Agricultural Internet of Things and Decision Support for Precision Smart Farming

Annamaria Castrignano,Gabriele Buttafuoco,Raj Khosla,Abdul Mouazen,Dimitrios Moshou,Olivier Naud

• Editorial: Academic Press
• Año: 2020
• ISBN:
  9780128183748
• Categoría: Betriebswirtschaft
• Categoría: Agribusiness

Agricultural Internet of Things and Decision Support for Smart Farming reveals how a set of key enabling technologies (KET) related to agronomic management, remote and proximal sensing, data mining, decision-making and automation can be efficiently integrated in one system. Chapters cover how KETs enable real-time monitoring of soil conditions, determine real-time, site-specific requirements of crop systems, help develop a decision support system (DSS) aimed at maximizing the efficient use of resources, and provide planning for agronomic inputs differentiated in time and space. This book is ideal for researchers, academics, post-graduate students and practitioners who want to embrace new agricultural technologies.

• Presents the science behind smart technologies for agricultural management
• Reveals the power of data science and how to extract meaningful insights from big data on what is most suitable based on individual time and space
• Proves how advanced technologies used in agriculture practices can become site-specific, locally adaptive, operationally feasible and economically affordable

Chapter 1

Introduction to agricultural IoT

Lucio Colizzi ¹ , Danilo Caivano ¹ , Carmelo Ardito ¹ , Giuseppe Desolda ¹ , Annamaria Castrignanò ^{2 , 3} , Maristella Matera ⁴ , Raj Khosla ⁵ , Dimitrios Moshou ⁶ , Kun-Mean Hou ⁷ , François Pinet ⁸ , Jean-Pierre Chanet ⁸ , Gao Hui ⁹ , and Hongling Shi ^{9 1} Computer Science Department, University of Bari Aldo Moro, Bari, Italy ²Council for Agricultural Research and Economics, Bari, Italy ³ National Research Council of Italy, Water Research Institute, Bari, Italy ⁴ Dipartimento di Elettronica, Informazione e Bioingegneria (DEIB), Politecnico di Milano, Milano, Italy ⁵ Department of Soil & Crop Sciences, Colorado State University, Fort Collins, CO, United States ⁶ Agricultural Engineering Laboratory - Faculty of Agriculture, Aristotle University of Thessaloniki, Thessaloniki, Greece ⁷ ISIMA, LIMOS, University of Clermont-Ferrand, Aubière, France ⁸ Irstea - Centre de Clermont-Ferrand - UR TSCF, Aubière, France ⁹ University Clermont Auvergne, LIMOS UMR 6158 CNRS, France

Abstract

Significant challenges will have to be overcome to achieve the level of agricultural productivity necessary to meet the predicted world demand for food, feed, fibre and fuel in 2050. Although agriculture has met significant challenges in the past, targeted increases in productivity will have to be made by 2050, in the face of stringent constraints including limited resources, less skilled labour, limited amount of arable land and changing climate, among others. Currently, agriculture production accounts for over 70% of freshwater consumption and unsustainable levels of chemical consumption for crop production. In the hyperconnected world, where people, computers and physical objects cooperate to solve complex tasks, a big amount of data and information rises rapidly and a critical aspect is to manage that knowledge to make the right decision at the right time and the right place. Also, farming has to become SMART adopting a new vision of the primary production sector where the development processes are based on the integration of information and communications technologies and Internet of Things technologies in a secure fashion to manage the rural assets and optimization of agronomic inputs such as water, fertilizer, agrochemical or soil tillage and to enhance input use efficiency, output or production and profitability in a sustainable manner. In this vision, the land becomes a substrate where different kinds of sensors could acquire heterogeneous data. Those sensors are connected in a sort of rural network in turn linked to the Internet network. The real-time streaming data are stored in complex database containing all the necessary knowledge about the land characteristics. Intelligent programmes connected with the knowledge base run to make real-time decisions, sending acting messages to the domotic back-end system or suggestions to the farmer.

Keywords

Arduino; Internet of things; Open source platform; Raspberry pi; Sensors; Smart farming; Smart object

1. 1.1 Introduction section: an integrated view on precision smart farming from a multidisciplinary perspective
   1. 1.1.1 Internet of things architectures and paradigms
      1. 1.1.1.1 Physical devices and controllers
      2. 1.1.1.2 Connectivity
      3. 1.1.1.3 Edge computing or cloud computing
      4. 1.1.1.4 Data accumulation
      5. 1.1.1.5 Data abstraction
      6. 1.1.1.6 Application layer
      7. 1.1.1.7 Collaboration and processes
   2. 1.1.2 Open source internet of things platforms
      1. 1.1.2.1 Arduino
      2. 1.1.2.2 The solenoid valves
      3. 1.1.2.3 Relay
      4. 1.1.2.4 Moisture sensor
      5. 1.1.2.5 Rainfall sensor
   3. 1.1.3 From an object to a smart object
      1. 1.1.3.1 State of the art of smart objects
      2. 1.1.3.2 State of the art of cognitive techniques
      3. 1.1.3.3 State of the art of smart objects platform
      4. 1.1.3.4 Smart object platform and use cases
      5. 1.1.3.5 Smart object interoperability
   4. 1.1.4 Developing internet of things applications
2. References
3. Further reading

1.1. Introduction section: an integrated view on precision smart farming from a multidisciplinary perspective

According to the recent report by FAO, the world's population will surpass 9.0 billion people by year 2050 (FAO, 2009). Significant challenges will have to be overcome to achieve the level of agricultural productivity necessary to meet the predicted world demand for food, feed, fibre and fuel in 2050. Although agriculture has met significant challenges in the past, targeted increases in productivity will have to be made by 2050, in the face of stringent constraints including limited resources, less skilled labour, limited amount of arable land and changing climate, among others. For most of the 20th century, many key factors influenced increases in the rate of crop production, primarily mechanization, improved genetics and increased use of inputs. However, such increase in crop production came at a cost of overapplication of various agricultural inputs, i.e., irrigation, nutrients and pesticides. The use of resource-intensive, high-input agriculture around the world led to depletion of soils, water scarcity, widespread deforestation and high levels of greenhouse gas emissions (FAO, 2017; NASEM, 2019 ). Currently, agriculture production accounts for over 70% of freshwater consumption and unsustainable levels of chemical consumption for crop production. Hence, sustainability in agriculture is a must that is becoming a need due not only to the scarceness of natural resources and the growth of population but also for the growing attention deserved to well-being and green lifestyle. Agriculture needs to provide effective solutions to old and new challenges to embrace the insights from other disciplines and use them in an integrated way.

Precision agriculture (PA) presents itself as one among many solutions to the grand challenges that agriculture and our world are currently facing. PA has been around for the past three decades and has established itself as a management approach that harnesses the heterogeneity in both space and time and in production fields to deploy its simple yet effective approach of applying the right input at the right time, at the right place, in the right amount and in the right manner—the five 'R' concept of PA (Khosla, 2010). Over the years, PA has grown worldwide and is slowly embracing newer technologies that are autonomous, disruptive and data-intensive. The first decade of PA had a strong focus on Global Navigation Satellite Services (GNSS) and its ability to locate and quantify spatial variability in soils. The second decade focused on tractor automation and developing technologies that would allow precision management of inputs, such as crop nutrients. Now, in its third decade, there is an exponential increase in collection of location-based agricultural data via suite of sensors and sensing devices that created a new paradigm of making management decision based on evidence for higher degree of precision management. Hence, the success of future far...