InteliCrop: A Machine Learning-based Group System for Crop Prediction

InteliCrop: A Machine Learning-based Group System for Crop Prediction

Spurthy S N¹, Assistant Prof. Venkatesh A²

¹ Student, Department Of Masters Of Computer Application, BMS Institute Of Technology And Management , Bangalore, Karnataka, India

² Assistant Professor, Department Of Masters Of Computer Application, BMS Institute Of Technology And    Management, Bangalore, Karnataka, India College

---------------------------------------------------------------------***---------------------------------------------------------------------

Abstract - The Voting Classifier ensemble approach is employed when suggested model to integrate the results of this separate algorithms and produce more precise predictions. Agricultural characteristics like temperature, rainfall, soil condition, and fertilisation comprised into the information set utilised for the study. The outcomes show that the ensemble model outperforms the individual algorithms in rapports of accuracy rates, demonstrating the effectiveness of the recommended strategy. The paper offers a workable solution for crop yield estimation and emphasises the potential of ML in agricultural prediction. Informed decisions on crop management and optimisation can be made by farmers and agricultural researchers without the assistance from proposed ensemble model.

Early crop output projection before to harvest is necessary for farmer to make multiple policy decisions regarding crop production to be capable of ensure food availability. The consequences of conventional methods are often only made public after harvest and rely on expensive, non-scalable survey data. The ensemble model for crop prediction presented in this paper makes use of the ML techniques include a Forest Classifier, logarithmic regression, and Gradient-Based Classifier techniques.

Key Words: machine learning, pyspark, crime identification, Crop prediction, Farming, environmental variables, Agriculture.