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

Correspondence MichaelA.Gore, PlantBreeding and Genetics Section, School of Integrative Plant Science,CornellUniversity, Ithaca, NY, 14853,USA Email:mag87@cornell.edu Abstract 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.

[1]  Margaret R. Krause,et al.  Random Forest Regression for Optimizing Variable Planting Rates for Corn and Soybean Using High-Resolution Topographical and Soil Data , 2020, bioRxiv.

[2]  Fusuo Zhang,et al.  Magnesium Fertilization Improves Crop Yield in Most Production Systems: A Meta-Analysis , 2020, Frontiers in Plant Science.

[3]  I. Ciampitti,et al.  Optimum Soybean Seeding Rates by Yield Environment in Southern Brazil , 2018, Agronomy Journal.

[4]  Patrizia Busato,et al.  Machine Learning in Agriculture: A Review , 2018, Sensors.

[5]  Salah Sukkarieh,et al.  Machine learning approaches for crop yield prediction and nitrogen status estimation in precision agriculture: A review , 2018, Comput. Electron. Agric..

[6]  C. Forest,et al.  Analysis of climate signals in the crop yield record of sub‐Saharan Africa , 2018, Global change biology.

[7]  N. Curi,et al.  Multiple linear regression and random forest to predict and map soil properties using data from portable X-ray fluorescence spectrometer (pXRF). , 2017 .

[8]  Chao Gao,et al.  Prediction of soil organic carbon in an intensively managed reclamation zone of eastern China: A comparison of multiple linear regressions and the random forest model. , 2017, The Science of the total environment.

[9]  Roger W. Elmore,et al.  Corn (Zea mays L.) seeding rate optimization in Iowa, USA , 2017, Precision Agriculture.

[10]  Jonathan P. Resop,et al.  Random Forests for Global and Regional Crop Yield Predictions , 2016, PloS one.

[11]  T. Shiraiwa,et al.  Branch development responses to planting density and yield stability in soybean cultivars , 2016 .

[12]  Y. Everingham,et al.  Accurate prediction of sugarcane yield using a random forest algorithm , 2016, Agronomy for Sustainable Development.

[13]  Jun Zhu,et al.  Identifying Field Attributes that Predict Soybean Yield Using Random Forest Analysis , 2016 .

[14]  R. Barnhisel,et al.  Agronomic Benefits of Varying Corn Seed Populations: A Central Kentucky Study , 2015 .

[15]  Fernando E. Miguez,et al.  Nonlinear Regression Models and Applications in Agricultural Research , 2015 .

[16]  Jongsung Kim,et al.  Holistic environmental soil-landscape modeling of soil organic carbon , 2014, Environ. Model. Softw..

[17]  R Core Team,et al.  R: A language and environment for statistical computing. , 2014 .

[18]  M. Sorrells,et al.  Using Genomic Prediction to Characterize Environments and Optimize Prediction Accuracy in Applied Breeding Data , 2013 .

[19]  W. Cox,et al.  Inconsistent Responses of Corn to Seeding Rates in Field‐Scale Studies , 2013 .

[20]  T. Amado,et al.  Optimization of corn plant population according to management zones in Southern Brazil , 2013, Precision Agriculture.

[21]  B. Schröder,et al.  Spatial disaggregation of complex soil map units: A decision-tree based approach in Bavarian forest soils , 2012 .

[22]  Onisimo Mutanga,et al.  High density biomass estimation for wetland vegetation using WorldView-2 imagery and random forest regression algorithm , 2012, Int. J. Appl. Earth Obs. Geoinformation.

[23]  Kyungsoo Yoo,et al.  Using hilltop curvature to derive the spatial distribution of erosion rates , 2012 .

[24]  B. Huwe,et al.  Uncertainty in the spatial prediction of soil texture: Comparison of regression tree and Random Forest models , 2012 .

[25]  M. Wimberly,et al.  Climatic and genetic controls of yields of switchgrass, a model bioenergy species , 2012 .

[26]  Jill A. Marshall,et al.  Evidence for biotic controls on topography and soil production , 2010 .

[27]  Douglas J. Miller,et al.  Product Life Cycles and Innovation in the US Seed Corn Industry , 2010 .

[28]  Ian J. Yule,et al.  Soil water status mapping and two variable-rate irrigation scenarios , 2009, Precision Agriculture.

[29]  Achim Zeileis,et al.  Conditional variable importance for random forests , 2008, BMC Bioinformatics.

[30]  L. Joseph.  ADAPT-N: ADAPTIVE NITROGEN MANAGEMENT FOR MAIZE USING HIGH- RESOLUTION CLIMATE DATA AND MODEL SIMULATIONS , 2008 .

[31]  Efi Foufoula-Georgiou,et al.  Channel network extraction from high resolution topography using wavelets , 2007 .

[32]  David S. Bullock,et al.  Using Spatial Analysis to Study the Values of Variable Rate Technology and Information , 2007 .

[33]  Achim Zeileis,et al.  Bias in random forest variable importance measures: Illustrations, sources and a solution , 2007, BMC Bioinformatics.

[34]  Michael J. Roberts,et al.  Nonlinear Effects of Weather on Corn Yields , 2006 .

[35]  K. Hornik,et al.  Unbiased Recursive Partitioning: A Conditional Inference Framework , 2006 .

[36]  David S. Bullock,et al.  Site-specific production functions for variable rate corn nitrogen fertilization , 2006, Precision Agriculture.

[37]  S. Swinton,et al.  Is Site‐Specific Yield Response Consistent Over Time? Does it Pay? , 2006 .

[38]  Yuxin Miao,et al.  Identifying important factors influencing corn yield and grain quality variability using artificial neural networks , 2006, Precision Agriculture.

[39]  Budiman Minasny,et al.  Uncertainty analysis for soil‐terrain models , 2006, Int. J. Geogr. Inf. Sci..

[40]  James Lowenberg-DeBoer,et al.  Economic Analysis of Spatial-Temporal Patterns in Corn and Soybean Response to Nitrogen and Phosphorus , 2006 .

[41]  B. Henderson,et al.  Australia-wide predictions of soil properties using decision trees , 2005 .

[42]  Rattan Lal,et al.  Relationships between surface soil organic carbon pool and site variables , 2004 .

[43]  Thomas A. Doerge,et al.  Feasibility of Site-Specific Management of Corn Hybrids and Plant Densities in the Great Plains , 2004, Precision Agriculture.

[44]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[45]  Graham A. Moore,et al.  Estimation of the Importance of Spatially Variable Nitrogen Application and Soil Moisture Holding Capacity to Wheat Production , 2004, Precision Agriculture.

[46]  P. Gerard,et al.  Variability of Selected Soil Properties and Their Relationships with Soybean Yield , 2003 .

[47]  S. Polasky,et al.  Agricultural sustainability and intensive production practices , 2002, Nature.

[48]  Z. L. Frogbrook,et al.  Exploring the spatial relations between cereal yield and soil chemical properties and the implications for sampling , 2002 .

[49]  R. Plant.  Site-specific management: the application of information technology to crop production , 2001 .

[50]  Gregory L. Tylka,et al.  METHOD TO USE CROP GROWTH MODELS TO ESTIMATE POTENTIAL RETURN FOR VARIABLE–RATE MANAGEMENT IN SOYBEANS , 2001 .

[51]  A. Kravchenko,et al.  Correlation of Corn and Soybean Grain Yield with Topography and Soil Properties , 2000 .

[52]  David S. Bullock,et al.  Does variable rate seeding of corn pay , 1998 .

[53]  Dennis Timlin,et al.  Spatial and temporal variability of corn grain yield on a hillslope , 1998 .

[54]  James Lowenberg-DeBoer,et al.  Economics of Variable Rate Planting for Corn , 1998 .

[55]  D. W. Stewart,et al.  Plant population density effects on maize inbred lines grown in short-season environments , 1998 .

[56]  Rattan Lal,et al.  Slope Position and Erosional Effects on Soil Properties and Corn Production on a Miamian Soil in Central Ohio , 1997 .

[57]  D. Mulla,et al.  Key processes and properties for site-specific soil and crop management. , 1997 .

[58]  N. Katerji,et al.  Effect of salinity on water stress, growth, and yield of maize and sunflower , 1996 .

[59]  Gary A. Peterson,et al.  Soil Attribute Prediction Using Terrain Analysis , 1993 .

[60]  D. T. Lewis,et al.  Soil Properties Associated with Landscape Position , 1993 .

[61]  R. Wells.  Dynamics of Soybean Growth in Variable Planting Patterns , 1993 .

[62]  D. R. Nielsen,et al.  Spatial variability of wheat yield and soil properties on complex hills , 1988 .

[63]  C. Thorne,et al.  Quantitative analysis of land surface topography , 1987 .

[64]  R. H. Fox,et al.  Soil magnesium level, corn (Zea mays L.) yield, and magnesium uptake , 1984 .

[65]  S. Rogers.  MAGNESIUM DEFICIENCY , 1976, The Lancet.

[66]  J. Rutger,et al.  Effect of High Plant Density on Silage and Grain Yields of Six Corn Hybrids 1 , 1967 .

[67]  L. T. Kurtz,et al.  Response of corn and soybeans to magnesium fertilizers. , 1960 .

[68]  S. A. Barber,et al.  Magnesium Deficiency and Corn Yield on Two Acid Indiana Soils1 , 1958 .

[69]  G. M. Shear,et al.  Variations in Response of Different Varieties and Hybrids of Field Corn to Planting Rate1 , 1946 .