Deep Learning Applications in Agriculture: The Role of Deep Learning in Smart Agriculture

Deep Learning Applications in Agriculture: The Role of Deep Learning in Smart Agriculture

Hari Kishan Kondaveeti (VIT-AP University, Andhra Pradesh, India), Gonugunta Priyatham Brahma (VIT-AP University, Andhra Pradesh, India) and Dandhibhotla Vijaya Sahithi (VIT-AP University, Andhra Pradesh, India)
DOI: 10.4018/978-1-7998-1722-2.ch020
OnDemand PDF Download:
Available
$37.50
No Current Special Offers
TOTAL SAVINGS: $37.50

Abstract

Deep learning (DL), a part of machine learning (ML), comprises a contemporary technique for processing the images and analyzing the big data with promising outcomes. Deep learning methods are successfully being used in various sectors to gain better results. Agriculture sector is one of the sectors that could be benefitted from the deep learning techniques since the current agriculture techniques cannot keep up with the rapid growth in population. In this chapter, the recent trends in the applications of deep learning techniques in the agricultural sector and the survey of the research efforts that employ deep learning techniques are going to be discussed. Also, the models that are implemented are going to be analyzed and compared with the other existing models.
Chapter Preview
Top

Introduction

Agriculture does not only provide a livelihood to the people, but also contributes significantly towards the national income, and therefore, national development. Agricultural products when processed and exported, provide a very valuable source of foreign exchange. The money so generated helps a lot with the development of a country, ensures the stability of the country’s currency, and gives the nation a veritable tool for importation. Agricultural products that are consumed have been the main sustenance of the human race since time immemorial. Since hardly anyone can stay without eating for several days, the role of agriculture in global civilization cannot be overemphasized. Yet the rapid, continuous increase in the human population will lead the world to face a severe catastrophe: food shortage and unprecedented hunger. According to some researchers, by the year 2050, it is assessed that the global population is going to exceed 9.5 billion (Alexandratos & Bruinsma, 2012). In such a case, food production has to be increased by two times to meet the growing demands of the population. In the meantime, the constraints like global warming and urbanization will make increasing the food production problematic. Global warming is drying up previously fertile ground, rendering them unproductive while making planning more difficult in the face of weather and seasons unpredictability. Urbanization has taken over agricultural lands, converting them into cities, and abysmally reducing available land for agriculture. This makes commercial agriculture difficult and reduces8 to a big extent total agricultural output.

Moreover, the collective effects of changes in climate, scarcity of energy and water requires a drastic change in the present agricultural systems. Industrial wastes, unburnt carbon, and oil spillage have combined to contaminate our waters and deny the world of aquatic agricultural products while also poisoning lands, killing crops and other plants. Thus, there's a need to not only confront all of these problems but to also produce enough products to meet up with the food needs of an astronomically rising population. This is where Machine Learning (ML) can play an essential role to double the production rate. Machine learning in agriculture will usher in and augment current efforts in building smart agriculture. (Smart Agriculture is a concept of agriculture management that uses the latest technologies such as Global Positioning System, soil scanning, IoT, data processing, and management to improve the quantity and quality of agricultural products, production efficiency, and agricultural resources optimization).

Smart agriculture is crucial to confront the challenges of crop production, such as crop diseases, sustainability, food security, and environmental impact. Nowadays, the new concepts of deep learning algorithms have been proven to be highly accurate. Deep learning algorithms make inference for future uses by analyzing images and pictures from phenomenons of interest. It goes into an in-depth study of such phenomenons, studying their characteristics deep into their genetic makeup. These deep learning algorithms empower smart agriculture. There are various applications of these deep learning algorithms in agriculture, such as leaf classification, plant disease identification, yield approximation, weed detection, weather prediction, and soil moisture prediction. These applications are going to be discussed in this chapter by comparing and analyzing the deep learning procedures with the present techniques that are being used.

Key Terms in this Chapter

Minimum Support Price (MSP): Minimum support price is a guaranteed price, usually given by the government, on the products that are produced by the farmers.

TARBIL (Turkish Agricultural Monitoring and Information Systems): The Turkish Agricultural Monitoring and Information Systems is an information system built by the Turkish government in 2008 to provide parcel-based continuous agro-meteorological parameter prediction, yield monitoring for precision farming, and good agricultural practices support.

Database: It is a collection of information in a proper and tabulated structure, which can be in a machine-readable format accessible by a computer.

Semi-Supervised Learning: Semi-supervised learning aims at labeling a set of unlabelled data with the help of a small set of labeled data.

Neuron: An artificial neuron is a model of a neuron present in an animal brain that is perceived as a mathematical function.

Diseases: Diseases are abnormal conditions of a human, animal, or plant that results in discomfort or dysfunction.

Perceptron: these are machine learning algorithms that undertake supervised learning of functions called binary classifiers which decide whether or not an input, usually identified with a vector of numbers, belongs to a particular class.

Neural Network: An artificial neural network is based on a simplification of neurons in an animal brain which is a group of interconnected neurons.

Microprocessor: A microprocessor is an integrated circuit (IC) that contains all the functions of a central processing unit (CPU) of a computer.

Artificial Neural Network (ANN): Artificial neural networks (ANNs) are a type of computing system that is inspired by biological neural networks present in the animal brain.

Optimization: Optimization is the design and operation of a system or process to make it as good as possible in some defined sense, it is the action of making the best or most effective use of a situation or resource.

Monitoring: Monitoring is the act of keeping something under systematic review by observing and checking the progress or quality of that thing over a while.

Node: A node is a computer or some other device that is attached to a network.

Global Warming: The gradual increase in the overall temperature of the earth's atmosphere generally attributed to the greenhouse effect is known as global warming.

Efficiency: Efficiency is the degree to which a resource is utilized for the intended task.

Speech Recognition: Speech recognition is a process through which machines convert words or phrases spoken into a machine-readable format.

Pipelining: Pipelining is a technique where various instructions execute in an overlapping manner.

Prediction: Prediction is a forecast, a statement of what will happen in the future.

Plant Phenology: It is a study of the plant’s life cycle and how these will be affected by seasonal changes in the climate and environmental aspects.

Internet of Things (IoT): IoT is a network of real-world objects which consists of sensors, software, and other technologies to exchange data with the other systems over the internet.

Modeling: Modeling here refers to the representation of depth in a two-dimensional (2D) image.

Data Collection: The method of collecting and evaluating data on selected variables, which helps in analyzing and answering relevant questions is known as data collection.

Image Classification: Image classification is the process of categorizing and labeling groups of pixels or vectors within an image based on specific rules, it is the primary domain, in which deep neural networks play the most important role of image analysis.

Scalable Vector Graphics (SVG): It is a vector-based picture format that makes use of Extensible Markup language (XML) and which unlike other images/graphics formats such as PNG comes with support for interactivity and animation.

Triangulation: Triangulation is a process of identifying a point in a three-dimensional space given its projection on multiple images.

Unsupervised Learning: Unsupervised Learning aims at inferring the given unlabelled data using a different type of structures present in the data points.

Artificial Intelligence (AI): AI is a simulation of human intelligence through the progress of intelligent machines that think and work like humans carrying out such human activities as speech recognition, problem-solving, learning, and planning.

Parallax: Apparent change in the position of an object because the variation in the location of the viewer is known as parallax.

Crop Variety Selection Method (CVSM): Crop variety selection method is an algorithm for predicting the yield rate of a crop by selecting the best crop variety amongst many through a fair consideration of current and variable market prices.

Machine Learning (ML): Machine learning is an application of artificial intelligence (AI) that provides systems the ability to automatically learn and improve from experience without being explicitly programmed and in the process developing computer programs that can access data and use it to learn for themselves.

Detection Device: It is a tool for identifying concealed objects or information.

Precision Agriculture: It is a concept in farming management that observes, measures, and responds to field variability in crops by defining a decision support system (DSS) to maximize farm output while optimizing the use of farming resources.

Crop Yield: The total production of fruits from planted crops.

Sensors: It is a device or module, and its task is to identify the variations in its physical or electrical or other quantities and produces an output as a response to that change.

Probabilities: A probability refers to the precise likelihood of an event happening which is most often expressed in a number, between 0 and 1, that make an accurate prediction of the likely occurrence of a certain event.

Supervised Learning: Supervised learning aims at developing a function for a set of labeled data and outputs.

Blob Recognition: Blob recognition is a process in computer vision that is used to recognize a specific region in an image that differs from its surroundings in some properties such as brightness or color.

Robot: A computer-programmed, self-aware machine built to carry out complex tasks or a group of tasks.

Algorithm: An algorithm is an ordered, accurate step-by-step process for a problem that provides a solution in a finite number of steps and that is unambiguous.

GPS: A global positioning system is a satellite navigation system used to determine the ground position, which is the geographical location, of an object.

Clusters: A cluster is a group of data objects which have similarities among them. It's a group of the same or similar elements gathered or occurring closely together.

Irrigation: It is the process of providing water to land that in turn assists in the production of crops.

Complete Chapter List

Search this Book:
Reset