Crop Yield Forecasting using Machine Learning Techniques - A Systematic Literature Review

The utilization of machine learning has become increasingly important in the prediction crop yields for facilitating decisions regarding cultivation and management during growing season. Numerous data mining algorithms have been developed to support research yield forecasting. In this study, a systematic literature review (SLR) was conducted on published between 2016 2021 investigate use A total 261 relevant studies were identified from five electronic databases, out which 15 selected further analysis based inclusion exclusion criteria. thoroughly examined, their methods features analyzed, provide suggestions future research. results showed that evapotranspiration, temperature, precipitation, soil type most commonly used forecasting, while RMSE, MSE, MAE, R2 evaluation parameters. challenges include selecting appropriate input variables, handling missing outliers, capturing non-linear relationships variables. authors discuss various techniques such as feature selection, regularization, imputation, learning, preprocessing, augmentation address these challenges. Support Vector Machine, Linear Regression, Artificial Neural Network (ANN), Long-Short Term Memory (LSTM) models.