Fuzzy Logic Based Hybrid Recommender of Maximum Yield Crop Using Soil, Weather and Cost

Our system is designed to predict best suitable crops for the region of farmer. It also suggests farming strategies for the crops such as mixed cropping, spacing, irrigation, seed treatment, etc. along with fertilizer and pesticide suggestions. This is done based on the historic soil parameters of the region and by predicting cost of crops and weather. The system is based on fuzzy logic which gets input from an Artificial Neural Network (ANN) based weather prediction module. An Agricultural Named Entity Recognition (NER) module is developed using Conditional Random Field (CRF) to extract crop conditions data. Further, cost prediction is done based on Linear Regression equation to aid in ranking the crops recommended. Using this approach we achieved an F-Score of 54% with a precision of 77% thus accounting for the correctness of crop production.