Proposal of an ontological approach to design and analyse farm information systems to support Precision Agriculture techniques

Abstract

After a comparative evaluation around the concepts of Industry 4.0, Precision Agriculture and Smart Farming, the paper discusses the necessity of identifying solutions able to apply the methods of the so-called Knowledge Management 4.0 in the agri-environmental enterprises. To this aim, an ontology based on a conceptual map derived from the data-to-information transformation is here proposed to support the design of a new generation of Farm Information Systems (FIS) able to fit the production needs of agri-environmental enterprises. The data-to-information cycle is split into four phases: A) Data collection, B) Data processing, C) Data analysis and evaluation, and D) Use of information. Phases A and D comprise tools of “light digitization” typically referring to OLTP components (On Line Transactional Processes). On their turn, phases B and C are typically formed by “heavy digitization” components (On Line Analytical Processes), generally more complicated to be managed by the farmers directly. The conceptual map defined by the ontology is firstly useful to plan the composition of the FIS according to a modular approach, possibly following a strategy that starts to consider the introduction of OLTP components, for then evolving gradually towards more articulated solutions that include also OLAP component and related functions. In this way, decision makers can manage practical planning instrument able to show clearly the level of complexity a FIS can reach, thus evaluating its sustainability with respect to the financial, cultural and professional resources available at the farm. Finally, after having underlined the opportunities offered by Cloud Computing and widespread connectivity, that provide an easier adoption of OLAP tools, some application cases are presented and discussed.

A Smart and Sustainable Future for Viticulture Is Rooted in Soil: How to Face Cu Toxicity

“…In fact, this revolution has brought significant attention to the new technological frontiers connected to the "Internet of Things" (IoT), Big Data, Cloud Computing, hyper-connectivity, cybernetics and augmented reality. As a consequence of this technological trend and its effects, the terms agriculture 4.0 and smart agriculture are coming to be preferred to the term precision agriculture [129].…”

“…In particular, precision and smart viticulture technologies could contribute positively to the following aspects: (1) crop monitoring, i.e., using optical sensors on vehicles (e.g., tractors, autonomous vehicles, or drones) to perform a sort of "early digital scouting" to be carried out promptly to keep the phytosanitary status of wide-crop areas under control [137,138]; (2) operational monitoring, i.e., using the so-called FORK systems (Field Operation Register Keeping) [129,139,140] which allow the detection and automatic recording of how a field operation is carried out; (3) implementation of site-specific techniques with retrofit components, i.e., adaptable to existing farm machinery, thus avoiding the need to make large investments in new equipment (see Figure 5). The first two aspects concern information management actions, necessary for medium-and long-term quality decision-making processes at the farm, based on targeted information.…”

“…The data analyses might also combine data from multiple farms/vineyards, as well as other big (information assets characterized by such a high volume, velocity and variety that it requires specific technology and analytical methods for its transformation into value [143]) data from several sources [144,145]. Finally, the results obtained can lead to an action, such as process optimization (modification of irrigation, fertilization, or chemical treatments), or to a report for internal or external users [129,131,133]. Such actions can also be implemented in a more precise and/or automatic way through straddle tractors/machines, autonomous vehicles/robots, and drones [120,146].…”

Developing an Automated Monitoring System for Cable Yarding Systems

“…The overall structure of the data intepretation procedure followed the main steps described in Mazzetto et al (2019) and consisted of raw data collection, data processing and analyses to obtain final operative reports (Fig. 1).…”

“…The approach was divided into three Fig. 1 Schematic representation of data process flowchart for ed system, showing how raw data is converted to obtain elemental time study information (after (Mazzetto et al 2019)) areas, the box A to the tasks directly carried out by the user, boxes B and C refers to the sets of procedures performed by the Inference Engine and box D refers to the achieved outputs.…”