Ecology, Environment and Conservation Paper

FERTILIZER TYPE AND QUANTITY RECOMMENDATION TOINCREASE OILSEED CROPS YIELD PREDICTION WITH INORGANICFERTILIZERS USING MACHINE LEARNING ALGORITHMS

Mithra C. and A. Suhasini

Abstract

Agriculture contributes significantly to India’s economy. The most serious threat to food security ispopulation growth. Population growth increases demand, forcing farmers to produce more to increasesupply. Crop yield prediction technology can help farmers to increase their output. Optimal fertilizer doseare required for boosting oilseed crop yield cultivation. However, when nutrients are scarce or overfertilizationoccurs, yields are considerably lowered and the environmental burden is increased. To addressthese issues, our proposed work employs machine learning techniques in the prediction of crop yield usinginorganic fertilizer as well as the amount and type of agricultural fertilizer to be used for a specific crop invarious districts of Tamil Nadu. Actual yield data from 1961 to 2007 is used as a training set, and data from2008 to 2019 is used as a validation set. The results of the proposed algorithm are compared with those ofthe other machine learning algorithms namely random forest, linear regression, support vector machine,and naive bayes with an accuracy rate of 94%, 91.33%, 88.4% and 75.56% respectively are observed. Accordingto the study, random forest results outperform other algorithms for crop yield prediction, and the decisiontree algorithm works better for recommendation systems. The research also helps farmers by providing arecommendation system for determining which crop to plant and which type of inorganic fertilizer andhow much quantity of fertilizer to use in a specific area and time. The proposed study also seeks to examinedifferent observations for each method by changing parameters to see if the varying parameter influencesthe accuracy rate or not.