Ai Sensors And Robotics In Plant Phenotyping And Precision Agriculture Volume Ii

This Research Topic is part of the High-Throughput Field Phenotyping to Advance Precision Agriculture and Enhance Genetic Gain series. The discipline of “High Throughput Field Phenotyping” (HTFP) has gained momentum in the last decade. HTFP includes a wide range of disciplines such as plant science, agronomy, remote sensing, and genetics; as well as biochemistry, imaging, computation, agricultural engineering, and robotics. High throughput technologies have substantially increased our ability to monitor and quantify field experiments and breeding nurseries at multiple scales. HTFP technology can not only rapidly and cost-effectively replace tedious and subjective ratings in the field, but can also unlock the potential of new, latent phenotypes representing underlying biological function. These advances have also provided the ability to follow crop growth and development across seasons at high and previously inaccessible spatial and temporal resolutions. By combining these data with measurements of all environmental factors affecting plant growth and yield (“Envirotyping”), genotypic-specific reaction norms and phenotypic plasticity may be elucidated.

This new book delves into how modern technologies—i.e., global positioning systems (GPS), unmanned aerial vehicles (drones), image processing methods, artificial intelligence, machine learning, and deep learning—are being used to make agriculture more farmer-friendly and more economically profitable. The volume focuses on the use of smart sensors, actuators, and decision support systems to provide intelligent data about crop health and for monitoring for yield prediction, soil quality, nutrition requirement prediction, etc. The authors discuss robotic-based innovations in agriculture, soft computing methodologies for crop forecasting, machine learning techniques to classify and identify plant diseases, deep convolutional neural networks for recognizing nutrient deficiencies, and more.

Plant phenotyping (PP) describes the physiological and biochemical properties of plants affected by both genotypes and environments. It is an emerging research field that is assisting the breeding and cultivation of new crop varieties to be more productive and resilient to challenging environments. Precision agriculture (PA) uses sensing technologies to observe crops and then manage them optimally to ensure that they grow in healthy conditions, have maximum productivity, and have minimal negative effects on the environment. Traditionally, the observation of plant traits heavily relies on human experts which is labor intensive, time-consuming, and subjective. Automatic crop traits measurement in PP and PA are two different fields, but they share the same sensing and data processing technologies in many respects. Recently, driven by computer and sensor technologies, machine vision (MV) and machine learning (ML) have contributed to accurate, high-throughput, and nondestructive plant phenotyping and precision agriculture. However, these technologies are still in their infant stage and there are many challenges and questions related to them that still need to be addressed. The goal of this Research Topic is to provide a platform to share the latest research results on the application of MV and ML for PP and PA. It aims to highlight cutting-edge technologies, bottle-necks, and future research directions for MV and ML in crop breeding, crop cultivation, disease management, weed control, and pest control.

This collection considers the variety of applications of Artificial Intelligence in agriculture, highlighting its use in vineyards to improve precision irrigation, as well as its use in harvest-assist platforms in citrus orchards.

This book was created with the intention of informing an international audience about the latest technological aspects for developing smart agricultural applications. As artificial intelligence (AI) takes the main role in this, the majority of the chapters are associated with the role of AI and data analytics components for better agricultural applications. The first two chapters provide alternative, wide reviews of the use of AI, robotics, and the Internet of Things as effective solutions to agricultural problems. The third chapter looks at the use of blockchain technology in smart agricultural scenarios. In the fourth chapter, a future view is provided of an Internet of Things-oriented sustainable agriculture. Next, the fifth chapter provides a governmental evaluation of advanced farming technologies, and the sixth chapter discusses the role of big data in smart agricultural applications. The role of the blockchain is evaluated in terms of an industrial view under the seventh chapter, and the eighth chapter provides a discussion of data mining and data extraction, which is essential for better further analysis by smart tools. The ninth chapter evaluates the use of machine learning in food processing and preservation, which is a critical issue for dealing with issues concerns regarding insufficient foud sources. The tenth chapter also discusses sustainability, and the eleventh chapter focuses on the problem of plant disease prediction, which is among the critical agricultural issues. Similarly, the twelfth chapter considers the use of deep learning for classifying plant diseases. Finally, the book ends with a look at cyber threats to farming automation in the thirteenth chapter and a case study of India for a better, smart, and sustainable agriculture in the fourteenth chapter. This book presents the most critical research topics of today’s smart agricultural applications and provides a valuable view for both technological knowledge and ability that will be helpful to academicians, scientists, students who are the future of science, and industrial practitioners who collaborate with academia.

This book provides an overview of the innovations in crop phenotyping using emerging technologies, i.e., high-throughput crop phenotyping technology, including its concept, importance, breakthrough and applications in different crops and environments. Emerging technologies in sensing, machine vision and high-performance computing are changing the world beyond our imagination. They are also becoming the most powerful driver of the innovation in agriculture technology, including crop breeding, genetics and management. It includes the state of the art of technologies in high-throughput phenotyping, including advanced sensors, automation systems, ground-based or aerial robotic systems. It also discusses the emerging technologies of big data processing and analytics, such as advanced machine learning and deep learning technologies based on high-performance computing infrastructure. The applications cover different organ levels (root, shoot and seed) of different crops (grains, soybean, maize, potato) at different growth environments (open field and controlled environments). With the contribution of more than 20 world-leading researchers in high-throughput crop phenotyping, the authors hope this book provides readers the needed information to understand the concept, gain the insides and create the innovation of high-throughput phenotyping technology.