predictors varied considerably across sites. Together, these results suggest that local testing may provide the most accurate optimized planting rate designs due to the unique set of conditions at each site. The proposed method was extended to identify the optimal variable rate planting design for maximizing yield at each site given the underlying conditions, and empirical validation of the resulting designs is currently underway.