Applications of Deep Learning in Agriculture

Applications of Deep Learning in Agriculture

Padmesh Tripathi, Nitendra Kumar, Mritunjay Rai, Ayoub Khan
DOI: 10.4018/978-1-6684-5141-0.ch002
OnDemand:
(Individual Chapters)
Available
$33.75
List Price: $37.50
10% Discount:-$3.75
TOTAL SAVINGS: $3.75

Abstract

Today's era is the era of technologies. Technologies have widely been employed in each and every field. The field of agriculture is not untouched with the technologies, and in several segments of agriculture; it has been employed at large. Deep learning techniques and its variants like convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial network (AGN), and their various subcategories like AlexNet, ImageNet, visual geometry group (VGG), etc. have widely been employed in many sectors of agriculture in order to increase the quality and quantity of production. In this chapter, some applications of deep learning have been explored.
Chapter Preview
Top

Introduction

Smart Farming

With the applications of technologies in agriculture, the term smart farming has emerged. Though, the majority of farmers is not aware with this term as they are not familiar with the technologies being used. But, the future of agriculture lies in the technology based farming. Smart farming talks about the applications of technologies like location systems, internet of things, robots, sensors, artificial intelligence, etc. in farming. Using these technologies, a farmer can increase both the quantity and quality of crops (Tyagi, 2016).

Smart farming/agriculture is a technology that depends on its employment on the application of artificial intelligence (AI) and internet of things (IoT) in cyber-physical farm management (Bacco et al., 2019). Smart farming talks of many issues associated with the crop production like observing the changes of climate factors, soil moisture (Kumar et al., 2021), soil characteristics, etc. IoT technology is able to link various remote sensors such as ground sensors, robots, and drones, as this technology allows devices to be linked together using the internet to be operated automatically (AlMetwally et al., 2020). IoT based Smart farming technology are beneficial in improvement of product quality, irrigation and plant protection, disease prediction, fertilization process control, etc. (Adamides et al., 2020). With the applications of IoT, all the agricultural equipment and devices are connected together to take precise decisions infertilizer supply and irrigation (Kumar and Periasamy, 2021). Darwin et al. (2021) have surveyed the applications of deep learning in smart farming.

Some technologies applied in farming are listed below:

  • Location systems – GPS, satellites, etc.

  • Sensors – for light soil, moisture, water, temperature management, etc.

  • Robots - for spaying the pesticides

  • Drone cameras – for monitoring the status of crops

  • Precise plant nutrition an precision irrigation

  • Software platforms

  • Optimization and analytics platforms

With the rising population worldwide, the rise in food production is essential. Not only food production is essential but also it is essential to maintain the availability and nutritional quality worldwide. Smart farming is essential to deal with the challenges encountered in agricultural production in terms of productivity, food security, environmental impact, and sustainability (Gebbers and Adamchuk, 2010).

A report of the Food and Agriculture Organization (FAO 2017) revealed that approximately 20–40% of crops are lost per annum due to pests and diseases and as a result of lack of good monitoring of the state of the crop. Hence, the use of smart farming technologies allows monitoring of weather factors, fertility status, and also determining the exact amount of fertilizers necessary for crop growth.

Complete Chapter List

Search this Book:
Reset