Using Machine Learning and Feature Selection for Alfalfa Yield Prediction

Abstract

Predicting alfalfa biomass and crop yield for livestock feed is important to the daily lives of virtually everyone, and many features of data from this domain combined with corresponding weather data can be used to train machine learning models for yield prediction. In this work, we used yield data of different alfalfa varieties from multiple years in Kentucky and Georgia, and we compared the impact of different feature selection methods on machine learning (ML) models trained to predict alfalfa yield. Linear regression, regression trees, support vector machines, neural networks, Bayesian regression, and nearest neighbors were all developed with cross validation. The features used included weather data, historical yield data, and the sown date. The feature selection methods that were compared included a correlation-based method, the ReliefF method, and a wrapper method. We found that the best method was the correlation-based method, and the feature set it found consisted of the Julian day of the harvest, the number of days between the sown and harvest dates, cumulative solar radiation since the previous harvest, and cumulative rainfall since the previous harvest. Using these features, the k-nearest neighbor and random forest methods achieved an average R value over 0.95, and average mean absolute error less than 200 lbs./acre. Our top R2 of 0.90 beats a previous work’s best R2 of 0.87. Our primary contribution is the demonstration that ML, with feature selection, shows promise in predicting crop yields even on simple datasets with a handful of features, and that reporting accuracies in R and R2 offers an intuitive way to compare results among various crops.

Application of machine learning to explore the genomic prediction accuracy of fall dormancy in autotetraploid alfalfa

“…The results showed that the correlation-based method is better than others. With feature selection, the k -nearest neighbor and random forest methods could predict alfalfa yield [ 29 ]. In this study, we used five methods to predict FD.…”

“…In alfalfa yield, machine learning models can use weather, historical yield, and sown date to make predictions. Published results have shown that the k -nearest neighbor and random forest methods performed well [ 29 ].…”

On Using Artificial Intelligence and the Internet of Things for Crop Disease Detection: A Contemporary Survey

“…Using this vector, it is possible to discriminate one class of objects from another. The final step is classification [32]. Note that the choice of a suitable classifier depends on the specific problem.…”

Prediction of Pest Insect Appearance Using Sensors and Machine Learning

“…In article [ 8 ], the input data of soil and crop properties were used to predict yield. ML algorithms can be used to predict alfalfa yield [ 9 ], maize yield and nitrate loss [ 10 ], and to assess the seasonal nitrogen status in maize [ 11 , 12 ], carrot yield mapping [ 13 ], soil suitability for growing individual crops [ 14 ] and peach tree nutrients at the local level [ 15 ].…”