An end-to-end workflow for processing multilingual stakeholder workshop data : a soil health case study
Vid Podpečan, Bojan Blažica, Fabio Volkmann, ... Marko Debeljak Vid Podpečan, Bojan Blažica, Fabio Volkmann, Carmen Vazquez, Rachel Creamer, Marko Debeljak Show all authors Show fewer authors
Show abstract Hide abstract
Stakeholder workshops often produce diverse qualitative and ordinal data that are difficult to process consistently, transparently, and reproducibly, particularly in multilingual settings. To address these challenges, we developed an end-to-end workflow for systematic processing of multilingual participatory workshop data. The workflow integrates preprocessing, structured data management, computational analysis, automated reporting, and interactive dissemination. It incorporates a range of data analysis methods, including large language models (LLMs), and supports both qualitative exploration and quantitative comparison of stakeholder perspectives. We also propose an LLM-based approach for topic extraction and intensity scoring, which transforms qualitative workshop inputs into quantitative representations. The workflow is demonstrated in the EU BENCHMARKS project, which involves multiple workshops, stakeholder groups, land-use contexts, and languages. The main contribution of this work is a transparent and adaptable workflow for systematic processing of multilingual participatory workshop data, supporting reproducible analysis, scalable dissemination, and cross-workshop comparison.
Benefits of gardening supported by information technology for older adults
István Vassányi, Benedek Szakonyi, Daniela Loi, ... Ferenc Rárosi István Vassányi, Benedek Szakonyi, Daniela Loi, Antonio Solinas, Bojan Blažica, Luigi Raffo, Marco Guicciardi, Andrea Manca, Balázs Gaál, Ferenc Rárosi Show all authors Show fewer authors
Show abstract Hide abstract
The paper presents a study performed in Italy evaluating the impact of social gardening for older adults, supported by a gardening and community mobile app and connected soil sensors. We conducted a pre- and post-test field trial with older adult volunteers (n=41) with organized gardening sessions. Standardized and ad hoc questionnaires were employed to measure changes in volunteers’ mental and psychological states. The statistical data analysis used t-tests, repeated measures MANOVA tests and logistic regression to find differences in, and predictors for, the pre- and post-testvalues of the key scores related to the perceived quality of life, cognitive functions, dietary habits and system usability. We found significant improvements in the cognitive functions, the perceived benefits of gardening and in the WHO Quality of Life (QOL) instruments, and a decrease in the fruit/vegetable consumption. The improvements in QOL were associated with the measured self-esteem, while cognitive improvement, measured by the Montreal Cognitive Assessment scale, was linked with higher commitment. Digital skills also improved and lasting social relationships formed during the trial. The observed results confirmed the positive effect of gardening on quality of life, thus justifying the viability of social gardening for older adults.
DEXiWare : a software development framework for building cooperative decision support systems
Bojan Blažica, Vladimir Kuzmanovski, Marko Bohanec, ... Marko Debeljak Bojan Blažica, Vladimir Kuzmanovski, Marko Bohanec, Tanja Dergan, Aneta Ivanovska, Jurij Marinko, Robert Modic, Matevž Ogrinc, Marko Debeljak Show all authors Show fewer authors
Show abstract Hide abstract
The development of decision support systems (DSS) for agriculture increasingly relies on complex decision models, yet transforming such models into operational, user-friendly software remains challenging. DEXiWare is a software framework designed to support the development of web-based, cooperative DSS based on decision models built with the DEX (Decision EXpert) method. The framework provides a standardized workflow for operationalizing decision models, including automated model import, data handling, assessment, and scenario analysis, within a reusable backend–frontend architecture. DEXiWare integrates backend services, a web-based user interface, and a decision engine supporting top-down (goal-seeking) and bottom-up (what-if) scenario exploration. The framework is evaluated through its application in multiple agricultural DSS and through usability testing with stakeholders, demonstrating its applicability for translating qualitative decision models into operational decision support tools for sustainability assessment in agricultural production systems.
Drivers and barriers to DSS adoption in European crop protection : insights from a machine learning analysis of farmer and advisor surveys
Margherita Furiosi, Jurij Marinko, Vid Podpečan, ... Tito Caffi Margherita Furiosi, Jurij Marinko, Vid Podpečan, Marko Debeljak, Giorgia Fedele, Tito Caffi Show all authors Show fewer authors
Show abstract Hide abstract
Integrated pest management (IPM) prioritizes non-chemical alternatives for managing pests and/or diseases, reserving chemicals as last solution, when economically and environmentally justified. The holistic consideration of the agroecosystem makes decision-making in crop protection more complex, as it requires selecting the most appropriate action at the right time. Decision support systems (DSS) for IPM help manage the risks of pests and diseases affecting crops by predicting potential threats and suggesting suitable control measures. However, their adoption remains modest among farmers, despite demonstrated benefits. An anonymous online survey was conducted among farmers, advisors, and other agricultural stakeholders to investigate factors influencing DSS uptake, or lack thereof. The survey distinguished between DSS users and non-users, enabling targeted questions on different aspects of DSS use and adoption. In total, 78 respondents were classified as DSS users and 29 as DSS non-users. Data were analyzed through clustering, followed by statistical validation of clusters and induction of a classification tree, to identify the most influential features shaping cluster formation among both DSS users and DSS non-users. The analysis identified four clusters in the DSS users’ dataset and two clusters in the DSS non-users’ dataset. For DSS users, DSS output reliability and usefulness were identified as the most influential features. Membership in a farmers’ network and DSS ease of use also contributed to cluster separation. For DSS non-users, DSS availability for different cropping systems was the most important attribute determining cluster separation. The results indicate that farmer involvement in DSS development and calibration may enhance trust and, therefore, adoption. Moreover, the need for user-friendly systems providing simple and clear information was highlighted. Although the lack of DSS tailored to specific cropping systems emerged as the main barrier, limited awareness and concerns about costs were also important obstacles. The applied methodological approach presents a reproducible and robust AI-based framework, built on open-source tools, to analyze stakeholders’ perceptions of IPM DSS and extract knowledge from complex survey data. This study provides valuable insights to facilitate DSS adoption for more sustainable crop protection and underscores the importance of both DSS technical performance and end-user needs.
Ko več podatkov ne pomeni boljših odločitev : UI pomaga kmetu ostati gospodar svojih odločitev
Od podatkov do varstva narave : stanje in izzivi v preučevanju biodiverzitete tal na Balkanskem polotoku
Manca Topole, Jurij Marinko, Vid Podpečan, ... Marko Debeljak Manca Topole, Jurij Marinko, Vid Podpečan, Photini Mylona, Marko Debeljak Show all authors Show fewer authors
Rapid evidence mapping of soil fauna responses to agricultural management assisted by large language models
Ricardo Leitão, Vid Podpečan, Luis Cunha, ... Martina Lori Ricardo Leitão, Vid Podpečan, Luis Cunha, Carmen Vazquez, Felix David, Camille Imbert, Sarah Symanczik, José Paulo Sousa, Else K. Bünemann, Marko Debeljak, Rachel Creamer, Martina Lori Show all authors Show fewer authors
Show abstract Hide abstract
The exponential growth of scientific literature challenges traditional synthesis methods, limiting our ability to derive broad insights into complex environmental processes. Large language models (LLMs) may help address this challenge by supporting the extraction of structured knowledge from unstructured text. To evaluate and demonstrate this potential in soil science, we developed a multi-module, LLM-assisted knowledge-extraction workflow built on a recently published meta-data-analysis of management–biota interactions as a contextual framework, using an iteratively refined prompt chain to extract directional relationships between agricultural management practices and soil fauna from scientific abstracts. Benchmarking against manually curated datasets showed high precision and recall, while expert-guided iterative development indicated that the information content of abstracts was likely a major practical constraint on extraction performance. To assess interpretative soundness, we applied the workflow in two use cases: an illustrative comparison with the well-established literature on reduced and no-tillage effects on soil fauna, and a knowledge-gap application on biochar and crop-residue retention. The workflow indicated predominantly beneficial reported patterns for crop residue retention, particularly for earthworms and nematodes, whereas biochar showed a more heterogeneous and context-dependent pattern. Overall, results show that LLM-assisted workflows can support rapid, large-scale evidence mapping of soil fauna responses to management practices when formal quantitative syntheses are unavailable. The proposed framework is best understood as a complementary tool for organising and screening dispersed ecological evidence, and not as a substitute for full-text synthesis, effect-size-based meta-analysis, or decision-grade inference. The complete workflow is publicly available and broadly transferable across environmental research domains.
Spatial hotspots and bundles of soil functions across Europe
Show abstract Hide abstract
A challenge in soil research is determining how multifunctional soils respond to a change in management and the environment. This is because soil functions are not independent of each other: complex interactions occur between functions across spatial scales. While a growing body of literature has attempted to quantify soil functions, few studies identified sites of multiple functions occurrence for large geographical areas. In this study, we investigate the spatial overlap between multiple soil functions in European croplands and grasslands. We generated maps of five soil functions using existing multi-attribute models developed for the large-scale assessment of soil functions. Out of these maps, we identified spatial hotspots, i.e. locations that concomitantly have a high supply of several soil functions and spatial coldspots, i.e. areas providing a low supply of functions. A cluster analysis combined with a hierarchical agglomerative clustering further revealed spatial bundles of functions, i.e. a set of soil functions that repeatedly appear together in space. Our analysis shows that hotspots of soil functions, where all five soil functions are supply at a high level, occur only in a few geographically isolated locations in Europe, covering just 0.03% of croplands and grasslands. However, broader zones were identified where three to four soil functions were achieved at an optimal level, together accounting for about 8% of the area. Similarly, only 7% of the area had at least four functions at low supply (i.e. coldspots). The cluster analysis resulted in five bundles that provided a differentiated view on multifunctional soils in Europe, with most soils providing a low to moderate levels of all five functions. Two main bundles, covering about 60% of European croplands and grasslands, were identified: one with high biodiversity and climate regulation but low other functions, and another with high nutrient cycling and biodiversity but low remaining functions. The analysis of spatial hotspots, coldspots and bundles of functions supply may be a tool for the regional-scale management of multifunctional soil so that all regions secure a sustainable supply of soil functions. It is also a first step to avoid potential conflicts between users, by allowing collective decisions on which bundles of functions to prioritize.
Synergies and trade-offs between soil functions differ with land-use intensity
Show abstract Hide abstract
The effect of soil management and the socio-economic system on soil function supply has been extensively studied. In contrast, the less explored question of how management intensity influences synergies and tradeoffs between functions – i.e. the competition between function supplies – is addressed here. Using a large soil dataset spanning 28 European countries, we estimate five soil functions and calculate co-occurrence relationships, both positive and negative, between these functions. We then examine how competition between functions varies with management intensity, using a map of land system archetypes. Our findings reveal that competition between functions varies with land-use intensity but can also differ spatially within a single intensity class. For example, we identified instances of conflicting synergies and trade-offs within one class. We also found a strong positive relationship between primary productivity and nutrient cycling in more intensively managed land, whereas there was a trade-off between water regulation and primary productivity in less intensively managed lands. These findings support future regional land-use policies focused on soil health. However, we emphasize that beyond individual soil function supply, it is necessary to consider soil multifunctionality and understand how interactions between function supplies change in response to both environmental and socio-economic factors.
Upscaling models for the large-scale assessment of soil functions
Show abstract Hide abstract
The characterization and assessment of soil functions is a prerequisite for agricultural and environmental policies aimed at soil health. However, there is a lack of satisfactory models for the assessment of soil functions supply to support national and intergovernmental initiatives. In this study we fill this gap by restructuring models developed to assess the multifunctionality of agricultural soils at the field scale. The multi-criteria decision models rely on soil properties, site characteristics and management information to assess the following five soil functions: (1) water regulation, (2) climate regulation, (3) nutrient cycling, (4) primary productivity and (5) provision of habitat for biodiversity. We develop models to assess soil functions supply at regional and national scales by adapting their structure to cope with the general lack of information on soil management at larger geographical scales. The restructured models are verified and a sensitivity analysis of the new model structure is performed. We further applied a comparison of the upscaled models with results from validated field-scale models using real data from 94 sites spanning across 13 European countries. We found that the upscaled models showed a similar sensitivity to the variability of the input data from the 94 sampling sites as the base models from which they were developed and that their overall supply is expected to be comparable. We describe the model structure of the upscaled models as well as their qualitative scales and integration rules. We propose the application of the models can serve for large-scale assessment of soil functions supply as part of soil health assessment for regional and national environmental and agricultural policies.
A methodology for developing sustainable business models in agri-food systems
Advances in the science, technology, and innovation of the senior wellness management : systemic organizational perspective
Vlado Dimovski, Sandra Penger, Simon Colnar, ... Judita Peterlin Vlado Dimovski, Sandra Penger, Simon Colnar, Vasja Roblek, Maja Meško, Anamarija Kejžar, Bojan Blažica, Mitja Luštrek, Judita Peterlin Show all authors Show fewer authors
Barriers and prospects for soil biodiversity research in the Balkans
Manca Topole, Jurij Marinko, Vid Podpečan, ... Marko Debeljak Manca Topole, Jurij Marinko, Vid Podpečan, Photini V. Mylona, Marko Debeljak Show all authors Show fewer authors
Show abstract Hide abstract
Soil degradation is a growing problem that threatens the well-being of humanity worldwide. One of the pillars of soil health are soil organisms, which are involved in a variety of soil processes and functions contributing to numerous ecosystem services. Although the Balkans are considered a hotspot of European biodiversity, our knowledge of soil life in this region is still limited. The Edaphobase data warehouse (https://portal.edaphobase. org/) focuses on European soil biodiversity data. The Balkan datasets in this database were analysed alongside relevant scientific literature to gain insight into soil biodiversity research and collaborative schemes in the region. In addition, assessments of national capacities for data provision and soil biodiversity research were obtained through an expert survey. The results of the study show large differences between the Balkan countries. Although Edaphobase enables metadata to accompany the soil biodiversity data, the potential of this comprehensive data warehouse for ecological modelling is largely underutilised by Balkan datasets. Responses to the questionnaire revealed significant gaps in national financial and technical capacities for soil biodiversity research, which could be addressed through an instrument that supports international collaboration via project funding. Such mechanisms would not only reduce economic disparities, but also promote cohesion within the scientific community of the region. The analysis of the network of Balkan authors revealed that collaboration between Balkan experts is currently quite unbalanced and that some countries are isolated in their research activities. This study provides a novel insight into the current state of soil biodiversity science in the Balkan countries and serves as an important reference point for a much-needed regional approach to promote soil biodiversity research in the Balkans.
Decision support system for garden centers : a rule based approach to in-store customer guidance
Developing a multi-criteria assessment model for soil primary productivity in double cropping systems : Insights from the North China plain
Yizan Li, Carmen Vazquez, Jiyu Jia, ... Rachel Creamer Yizan Li, Carmen Vazquez, Jiyu Jia, Jiangzhou Zhang, Ron De Goede, Marko Debeljak, Fusuo Zhang, Junling Zhang, Rachel Creamer Show all authors Show fewer authors
Show abstract Hide abstract
Soil, one of the Earth’s most critical natural resources, supports global agricultural production and underpins key ecosystem services. Among the multiple functions soil performs, primary productivity stands out as a crucial element, pivotal for ensuring food security as the basis of the agricultural system. This study aimed to develop a multi-criteria assessment model for soil primary productivity at field scale, drawing insights from the winter wheat summer maize rotation systems in the North China Plain. The development of the model followed the Decision Expert (DEX) methodology, using an integrated approach that combines knowledge graph and data mining techniques. We systematically structured the knowledge underpinning soil primary productivity. Uti lising datasets derived from long-term field experiments and smallholder farms, the model was subjected to an iterative process of calibration and validation, enhancing both its predictive accuracy and operational applica bility. The developed DEX model consists of 28 input attributes that encompass soil properties, field management practices, and meteorological conditions. The model achieved an accuracy of 71% in assessing soil primary productivity in the experimental field dataset after calibration, and 62% in the smallholder farm dataset as model validation. The developed model can effectively assess soil primary productivity function and facilitate the improvement of soil management. The innovative integration of knowledge-based and data-driven approaches proved to be effective. It is expected that the developed model can be integrated with other soil function models into a soil health decision support system that provides a holistic approach to soil health assessment and opti misation of field practices
GoraNiNora : context-dependent information for safe mountain visits
Incentives and barriers to adoption of decision support systems in integrated pest management among farmers and farm advisors in Europe
Jurij Marinko, Aneta Ivanovska, Martin Marzidovšek, ... Marko Debeljak Jurij Marinko, Aneta Ivanovska, Martin Marzidovšek, Mark Ramsden, Marko Debeljak Show all authors Show fewer authors
IPM Decisions Platform – a Pan-European online platform hosting decision support systems and associated resources for integrated pest management
Mark Ramsden, Berit Nordskog, Tor-Einar Skog, ... Neil Paveley Mark Ramsden, Berit Nordskog, Tor-Einar Skog, Dave Skirvin, Angelo Marguglio, Antonio Caruso, Christophe Pradal, Lise Jorgensen, Mette Sonderskov, Nikos Georgantzis, Marko Debeljak, Jurij Marinko, Harm Brinks, Bjorn Andersson, Ilias Travlos, Eleanor Dearlove, Neil Paveley Show all authors Show fewer authors
Show abstract Hide abstract
Crop protection and pest management are major economic and environmental concerns throughout Europe. The consultation of decision support systems (DSS) to guide decisions relating to Integrated Pest Management (IPM) is one of the key principles of IPM, reducing the ambiguity around potential risks to crop health. ‘Pests’ in this context include invertebrate pests, weeds and pathogens. The impact of DSS can be limited by a lack of awareness of DSS availability, inconsistencies in the user functions of different DSS, regional fragmentation of access, and a lack of transparency of the origin, validity, and benefits of DSS. Failure to address these limitations undermines trust in IPM DSS and leads to a reluctance of farmers and advisors to invest time in consulting multiple DSS sources as part of their agronomic decision toolbox. The EU-funded IPM Decisions project (Grant agreement ID: 817617) addressed these limitations by creating a Europe-wide free-access online platform. The IPM Decisions platform was designed in consultation with farmers, advisors and wider stakeholders to increase access to and uptake of IPM DSS integrated within it. It offers an end-point for IPM researchers and DSS developers to make adapted and novel DSS available to users, and provides a ‘one-stop shop' for farmers and advisors looking to consult free access or paid IPM DSS. Dedicated dashboards within the platform facilitate farm set up, consultation of DSS, comparison of DSS outputs, and adjustment of model parameters for adaption to different pests/regions. The IPM Decisions digital infrastructure enables easy integration of models and data with external platforms, providing a framework for accessing and sharing models and data between researchers and developers. The platform therefore provides both a ready to go user interface for new DSS, as well as the infrastructure to support and connect existing and future user interfaces.

