A review of visualisations in agricultural decision support systems: An HCI perspective

Abstract

Decision Support Systems (DSSs) are used in precision agriculture to provide feedback to a variety of stakeholders, including farmers, advisers, researchers and policymakers. However, increments in the amount of data might lead to data quality issues, and as these applications scale into big, real-time monitoring systems the problem gets even more challenging. Visualisation is a powerful technique used in these systems that provides an indispensable step in assisting end-users to understand and interpret the data. In this paper, we present a systematic review to synthesise literature related to the use of visualisation techniques in the domain of agriculture. The search identified 61 eligible articles, from which we established end-users, visualisation techniques and data collection methods across different application domains. We found visualisation techniques used in various areas of agriculture, including viticulture, dairy farming, wheat production and irrigation management. Our results show that the majority of DSSs utilise maps, together with satellite imagery, as the central visualisation. Also, we observed that there is an excellent opportunity for dashboards to enable end-users with better interaction support to understand the uncertainty of data. Based on this analysis, we provide design guidelines towards the implementation of more interactive and visual DSSs.

Precision Techniques and Agriculture 4.0 Technologies to Promote Sustainability in the Coffee Sector: State of the Art, Challenges and Future Trends

“…In this sense, several studies are related to the use of A4.0 technologies, such as sensing and actuation drones to identify and control pests in crops [20], sensors and Internet of Things (IoT) for water management [21], agricultural decision support systems [22], proximal images and machine learning (ML) to identify nutritional deficiencies in crops [23], among others. These technologies assist in data collect, information analysis, diagnostics and formulation of strategies for the agricultural sector [24].…”

Ordinary User Experiences at Work

“…We do not try to provide full coverage of this literature, which spans different disciplines beyond HCI, but try to situate our research in this literature. We focus on: Structure Task Actors Technology  Professional growers as work domain experts [22], not on leisure gardening or urban farming [11,38,81]  Climate-management tasks related to caring for plants [25], not on the indoor comfort of people [1,50]  Commercial, present-day horticulture [74], not on futuristic alternatives [69,88] or interaction design for the international development of agricultural practices [108]  Climate-management technology as a professional tool [66], not on leisure tools such as open-source sensors for urban gardens or urban installations involving plants [18,19,41] 2.1 UX at work…”

“…However, some research addresses usability and UX in specific work domains, such as administration [9], health [53], manufacturing [45], and maritime work [27]. The work domain that we study in this paper is horticulture, or more broadly agriculture, which is an emerging area in HCI research (e.g., [25,64,85,88]). In the following, we structure the presentation of related work around the four elements of Figure 1 and, wherever possible, limit our examples to the studies most relevant to the horticultural domain.…”

“…Much of this is captured by the notion of organizational usability, defined as "the match between a computer system and the structure and practices of an organization, such that the system can be effectively integrated into the work practices of the organization's members" [17]. For example, Gutiérrez et al [25] found that an important reason for the modest use of agricultural decision support systems was that their terminology and logic were designed by agricultural scientists and IT developers and failed to consider the work-domain expertise and practical needs of farmers. These systems met neither business goals, nor user goals, and were far from providing good UX at work.…”

Decision Support on Monitoring and Disaster Management in Agriculture with Copernicus Sentinel Applications

“…Therefore, there is an emerging need for custom-built solutions and one-package tools that include specific sets of processing functions to perform the satellite image analysis for crop type mapping and for mapping the agricultural area affected by a natural disaster. A recent review [11] presents several examples of DSS for agricultural applications, but these are usually addressing the farmers, farm advisers, or agronomists. They identify four tools that address policymakers [12][13][14][15], but still none of these address the PAs or IOs for crop type mapping or for mapping of affected agricultural areas by natural disasters.Regarding the crop type mapping, some recent projects focus on the exploitation of Copernicus Sentinel data.…”