Open AccessA HYBRID APPROACH FOR CROP YIELD PREDICTION USING MACHINE LEARNING AND DEEP LEARNING ALGORITHMS
Author(s) -
Sonal Agarwal,
Sandhya Tarar
Publication year - 2021
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1714/1/012012
Subject(s) - machine learning , artificial intelligence , agriculture , algorithm , artificial neural network , deep learning , crop yield , python (programming language) , computer science , agricultural engineering , agronomy , engineering , ecology , biology , operating system
Agriculture is defined as the science and art of cultivating the flora and fauna. Farming in India is ranked as second around the globe and occupies 60.45% of Indian land. The Indian economy, dominatingly, depends upon farming along with agro-industry things. The soil ingredients (like Nitrogen, Phosphorous, Potassium), crop rotation, soil clamminess, atmospheric and surface temperature, precipitation, etc, play an efficient role in cultivation. The present evidence related to this field includes a model which is incorporated with ML algorithms (Random Forest, Decision Tree, Artificial Neural Network) to determine best crop. In this paper, the proposed model is enhanced by applying deep learning techniques and along with the prediction of crop, a clear information is achieved regarding the amounts of soil ingredients needed with their expenses separately. It provides a better accuracy than the existing model. It analyzes the given data and help the farmers in predicting a crop which in return help in gaining profits. The climatic and soil conditions of land are taken into consideration to predict a proper yield. The objective is to present a python based system that uses strategies smartly to anticipate the most productive reap in given conditions with less expenses. In this paper, SVM is executed as Machine Learning algorithm while LSTM and RNN are used as Deep Learning algorithms.