IoT and AI in Agriculture

Abstract

Agriculture and food production systems face the common challenge of achieving all 17 sustainable development goals (SDGs).To achieve the SDGs, the Tsukuba Conference (TC) and Tsukuba Global Science Week (TGSW) organize global platforms to determine future policy challenges.This book is the outcome of our yearly efforts to address agricultural challenges, new developments to address climate change, and increased food production to meet global demands.Investing in the agricultural sector can address not only hunger and malnutrition but also other challenges, including poverty, water and energy use, climate change, and unsustainable production and consumption.To increase agricultural productivity, artificial intelligence (AI), machine learning (ML), and deep learning (DL) have led to the development of new prediction strategies for crop production, livestock development, and fisheries from pre-harvest to post-harvest levels.These digital innovations contribute to achieving the SDGs and Society 5.0.In this book, Chap. 1 reviews the current digital innovations in agri-food systems and aligns them with their contributions toward achieving the SDGs and Society 5.0.Chapter 2 briefly describes current trends and digital innovations in mechanization and automation in smart agriculture.In Chap.3, the authors present how farmers adopt strategies involving the use of agricultural machines such as combine harvesters for early harvests and the use of postproduction methods to counter fluctuations in crop production due to changing weather conditions.Chapter 4 further explains the appropriate agricultural mechanization scale for Southeast Asian countries.The various agricultural mechanization scales throughout the region and the current trends in agricultural mechanization and automation are also explained in this chapter.Recent trends in automation include advanced sensors and actuators.The cost and availability of these technologies has made them more attractive for developing navigation platforms using light detection and ranging (LiDAR), global navigation satellite system (GNSS), and vision sensors.The application of sensors with the development of algorithms is described in this book.Some of the key problems and labor shortage areas are highlighted.Among them, the transportation of agricultural products from farms to consumers is particularly challenging.Therefore, Chap. 5 of vi this book discusses a small-scale navigation system of mobile robots to carry and deliver agricultural products using a combination of a Kalman filter, fuzzy control, and LiDAR techniques.Furthermore, Chap.6 reviews the literature that has illustrated the potential of LiDAR for navigation systems in pesticide spraying vehicles in orchards.Since GPS and machine vision are easily influenced and limited by the environment, LiDAR was selected as the only sensor in this study, the planning paths were calculated via the density-based spatial clustering of applications with noise (DBSCAN), K-means, and random sample consensus (RANSAC) algorithms based on tree locations, and the vehicle was guided to follow the path.The feasibility of the system was proven by testing concrete roads and facilitated artificial-treebased orchards.With the aging of agricultural drivers worldwide, the safety risks associated with driving agricultural machinery have increased.Therefore, it is necessary to establish a stable, reliable, and effective system to ensure the safety of agricultural drivers.Thus, Chap.7 elaborates on the application of AI to identify and classify drivers' actions while driving to determine dangerous behaviors and consequently provide an early warning signal to ensure driving safety.This research utilizes deep learning algorithms to determine dangerous driving behaviors to provide early warning signals to prevent accidents.Chapter 8 discusses the development of an autonomous agricultural vehicle based on stereo simultaneous localization and mapping (SLAM) for indoor e