Review of Deep Learning in Agriculture and Smart Farming

  • Gayatri. K, Srikanth Yadav.M, Kedar Nadh Ragam, Chittibabu Ravela
Keywords: Agriculture, Convolutional Neural Networks, Deep Learning, Recurrent Neural Networks, Smart Farming

Abstract

New and sophisticated, Deep Learning is an up-and-coming new technology with tremendous potential for image processing and data analysis. For this reason, deep learning has now spread into the realm of agriculture. In this article, we explain the many agricultural issues that were examined and the models and systems used, as well as the design and pre-processing of the data used and the results that were discovered by measuring the functions involved. Furthermore, we look at deep learning and other standard classification and regression techniques. Our findings show that deep learning outperforms standard image processing methods in terms of accuracy. However, using an advanced picture recognition technique and massive data mining is required for deep learning. The current deep learning method has been applied to many different areas of study, such as agriculture. The purpose of this article is to provide the reader with an in-depth analysis of various deep learning approaches that are used to a wide range of agricultural problems, such as disease detection and identification, plant and fruit categorization, and seed counting. In addition, the study explores future interaction with autonomous robot platforms by exploring alternative models, data sources, the output of each design, the equipment utilized, and the practicality of implementation in real-time. Using deep learning, the researchers found that deep learning provides accurate results, with exceptions.

Published
2021-09-06
How to Cite
Kedar Nadh Ragam, Chittibabu Ravela, G. K. S. Y. (2021). Review of Deep Learning in Agriculture and Smart Farming. Design Engineering, 10879-10887. Retrieved from http://www.thedesignengineering.com/index.php/DE/article/view/4089
Section
Articles