A Neural Network for Setting Target Corn Yields

Setting a realistic yield goal in each part of the field is one of the critical problems in precision agriculture. Factorsaffecting crop yields, such as soil, weather, and management, are so complex that traditional statistics cannot give accurateresults. As an automatic learning tool, the artificial neural network (ANN) is an attractive alternative for processing themassive data set generated by precision farming production and research. A feedforward, completely connected,backpropagation ANN was designed to approximate the nonlinear yield function relating corn yield to factors influencingyield. By stratified sampling based on rainfall, some of the data were excluded from the training set and used to verify theyield prediction accuracy of the ANN. The RMS error for 60 verification patterns was about 20%. After the ANN wasdeveloped and trained, three aspects of the input factors were investigated: (1) yield trends with 4 input factors, (2) interactionbetween nitrogen application rate and late July rainfall, and (3) optimization of the 15 input factors with a genetic algorithmto determine maximum yield. The model was then used on another field, and preliminary results of the latter study are given.