Smart farming is the evolution of precision agriculture, it is based on Internet of Things (IoT), this term was coined by Kevin Ashton in 1999 and it represents data collected from objects or ‘things’, (e.g., devices, implements, sensors) and processed individually or together with algorithms that correlate the information to help the users to take decisions not based only on position, as is in precision agriculture, but also on data ‘enhanced by context and situation awareness, triggered by real-time events’ (Wolfert et al., 2017). The technology advancement in agriculture is very heterogeneous (Pivoto et al., 2017), also very much variable in the same country, as a consequence in some areas, it is possible to start immediately with the introduction of smart farming approach because the farmers have been already working with the fundamental technology such as automatic satellite guidance systems, control sections and variable rate or they have already sensors to monitor some important crop variables. On the contrary, the majority of farmers must introduce the innovation in their machines, but this is a process that will need some time because first of all they would provide the base of technology and above all they would change the way of work. In a tradition-based culture, it is difficult to introduce a change, so it is necessary that not only the companies talk about smart farming to farmers but also all the public and private entities, the association of farmers, universities and consultants show the advantages of the new technologies and present this as the best way to reduce costs and pollution and increase the quality of production. The smart farming approach is based on the collection of data from different sources in a way as automatic as possible because it is possible to acquire huge amount of data (so-called Big Data) without big efforts by the farmer (Wolfert et al., 2018). Data collected in this frame are generally exported to the cloud from the tractor and its implement, from various kinds of sensors on the field, proximity or remote multispectral cameras, weather stations, etc. After an automatic data collection, the core of the platforms performs some adjustments and delivers the data to the platforms; at this stage, consultants can analyze the output and give precious results to the farmers. These systems are called decision support systems (Ahmad and Mahdi. 2018), but every IoT platform even if very precise could not work automatically without the supervision of agronomists and the final approval and review of the farmer. Smart farming, for the first time, lets to involve all the actors in a farmer’s season, farmer, agronomist, consultant and contractors, to collect all possible data from the field and to help the farmer to take the right decisions. Although the aforementioned technologies have not reached all parts of the world, the improvement in precision farming represents a positive result for everyone without any distinction. In this chapter, after the description of some new technologies applied in the so-called ‘smart farming’, seven case studies from different countries, of their technological equipment and approaches used in precision agriculture and IoT, are showed. The case studies presented here deal with the use of satellite imagery for crop canopy vigour mapping, prescription map fertilization strategy, smart irrigation approach and use of proximal sensing sensor developed as major investment by farmers could be made in regard of the technological improvements offered by GNSS (Global Navigation Satellite Systems: GPS, GLONASS, Galileo and Beidou and services related on). As data acquisition through proximal and remote sensing has become more affordable, there was an increase in variable rate fertilization, weeding and seeding, as well as precision irrigation. Smart irrigation consists in a developing strategy for the agriculture sustainability and there is a huge interest in developing this technology commercially. The spectrum of the technologies reported in the case studies is between the state of the art and to some other relatively known technologies but of widespread use and of overwhelming success. The case studies provide some recent operative advances for some countries such as Italy, Greece, France, United States and Japan. An example of a Mediterranean farm (commercial wine estate) in France is presented; in this example, digital and precision agriculture tools are used for wine growers and advisors. In the second case study, cropland and perennial crop precision farming in Greece is presented with many case studies that highlighted the use of remote and proximal sensing in a variety of conditions. Variable rate nitrogen fertilization based on prescription maps and ‘onthe-go’ sensors are examples of Northern Italy maize cultivation. Smart irrigation is the theme of the Unites states; this case history reports the technological achievements made in cotton irrigation to optimize yields and sustainability. In Japan, rice production based on proximal sensors and IoT is described. In some other case studies (Argentina and Tanzania), an overview of the adoption of smart farming technologies and methods used in the countries, respectively, is discussed. The results of this chapter show the potential of precision farming in connecting each part of the farm to the stakeholders and the economical profitability of the newest technologies as well as the improved environmental sustainability. It also underlined that in some countries there is a lack of technologies (e.g., new machinery systems and knowledge in data analysis), hence strong investment is then required for the conversion into the IoT system. Precision farming and IoT are not only technologies that can help to increase yields but also they are mainly devoted at the optimization of the resources and the resilience of the human kind and the agro-ecosystems. Outline of the chapter: Chapter introduction 7.1 France 7.2 Greece 7.3 Italy 7.4 Georgia, USA 7.5 Argentina 7.6 Tanzania 7.7 Japan

Precision farming and IoT case studies across the world / G. Fastellini, C. Schillaci - In: Agricultural Internet of Things and Decision Support for Precision Smart Farming / [a cura di] A. Castrignanò, G. Buttafuoco, R. Khosla, A.M. Mouazen, D. Moshou, O. Naud. - [s.l] : Elsevier Academic Press, 2020. - ISBN 9780128183731. - pp. 331-415 [10.1016/B978-0-12-818373-1.00007-X]

Precision farming and IoT case studies across the world

C. Schillaci
2020

Abstract

Smart farming is the evolution of precision agriculture, it is based on Internet of Things (IoT), this term was coined by Kevin Ashton in 1999 and it represents data collected from objects or ‘things’, (e.g., devices, implements, sensors) and processed individually or together with algorithms that correlate the information to help the users to take decisions not based only on position, as is in precision agriculture, but also on data ‘enhanced by context and situation awareness, triggered by real-time events’ (Wolfert et al., 2017). The technology advancement in agriculture is very heterogeneous (Pivoto et al., 2017), also very much variable in the same country, as a consequence in some areas, it is possible to start immediately with the introduction of smart farming approach because the farmers have been already working with the fundamental technology such as automatic satellite guidance systems, control sections and variable rate or they have already sensors to monitor some important crop variables. On the contrary, the majority of farmers must introduce the innovation in their machines, but this is a process that will need some time because first of all they would provide the base of technology and above all they would change the way of work. In a tradition-based culture, it is difficult to introduce a change, so it is necessary that not only the companies talk about smart farming to farmers but also all the public and private entities, the association of farmers, universities and consultants show the advantages of the new technologies and present this as the best way to reduce costs and pollution and increase the quality of production. The smart farming approach is based on the collection of data from different sources in a way as automatic as possible because it is possible to acquire huge amount of data (so-called Big Data) without big efforts by the farmer (Wolfert et al., 2018). Data collected in this frame are generally exported to the cloud from the tractor and its implement, from various kinds of sensors on the field, proximity or remote multispectral cameras, weather stations, etc. After an automatic data collection, the core of the platforms performs some adjustments and delivers the data to the platforms; at this stage, consultants can analyze the output and give precious results to the farmers. These systems are called decision support systems (Ahmad and Mahdi. 2018), but every IoT platform even if very precise could not work automatically without the supervision of agronomists and the final approval and review of the farmer. Smart farming, for the first time, lets to involve all the actors in a farmer’s season, farmer, agronomist, consultant and contractors, to collect all possible data from the field and to help the farmer to take the right decisions. Although the aforementioned technologies have not reached all parts of the world, the improvement in precision farming represents a positive result for everyone without any distinction. In this chapter, after the description of some new technologies applied in the so-called ‘smart farming’, seven case studies from different countries, of their technological equipment and approaches used in precision agriculture and IoT, are showed. The case studies presented here deal with the use of satellite imagery for crop canopy vigour mapping, prescription map fertilization strategy, smart irrigation approach and use of proximal sensing sensor developed as major investment by farmers could be made in regard of the technological improvements offered by GNSS (Global Navigation Satellite Systems: GPS, GLONASS, Galileo and Beidou and services related on). As data acquisition through proximal and remote sensing has become more affordable, there was an increase in variable rate fertilization, weeding and seeding, as well as precision irrigation. Smart irrigation consists in a developing strategy for the agriculture sustainability and there is a huge interest in developing this technology commercially. The spectrum of the technologies reported in the case studies is between the state of the art and to some other relatively known technologies but of widespread use and of overwhelming success. The case studies provide some recent operative advances for some countries such as Italy, Greece, France, United States and Japan. An example of a Mediterranean farm (commercial wine estate) in France is presented; in this example, digital and precision agriculture tools are used for wine growers and advisors. In the second case study, cropland and perennial crop precision farming in Greece is presented with many case studies that highlighted the use of remote and proximal sensing in a variety of conditions. Variable rate nitrogen fertilization based on prescription maps and ‘onthe-go’ sensors are examples of Northern Italy maize cultivation. Smart irrigation is the theme of the Unites states; this case history reports the technological achievements made in cotton irrigation to optimize yields and sustainability. In Japan, rice production based on proximal sensors and IoT is described. In some other case studies (Argentina and Tanzania), an overview of the adoption of smart farming technologies and methods used in the countries, respectively, is discussed. The results of this chapter show the potential of precision farming in connecting each part of the farm to the stakeholders and the economical profitability of the newest technologies as well as the improved environmental sustainability. It also underlined that in some countries there is a lack of technologies (e.g., new machinery systems and knowledge in data analysis), hence strong investment is then required for the conversion into the IoT system. Precision farming and IoT are not only technologies that can help to increase yields but also they are mainly devoted at the optimization of the resources and the resilience of the human kind and the agro-ecosystems. Outline of the chapter: Chapter introduction 7.1 France 7.2 Greece 7.3 Italy 7.4 Georgia, USA 7.5 Argentina 7.6 Tanzania 7.7 Japan
Precision agriculture; Smart farming; Variable Rate Fertilization
Settore AGR/02 - Agronomia e Coltivazioni Erbacee
Settore AGR/14 - Pedologia
2020
Book Part (author)
File in questo prodotto:
File Dimensione Formato  
capitolo7.pdf

accesso riservato

Descrizione: Capitolo utile per studenti di lauree specialistiche in scienze agrarie
Tipologia: Post-print, accepted manuscript ecc. (versione accettata dall'editore)
Dimensione 8.94 MB
Formato Adobe PDF
8.94 MB Adobe PDF   Visualizza/Apri   Richiedi una copia
Pubblicazioni consigliate

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/2434/738718
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 27
  • ???jsp.display-item.citation.isi??? 15
social impact