The Digital Agricultural Revolution

Innovations and Challenges in Agriculture through Technology Disruptions

Roheet Bhatnagar, Nitin Kumar Tripathi, Nitu Bhatnagar, Chandan Kumar Panda, Roheet Bhatnagar, Nitin Kumar Tripathi, Nitu Bhatnagar, Chandan Kumar Panda

• Éditeur: Wiley-Scrivener
• Année: 2022
• ISBN:
  9781119823445
• Édition: 1
• Sujet: Computer Science
• Sous-sujet: Artificial Intelligence (AI) & Semantics

THE DIGITAL AGRICULTURAL REVOLUTION

The book integrates computational intelligence, applied artificial intelligence, and modern agricultural practices and will appeal to scientists, agriculturists, and those in plant and crop science management.

There is a need for synergy between the application of modern scientific innovation in the area of artificial intelligence and agriculture, considering the major challenges from climate change consequences viz. rising temperatures, erratic rainfall patterns, the emergence of new crop pests, drought, flood, etc. This volume reports on high-quality research (theory and practice including prototype & conceptualization of ideas, frameworks, real-world applications, policy, standards, psychological concerns, case studies, and critical surveys) on recent advances toward the realization of the digital agriculture revolution as a result of the convergence of different disruptive technologies.

The book touches upon the following topics which have contributed to revolutionizing agricultural practices.

• Applications of Artificial Intelligence in Agriculture (AI models and architectures, system design, real-world applications of AI, machine learning and deep learning in the agriculture domain, integration & coordination of systems and issues & challenges).
• IoT and Big Data Analytics Applications in Agriculture (theory & architecture and the use of various types of sensors in optimizing agriculture resources and final product, benefits in real-time for crop acreage estimation, monitoring & control of agricultural produce).
• Robotics & Automation in Agriculture Systems (Automation challenges, need and recent developments and real case studies).
• Intelligent and Innovative Smart Agriculture Applications (use of hybrid intelligence in better crop health and management).
• Privacy, Security, and Trust in Digital Agriculture (government framework & policy papers).
• Open Problems, Challenges, and Future Trends.

Audience

Researchers in computer science, artificial intelligence, electronics engineering, agriculture automation, crop management, and science.

1
Scope and Recent Trends of Artificial Intelligence in Indian Agriculture

X. Anitha Mary¹, Vladimir Popov^2,3, Kumudha Raimond⁴, I. Johnson⁵ and S. J. Vijay^6*

¹Department of Robotics Engineering, Karunya Institute of Technology and Sciences, Coimbatore, Tamil Nadu, India

²Additive Manufacturing, Technion-Israel Institute of Technology, Haifa, Israel

³Ural Federal University, Ekaterinburg, Russia

⁴Department of Computer Science and Engineering, Karunya Institute of Technology and Sciences, Coimbatore, Tamil Nadu, India

⁵Department of Plant Pathology, TamilNadu Agricultural University, Coimbatore, India

⁶Department of Mechanical Engineering, Karunya Institute of Technology and Sciences, Coimbatore, Tamil Nadu, India

Abstract

Agriculture is the economic backbone of India. About 6.4% of the total world’s economy relies on agriculture [1]. Automation in agriculture is the emerging sector as there is an increase in food demand and employment. The traditional ways used by farmers are not sufficient to fulfill the demands and it is high time that newer technologies are implementing in the agricultural sector. Artificial Intelligence (AI) is one of the emerging and promising technologies where intelligence refers to developing and utilizing human-level thinking machines through learning algorithms programmed to solve critical problems. Artificial Intelligence plays an important role in supporting agriculture sectors with the objectives of boosting productivity, efficiency, and farmers’ income. This chapter focuses on how AI helps in increasing the socioeconomic and environmental sustainability in the Indian agricultural sector. Also, it highlights the AI practices in India incorporated by farmers having small and medium-size agricultural lands.

Keywords: Indian agriculture, Artificial Intelligence, farmers

1.1 Introduction

Artificial Intelligence (AI) is a broad field of computer science that focuses on creating intelligent machines that can accomplish activities that would normally need human intelligence. Although AI is a multidisciplinary field with many methodologies, advances in machine learning (ML) and deep learning (DL) [4] are causing a paradigm shift in nearly every sector of the IT industry.

One of the oldest occupations in the world is farming and agriculture. It has a significant impact on the economy. Climate variations also play an influence in the agriculture lifecycle. Climate change is a result of increasing deforestation and pollution, making it difficult for farmers to make judgments about which crop to harvest. Nutrient insufficiency can also cause crops to be of poor quality [37]. Weed control has a significant impact and can lead to greater production costs. The above traditional farming can be replaced by using modern technology with AI.

1.2 Different Forms of AI

Agriculture is extremely important, and it is the primary source of income for almost 58% of India’s population [2]. However, it lacks support and suffers from a variety of factors, such as groundwater depletion, erratic monsoons, droughts, plant diseases, and so on. To detect the relationship between influencing factors with crop yield and quality, a variety of tools and approaches have been identified. The impact of recent technological advancements in the field of AI is significant. Recently, large investors have begun to capitalize on the promise of these technologies for the benefit of Indian agriculture. Smart farming and precision agriculture (PA) are ground-breaking science and technological applications for agriculture growth. Farmers and other agricultural decision makers are increasingly using AI-based modeling as a decision tool to increase production efficiency.

Artificial Intelligence is silently entering Indian agriculture and impacting society to a greater extent. There are three forms of AI, namely Artificial Narrow Intelligence (ANI), Artificial General Intelligence (AGI), and Artificial Super Intelligence (ASI) [3] as shown in Figure 1.1 Artificial Narrow Intelligence as the name suggests uses computer programming to do a specific task. Artificial General Intelligence refers to a machine that can think like a human and perform huge tasks. Artificial Super Intelligence is designed to think beyond humans. Artificial Narrow Intelligence is mainly used in agriculture to do some specific tasks, such as identification of diseases in leaf, optimization in irrigation, the optimal moisture content in crops, and so on, using AI techniques. The different forms of AI are shown in Figure 1.1.

Figure 1.1 Different forms of AI [3].

1.3 Different Technologies in AI

There are many subfields, such as ML, Artificial Neural Network (ANN), and DL, as shown in Figure 1.2. The distinguishing features of these subfields are shown in Table 1.1.

Figure 1.2 AI versus ML versus ANN versus DL.

Table 1.1 Distinguishing feature of subfields of AI.

AI	AI is a technology that allows us to build intelligent systems that mimic human intelligence.
ML	ML is an AI discipline that allows machines to learn from previous data or experiences without having to be explicitly programmed.
ANN	ANN depends on algorithms resembling the human brain.
DL	DL algorithms automatically build a hierarchy of data representations using the low- and high-level features.

1.3.1 Machine Learning

A subset of AI focuses on algorithm development by learning from experience and helps in the improvement of decision making with greater accuracy. The categories and the corresponding tasks are shown in Figure 1.3. Supervised, unsupervised, and reinforcement are the three main learning paradigms. Supervised is the most prevalent training paradigm for developing ML models for both classification and regression tasks [27]. It finds the relationship between the input and target variables. Some of the supervised learning algorithms are support vector machine (SVM), logistic regression, Decision Tree (DT), random forest, and so on. Unsupervised learning is often used for clustering and segmentation tasks. This method does not require any target variable to group the input data sets. Some of the examples are K-means, hierarchical, density, grid clustering, and so on. Reinforcement learning corresponds to responding to the environment and deciding the right action to complete the assignment with maximum reward in a given application. It finds its applications in a real-time environment.

Figure 1.3 Types of machine learning.

Figure 1.4 Generic methodology in building a model using machine learning algorithms.

In ML, training is performed with a huge amount of data to get accurate decisions or predictions. The general steps involved in building an ML model are shown in Figure 1.4.

1.3.1.1 Data Pre-processing

It is a process of converting raw data into a usable and efficient format.

1.3.1.2 Feature Extraction

Before training a model, most applications need first transforming the data into a new representation. Applying pre-processing modifications to input data before presenting it to a network is almost always helpful, and the choice of pre-processing will be one of the most important variables in determining the final system’s performance. The reduction of the dimensionality of the input data is another key method in which network performance can be enhanced, sometimes dramatically. To produce inputs for ...