Abstract:

Agriculture is a developing topic of study. Crop prediction, in particular, is crucial in agriculture and is heavily reliant on soil and environmental factors such as rainfall, humidity, and temperature. Farmers used to be able to choose the crop to produce, watch its progress, and select when it might be harvested. Today, however, fast changes in environmental circumstances have made it impossible for farmers to continue in this manner. As a result, machine learning approaches have taken up the role of prediction in recent years, and this study has employed many of them to calculate crop production. To guarantee that a particular machine learning (ML) model operates with high accuracy, it is critical to use effective feature selection techniques to preprocess raw data into a Machine Learning friendly dataset. Only data characteristics that have a high degree of importance in defining the final output of the model must be used to eliminate redundancy and improve the accuracy of the ML model. As a result, optimum feature selection emerges to guarantee that only the most relevant characteristics are included in the model. Consolidating every single characteristic from raw data without considering their importance in the model-making process would unduly complicate our model. Furthermore, adding characteristics that contribute little to the ML model would raise its time and space complexity, affecting the model's output accuracy.

Description:

Agriculture, classification, crop prediction, feature selection.