Smart Decision Systems for Digital Farming: 2nd Edition

Dear Colleagues,

Recently, agriculture has adopted digital farming with artificial intelligence, which aims to improve the productivity, convenience, and quality of classical farming, which relies on the intuition and experience of farmers. Digital farming technologies enable data-based smart decisions in all fields of agriculture, such as production, distribution, and consumption, to solve agricultural problems faced by rural aging, labor shortages, and climate change and to achieve sustainable agriculture. In the agricultural sector, the term 'Agriculture 5.0' refers to digital farming based on artificial intelligence and the Internet of Things.

This Special Issue welcomes the contribution of studies focusing on the use of recent techniques, including artificial intelligence and the Internet of Things, with the aim of obtaining information related to digital farming. Topics of interest include, but are not limited to, the following:

• Decision support systems for crop management.
• Decision support systems for livestock management.
• Monitoring systems for crop management.
• Monitoring systems for livestock management.

Prof. Dr. Yongwha Chung
Dr. Sungju Lee
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Sensors is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

• digital farming, agriculture 5.0
• crop management, livestock management
• decision support systems, monitoring systems
• image processing, signal processing
• artificial intelligence, Internet of Things

• Smart Decision Systems for Digital Farming in Sensors (10 articles)

Title: Embedding AI-enabled data infrastructures for sustainability in Agri-Food: A Soft-Fruit and Brewery Use Case Perspectives
Authors: Milan Markovic, Andy Li, Tewodros Alemu Ayall, Alexander Bowler, Nicholas Watson, Mel Woods, Rachael Ramsay, Peter Edwards, Georgios Leontidis
Affiliation: University of Aberdeen, University of Leeds, University of Dundee, Scotland's Rural College
Abstract: The global food system contributes about a third of the total anthropogenic GHG emissions and like other sectors, it must be part of a rapid transition to net zero. Over the past couple of decades, we have seen a comprehensive adoption of new technologies across several subsectors, such as farming, livestock, horticulture, and others, that span, among else, sensor technologies, IoT, remote sensing, AI, and computer vision. However, several challenges still remain in co-designing and co-developing approaches that can support the sector's carbon action planning at scale, including deploying technologies and infrastructure; evaluating interventions; involving stakeholders; and providing granular enough information for decision making. In this perspectives article, we explore some approaches that have been developed and deployed recently focusing on two distinct use cases related to soft fruits and brewery. We also provide some directions that we believe can have an impactful influence in enabling the more widespread adoption of technologies to support carbon reduction in the agri-food sector.

Title: Image Processing for Smart Agriculture Applications Using Cloud-Fog Computing
Authors: Dušan Marković; Zoran Stamenković; Borislav Đorđević; Siniša Ranđić
Affiliation: University of Kragujevac, Faculty of Agronomy in Čačak, Cara Dušana 34, 32102 Čačak, Serbia
Abstract: The widespread use of IoT devices leads to the generation of a huge amount of data and initiate the need for analytical solutions in many areas of human activities, such as the field of smart agriculture. Decision-making systems in smart agriculture involve the image analysis with potential to increase the productivity, efficiency and sustainability. By applying Convolutional Neural Networks (CNN), state recognition and classification can be performed based on images from locations, thus obtain potential solution for early detection of problems or optimized management of resources. Continuous monitoring of crop growth stages enables timely interventions, such as control of weeds and plant diseases, as well as pest control, ensuring optimal development. The main concept of proposed solution relies on the direct connection between Cloud and Edge devices, which is achieved through Fog computing. The use of CNN models that would be trained on the Cloud platform and transferred to the Fog computing layer would bring to the fore the advantages of image processing in agriculture such as the reduction of operating costs and the requirements for manual labor. The IoT data processing on devices belonging to Fog Computing level involves handling data close to their source, which provides certain advantages over traditional Cloud-only approaches. In the case of data processing off-load to Edge and Fog devices, the system responsiveness can be improved, the costs associated with data transmission and storage can be reduced, and the overall system reliability and security can be increased.