Crop yield prediction: two-tiered machine learning model approach

Nutrient deficiency analysis is essential to ensure good yield. The crop yield is dependent on the nutrient contents and drastically affects the health of the crop. In this paper the nutrient deficiency of a paddy crop is considered. Tensor Flow’s (Google’s Machine Learning Library) is used to build a neural network to classify them into nitrogen, potassium, phosphorous deficiencies or healthy independently. It is necessary to have an optimal balance between nitrogen, potassium and phosphorous content. Tensor Flow’s model identifies the deficiency using a set of images. The result is fed to “machine learning driven layer” to estimate the level of deficiency on a quantitative basis. It specifically makes use of k means-clustering algorithm. It is then evaluated through the rule-matrix to estimate the cropland’s yield. A fair prediction of 76–77% was observed with two tired machine learning models.