Ebooks

Artificial intelligence AI is a general purpose technology with significant implications for all aspects of society and everyday life. In different sectors, such as health care, manufacturing, automobile, finance and agriculture, AI technology is being applied in order to increase productivity and efficiency and overcome the usual challenges. Understanding intelligence so that it can be reproduced in machines is a prerequisite for the development of artificial intelligence. Most AI systems collect input, analyze this data and make decisions on the basis of these inputs. Embracing AI yields numerous positive outcomes and societal advantages. Its applications hold the potential to enhance living standards, promote health, facilitate judicial processes, foster economic prosperity, bolster public safety, and mitigate human impact on the environment and climate. AI acts as a valuable ally, empowering individuals to complete tasks with greater efficiency and effectiveness, leading to a multitude of advantages. Furthermore, AI goes beyond simply optimizing current tasks; it opens doors to new possibilities, such as analyzing vast research data sets, paving the way for groundbreaking scientific discoveries that could positively impact every aspect of our lives. In today's agriculture, drones and robots are like our high-tech helpers, wandering the fields and gathering data to make farming smarter. With the help of interconnected technologies and intelligent analytics, farmers can now comprehend what's occurring in real-time on their farms. They're learning how to grow more crops, use resources more efficiently, manage their farms better, and make eco-friendly choices about where and how to use those resources.This book has been prepared to provide comprehensive knowledge about role of robotics in horticulture including various topics viz., Artificial Intelligence, Crop and Soil Monitoring in Horticulture Crops, Robotics in Training and Pruning of Horticultural Crops, Role of AI in Diagnosis and Monitoring of Diseases and Insect Pests, Intelligent spraying in horticultural crops, Robotic Pollination in Horticultural Crops, Future Of AI In Horticultural Crops. All these techniques and their various applications have been thoroughly discussed in this book. This book provides a thorough understanding of these chapters and their role in the development of horticulture crops this book has been divided into seven thoroughly dealt chapters that provide all the novel information required.

1.1 Introduction Since the beginning of humankind, we have thrived as a species due to our unique capabilities. These skills have developed and progressed over the centuries to the point that, in recent decades, we have been able to build machines that can imitate our intelligence, as far as we comprehend it. A novel type of world may lie ahead of us. Artificial intelligence is the future, and the future is here." - Dave Waters Artificial intelligence (AI) refers to the replication of human intelligence in computers, which are programmed to think and behave in a manner similar to humans. Literacy, logic, problem-solving, perception, and linguistic appreciation are all manifestations of cognitive abilities. Artificial Intelligence refers to the development of computer systems, computer-controlled robots, or software that are designed to exhibit intelligent behavior similar to that of the human mind. The term artificial intelligence is composed of the word "Artificial," which denotes something created by humans rather than existing naturally, and "Intelligence," which refers to the capacity to gain and utilize knowledge and skills.AI is achieved by the analysis of patterns in the human brain and the evaluation of cognitive processes. The culmination of these studies leads to the creation of sophisticated software and systems with advanced intelligence. The term AI was coined by McCarthy et al. 2006 while working on Dartmouth summer research project in which they proposed that machines have the capability to emulate "every facet of learning or any other characteristic of intelligence."

2.1 Introduction Horticulture plays a pivotal role in global food production and is essential for ensuring food security and improving nutrition. However, the increasing pressure on agricultural resources, coupled with environmental challenges, necessitates the adoption of innovative technologies to enhance productivity and sustainability. Artificial Intelligence (AI) has emerged as a powerful tool in this regard, offering unprecedented capabilities in data analysis, pattern recognition, and decision-making. In horticulture, AI holds immense potential for revolutionizing crop and soil monitoring practices, enabling more efficient resource utilization and better management strategies. 2.2 Foundations of Ai in Crop and Soil Monitoring Artificial Intelligence (AI) forms the backbone of modern crop monitoring techniques, enabling the processing of vast amounts of agricultural data and the extraction of actionable insights. This section provides an in-depth exploration of the fundamental principles of AI, machine learning, and deep learning, elucidating their applications in crop monitoring within horticulture. 2.1.1 Understanding Artificial Intelligence (AI) Definition and Scope: AI refers to the development of computer systems capable of performing tasks that typically require human intelligence, such as learning, reasoning, and problem-solving. Types of AI: AI can be categorized into two broad types: narrow AI, which is designed for specific tasks, and general AI, which exhibits human-like intelligence across a wide range of domains. In the context of crop monitoring, narrow AI applications are more prevalent, focusing on tasks such as image recognition, predictive modeling, and decision support.

3.1 Training Virtual orchards are sophisticated, simulated environments used to train agricultural robots in a controlled, risk-free setting. These virtual landscapes replicate real-world orchards with high fidelity, incorporating detailed models of trees, fruits, branches, and various terrain features. By leveraging advanced technologies like 3D modelling, physics-based simulation, and machine learning, virtual orchards provide a comprehensive platform for developing and testing robotic algorithms without the logistical challenges and costs associated with field trials. In these simulations, agricultural robots can perform various tasks, such as navigating through rows of trees, detecting and localising fruits, and executing precise pruning actions (Shamshiri et al., 2018). The virtual environment allows for testing different path planning and control algorithms, enabling researchers to fine-tune these systems for optimal performance. Additionally, virtual orchards can simulate various environmental conditions, such as changing light levels, weather patterns, and the presence of obstacles, providing a robust testing ground for robots to adapt to dynamic scenarios. One significant advantage of virtual orchards is the ability to generate large amounts of training data for machine-learning models. Robots can be exposed to many pruning scenarios, enhancing their ability to generalize and perform effectively in real-world conditions. Furthermore, the use of virtual reality (VR) and augmented reality (AR) can aid in training human operators to control and supervise these robots, improving their proficiency and reducing the learning curve (Sarker, 2021).

4.1 Introduction Pests and plant diseases pose serious risks to global agriculture (Strange and Scott, 2005; Oerke, 2006). Plant diseases and pests are the natural disasters that can impede a plant’s normal growth throughout the plant’s whole life cycle, from seed formation to seedling growth and may result in plant death (Liu and Wang, 2021). Diseases reduce yields in a number of important crops by 21–30% globally (Savary et al., 2019), whereas insect infestations reduce crop output by 30–33% annually (Kumar et al., 2019). For the management, accurate disease diagnosis and pest identification are essential. Artificial intelligence (AI) techniques can be a crucial addition to enable the monitoring of plant diseases and pests at a coarse scale, as traditional field scouting of these pests and diseases is labor-intensive, subject to bias, and typically shows low efficiency (Mahlein, 2016). Agriculture is undergoing a revolution because of artificial intelligence (AI), which is replacing outdated techniques with more effective ones (Talaviya et al., 2020). AI intervention in agriculture is helping farmers increase productivity and reduce adverse environmental effects (Sujawat, 2021). The application of AI techniques has created new opportunities for scientific research as well as new instruments and ways for handling and analyzing vast volumes of data. An important benefit of AI is its capacity to spot patterns in data that are not immediately obvious or available to humans. This allows for previously unattainable new insights and discoveries (Angermueller et al., 2016; Eraslan et al., 2019). AI is currently changing how we work and live, yet its influence on pathology and entomology research is still underappreciated. AI’s cost-effectiveness, precision, quickness of performance, and adaptability are its core concepts in agriculture (Eli-Chukwu, 2019). In agriculture, artificial intelligence not only helps farmers use their abilities, but it also guides them to obtain better quality and larger yields with fewer resources (Khandelwal and Chavhan, 2019). AI-based technology addresses the issues that agricultural sector faces and helps to increase efficiency in all areas. These challenges include crop harvesting, irrigation, soil content sensitivity, crop monitoring, weeding, harvesting, and establishing.

5.1 Introduction The application of chemical pesticides is crucial in horticultural production, but it is also one of the most hazardous agricultural operations. Overapplication can lead to significant environmental concerns. Spraying is vital for reducing harvest losses and improving productivity. According to Cho et al.,(2012), 30-35% of production damages can be prevented by reducing harmful insects and diseases through spraying. Plant protection is essential for ensuring yield quantity and quality. Effective pesticide use is crucial, as excessive application can lead to pests developing immunity, destruction of beneficial insects and natural pest enemies, and increased harmful insect populations. Excessive pesticide use also disrupts pollination, preventing fruit formation. The method of pesticide application is key to targeting the correct quantity and quality, reducing environmental contamination, and increasing sustainability (Abbas et al., 2020). Site-specific application rates in precision horticulture can decrease pesticide use. Only 30-40% of pesticides typically reach their targets, with most lost to the environment, contaminating workers and causing pollution. Protecting plants with chemicals aims to prevent infections and ensure healthy growth. Spray drift can harm non-target plants and contaminate watercourses, posing a severe and costly problem for horticultural farmers using air-assisted variable sprayers (Seol et al., 2022). Spray drift refers to airborne spray droplets moving beyond the intended application area from aerial or ground-based methods. Studies have found that a significant portion of pesticides is lost to the air and ground, with up to 30-50% of the applied pesticides being lost through various means (Abbas et al., 2020). Modern trends emphasize the importance of sensors and precision agriculture for effective pesticide use. Understanding tree canopy physical features is crucial for effective spray application. This study focuses on recognizing and geometrically classifying canopies for adequate pesticide protection. Variable rate spraying targets only the canopy, enhancing pesticide application efficiency (Rathnayake et al., 2022). Electronic methods and innovative equipment reduce operational and environmental costs. Sensors tracking canopy characteristics and spacing ensure optimal use of inputs, promoting sustainability.

6.1 Introduction Perennial crops are crucial for maintaining food security, despite making up only 4.2–4.7% of all agricultural acreage (Kreitzman et al., 2020). The value of fruit and nut production reached a value of USD 823 billion globally in 2020, with the top five fruit crops being apples (87 Mt), oranges (78 Mt), grapes (77 Mt), mangoes (55 Mt), and apricots (41 Mt) (Statista, 2020). The tree nut business is growing quickly, although making up a smaller share of the world’s agricultural output. Global tree nut output is expected to reach 4.2 Mt in 2019–2020, with almonds, cashews, walnuts, hazelnuts, and pistachios accounting for 31%, 17%, 21%, 12%, and 14% of the nut market share, respectively (Serna, 2020). Tree crops require a longer investment period before producing a commercial yield; sweet cherry takes three years to attain a commercial yield, while pistachio takes ten (Rezaei et al., 2019). High-density monocultures of cultivars chosen for their potential yield, fruit quality, and disease resistance are part of optimal tree crop production techniques. These monocultures are maintained under intensive, high-input farming systems (Simon et al., 2017). However, inadequate pollination can seriously impair the quantity and quality of these agricultural products, prompting for meticulous dedication to pollination research and management (Bosch et al., 2021; Forbes et al., 2019). Effective pollination, and on the contrary, situations in which pollination is restricted or deficient, depend on both internal and external factors (Figure 7.1, Table 7.1). The period of stigma receptivity, the lifespan of the ovule, and the quality and availability of compatible, suitable pollen are all considered as intrinsic factors (Howlett et al., 2015). Agronomic methods pertaining to plant nutrition, orchard layout, pest and disease control, pollinator activity, pollen quality, and weather patterns and their effects on flowering synchrony are examples of extrinsic factors(Toledo-Hernandez et al., 2017). Hatfield and Prueger assert that pollination is one of the phenological stages that is most sensitive to temperature, and as such, it has a significant impact on productivity (Hatfield and Prueger, 2015). Climate has been shown to be a key factor in determining pollination success and production in crops including peaches, apples, and almonds.

7.1 Introduction Artificial intelligence (AI) is the imitation of human intellect in machines designed to emulate human activities and cognitive functions. These machines are designed to accomplish tasks that normally require human intellect, such as learning, problem solving, perception, and decision-making (Zhang et al., 2022). Horticultural crops, including fruits, vegetables, nuts, and ornamental plants, are of paramount importance in global agriculture, as they contribute significantly to food security, economic prosperity, and environmental sustainability. Nevertheless, the cultivation of these crops poses numerous challenges for growers, such as fluctuating market demand, insufficient resources, unpredictable climate conditions, and the constant threat of pests and diseases (Nowak & Grant, 2018). In recent years, the agricultural sector has experienced a significant shift owing to advancements in Artificial Intelligence (AI) technologies (Liakos et al., 2018). AI has emerged as a powerful tool for the cultivation of horticultural crops, providing solutions for boosting productivity, sustainability, and efficiency (Shrivastava & Kumar, 2021). By utilizing AI, horticulturists can overcome the traditional challenges associated with crop management, resource allocation, and environmental sustainability, paving the way for a more resilient and productive agricultural sector (Garg et al., 2019). The integration of AI into horticultural crop production encompasses a diverse range of applications, including precision agriculture, crop monitoring and management, predictive analytics, automated harvesting, and genetic improvement (Golhani et al., 2018). These applications leverage machine learning algorithms, remote sensing technologies, and data analytics to analyze vast amounts of agricultural data ranging from soil composition and weather patterns to crop health and market trends (Araus& Cairns, 2014). Through intelligent data-driven insights, AI enables farmers to make informed decisions in real-time, optimize resource utilization, minimize waste, and maximize yields (Kamilaris et al., 2017). This technological convergence offers promising prospects for food production, enabling stakeholders to explore new avenues for growth, resilience, and sustainability in horticultural crop cultivation (Mohanty et al., 2016).

A AI in Disease Diagnosis 104, 106  AI in Yield Forecasting 104, 106 Artificial Intelligence (AI) 3, 4, 5, 6, 8, 14, 19, 20, 24, 49, 50, 51, 52, 55, 58, 99, 100, 101   Automation 7, 8, 37, 70, 71, 92, 102  B Bias 21, 50, 106 C Crop Health 7, 8, 9, 24, 27, 30, 71, 100, 101, 104  Crop yield 10, 14, 22, 23, 26, 30, 70, 71, 73, 101, 104 Climate Change 8, 9, 93, 101, 102   Computer Vision 4, 5, 6, 10, 19, 41, 51, 57, 71, 99, 101, 102, 103, 104, 105, 106    Cloud Computing 7 D Data Analysis 20, 24, 67, 74   Deep Learning 2, 3, 8, 9, 11, 20, 21, 23, 29, 41, 45, 50, 51, 55, 56, 57, 69, 100, 103, 104       Disease Detection 21, 26, 27, 49, 52, 55, 57, 100, 106   Drones 1, 7, 9, 72, 73, 74, 87, 92, 100,  101, 103, 104, 105