Original scientific article

Modelling of soil multifunctionality across Europe

Alexandre M.J.-C. Wadoux, Marko Debeljak, Philippe Lagacherie, Rachel Creamer
Show abstract Hide abstract

Soils sustain a number of functions playing a key role in ecosystem functioning and providing a multitude of services to human society. While it is acknowledged that all soils are multifunctional, there is, to date, limited knowledge on how the supply of soil functions and their combination differ spatially with land use type, soil characteristics, climate and land use intensity at large geographical scales. We address this gap by quantifying five functions of major importance to European soils: (1) primary productivity, (2) water regulation, (3) climate regulation, (4) nutrient cycling and (5) provision of habitat for biodiversity. We built a multi-attribute semi-quantitative model with a hierarchical structure. The model is structured for the large-scale evaluation of soil functions and takes as input a set of indicators related to dynamic and stable soil properties, as well as climate, topography and management practices, and returns qualitative aggregated attributes representing the soil functions supply. Thresholds for the soil functions supply are obtained by statistical analysis coupled with expert knowledge and vary across European environmental zones. The model is tested utilizing a large pan-European dataset focused on cropland and grassland systems. Statistical distributions of soil functions supply are obtained alongside alpha- and beta-multifunctionality representing the diversity of soil functions represented at a sampling location and the unique contribution of the sampled site to the regional (i.e. NUTS3 level) soil functions supply, respectively. We found that the supply of soil functions varied greatly across landscapes in Europe and between environmental zones. Spatial patterns of the alpha- and beta-multifunctionality revealed hotspots of multifunctionality (alpha multifunctionality) but also sites providing a set of soil function delivery unique within the region (beta multifunctionality). Few sites are both unique and highly diverse. Our study set a baseline estimate of soil functions in Europe as a prerequisite to consider soil functions in environmental planning.

Conference proceedings placeholder cover
2025
Published scientific conference contribution

Offline indoor navigation via QR codes

Robert Modic, Matevž Ogrinc, Andraž Simčič, ... Drago Torkar Robert Modic, Matevž Ogrinc, Andraž Simčič, Bojan Blažica, Drago Torkar Show all authors Show fewer authors
Show abstract Hide abstract

This paper introduces a novel, cost-effective system for indoor navigation and localization that operates independently of satellite positioning services and data communication networks. The proposed solution leverages QR codes affixed within building interiors and an accompanying smartphone application, which, through integration with the device’s inertial motion unit (IMU) sensors and the application of the Pedestrian Dead Reckoning (PDR) algorithm [1], accurately determines the user’s position. This position data is then utilized by the Dijkstra navigation algorithm [2] to facilitate user navigation to their desired destination. Beyond navigation, this system offers significant utility in healthcare logistics, enabling efficient collection and transmission of triage decisions in emergency situations, even in the absence of a communication network.

Original scientific article

Overcoming barriers to the adoption of decision support systems in integrated pest management in some European countries

Jurij Marinko, Vladimir Kuzmanovski, Mark Ramsden, Marko Debeljak
Show abstract Hide abstract

Decision support systems (DSSs) can improve decision making in integrated pest management (IPM), but are still underutilised despite proven environmental and economic benefits. To overcome the barriers to DSS adoption, this study analyses survey data from 31 farmers and 94 farm advisors, researchers and developers across 11 European countries. Using machine learning techniques, respondents were first categorised into clusters based on their responses to the questionnaire. The clusters were then explained using classification trees. For each cluster, customised approaches were proposed to overcome the barriers to DSS adoption. For farmers, these include building trust through co-development, offering free trials, organising practical workshops and providing clear instructions for use. For farm advisors and researchers, involvement in the development of DSS and giving them access to information about the characteristics of the DSS is crucial. IPM DSS developers should focus on 14 key recommendations to improve trust and the ease of use, increase the transparency of DSS descriptions and validation, and extend development to underserved sectors such as viticulture and vegetable farming. These recommendations aim to increase the uptake of DSSs to ultimately improve the implementation of IPM practises and help reduce the risk and use of pesticides across Europe despite the ever-growing challenges in agriculture.

Original scientific article

Robot NAO integrated lesson vs. traditional lesson : measuring learning outcomes on the topic of “societal change” and the mediating effect of students’ attitudes

Violeta Rosanda, Ivan Bratko, Mateja Gačnik, ... Andreja Istenič Violeta Rosanda, Ivan Bratko, Mateja Gačnik, Vid Podpečan, Andreja Istenič Show all authors Show fewer authors
Show abstract Hide abstract

Our research aims to examine the effectiveness of introducing social robots as educational technology within authentic classroom activities without modifying them to be designed for a robot. We chose as test subject the fifth-grade curricular topic “The role of technology and its impact on society”, meeting the critical stage of moral development students aged of 11–12. The study, with both experimental (EG) and control groups (CG), will be conducted over 6weeks. This study will examine the impact of robot-supported lessons with post-participation testing on learning outcomes and examine students' perception of the robot in the classroom as a potential correlation with academic performance. The form of the study will be a between-group non-randomised controlled experiment. Control and experimental groups will be matched concerning gender, mastery of technology and previous knowledge and understanding of the curricular topic in focus. The instructional design of process-outcome strategies will incorporate all of Bloom's taxonomic levels. In the review of related studies, we identified gaps in social robot-supported lessons within the regular curriculum between-group experiment. Based on a review of related research showing more focus on robot performance in the classroom from technical-interaction aspects we want to convey from pedagogical starting point. The robot's placement in the pedagogical process will be considered an integral part of the teacher's technical environment. We will use the pre-participation test to establish whether there is the initial equivalence between EG and CG in terms of gender, mastery of technology, and previous knowledge and understanding of the curricular topic under examination.

Original scientific article

Slovenian Social Assistance Rights text data collection (SSAR 1.0)

Matej Martinc, Senja Pollak, Vid Podpečan, ... Špela Arhar Holdt Matej Martinc, Senja Pollak, Vid Podpečan, Luka Mišič, Tilen Štajnpihler Božič, Nejc Urankar, Kristina Krajnc, Ana Marija Sobočan, Špela Arhar Holdt Show all authors Show fewer authors
Show abstract Hide abstract

This paper presents the Slovenian Social Assistance Rights text corpus (SSAR 1.0), a newly compiled and openly available dataset intended to support linguistic and computational analysis of language complexity in the domain of social assistance law. The corpus includes both legally binding and interpretative texts and is analysed using a range of established readability formulas and syntactic complexity metrics. The results show that social assistance texts tend to exhibit significantly higher sentence-level complexity than selected reference texts from news portals and government websites, particularly in terms of sentence length, syntactic depth, and dependency structure. Importantly, some explanatory texts intended for beneficiaries were found to be among the most complex, pointing to a notable disconnect between communicative purpose and linguistic form. In contrast, texts from news portals displayed consistently lower structural complexity, offering valid empirical points of comparison. The study confirms that quantitative measures can reliably flag particularly complex texts and identify more accessible examples, providing a practical foundation for developing clearer legal drafting practices. By establishing a replicable methodology and empirical baseline, this work contributes to ongoing efforts to improve linguistic accessibility in Slovenian public communication.

Original scientific article

Social robot radical innovation : capacities and status attributed to the NAO robot by 11 to 12-year-old students and preservice teachers’ perceptions

Andreja Istenič, Vid Podpečan, Violeta Rosanda, Xuesong Zhai
Show abstract Hide abstract

Children’s environments are radically modified by introducing artificial intelligence-based technology that can mimic human socio-emotional capabilities. Artificial intelligence facilitated the transition from computers to real-world embodied physical systems such as social robots, anthropomorphic artefacts with implications for child development and a distinctly radical innovation compared to all previous technologies in classrooms. Empirical research of child-learning process in an authentic classroom and teachers’ perception of how children perceive anthropomorphic robots is deficient. Teachers’ knowledge of students’ perception of technology is essential. Social robots are anticipated for future generations of teachers and students. A two-part survey applied ASOR ascription of mental capacities, socio-practical capacities and socio-moral status. Involved were two samples, elementary school students aged 11–12 and preservice teachers. In the first part, students’ perceptions of a social robot were examined. The NAO robot-assisted lesson was conducted in a regular classroom according to a regular curriculum addressing the role of technology in society, followed by a survey. In the second part, preservice teachers assess children’s perceptions of social robots. The study objective was (a) preservice teachers’ knowledge of which capacities and status students attribute to the NAO robot in an educational setting compared with (b) the capacities and status students attribute to the NAO robot. In data analysis, preservice teachers’ and students’ scores were compared. Our findings show that (a) preservice teachers don’t know students’ perceptions of NAO; (b) compared the perceptions of 11-year-old fifth graders and 12-year-old sixth graders showed no statistically significant difference. Examining gender differences three items were identified.

Conference proceedings placeholder cover
2025
Published scientific conference contribution abstract

Trajnostna in družbeno sprejemljiva osvetlitev javnih odprtih prostorov

Marko Debeljak
Conference proceedings placeholder cover
2025
Published scientific conference contribution

Typology of B2B and B2C decision support tools in the agri-food sector

Tanja Dergan, Marko Debeljak
Original scientific article

Computer vision techniques for morphological analysis and identification of two Pseudo-nitzschia species

Martin Marzidovšek, Patricija Mozetič, Janja Francé, Vid Podpečan
Show abstract Hide abstract

The diversity of phytoplankton influences the structure of and processes that occur in marine ecosystems, with size and other morphological traits being crucial for nutrient uptake and retention in the euphotic zone. Our research introduces a machine learning method that can facilitate the analysis of phytoplankton functional traits from image data. We use computer vision to identify and quantify phytoplankton species and estimate size-related traits based on cell morphology. The study uses transfer learning, where generic, pre-trained YOLOv8 computer vision models are fine-tuned with microscope image data from the Adriatic Sea. The study shows that, for this task, it is possible to effectively fine-tune models trained on out-of-domain images and that this is possible with a small training dataset. The results show high accuracy in detecting and segmenting phytoplankton cells from the microscopic images of the two selected phytoplankton taxa. For detection, the model achieves AP scores of 88.1% for Pseudo-nitzschia cf. delicatissima and 90.9% for Pseudo-nitzschia cf. calliantha, while for segmentation, the scores are 88.4% for Pseudo-nitzschia cf. delicatissima and 91.2% for Pseudo-nitzschia cf. calliantha. Compared to manual image analysis, the developed automatic method significantly increases the number of samples that can be processed.

Original scientific article

Explainable machine learning for predicting diarrhetic shellfish poisoning events in the Adriatic Sea using long-term monitoring data

Martin Marzidovšek, Janja Francé, Vid Podpečan, ... Patricija Mozetič Martin Marzidovšek, Janja Francé, Vid Podpečan, Stanka Grebenc, Jožica Dolenc, Patricija Mozetič Show all authors Show fewer authors
Show abstract Hide abstract

In this study, explainable machine learning techniques are applied to predict the toxicity of mussels in the Gulf of Trieste (Adriatic Sea) caused by harmful algal blooms. By analysing a newly created 28-year dataset containing records of toxic phytoplankton in mussel farming areas and diarrhetic shellfish toxins in mussels (Mytilus galloprovincialis), we train and evaluate the performance of machine learning (ML) models to accurately predict diarrhetic shellfish poisoning (DSP) events. Based on the F1 score, the random forest model provided the best prediction of toxicity results at which the harvesting of mussels is stopped according to EU regulations. Explainability methods such as permutation importance and Shapley Additive Explanations (SHAP) identified key species (Dinophysis fortii and D. caudata) and environmental factors (salinity, river discharge and precipitation) as the best predictors of DSP toxins above regulatory limits. These findings are important for improving early warning systems, which until now were based solely on empirically defined alert abundances of DSP species. They provide experts, aquaculture practitioners, and authorities with additional information to make informed risk management decisions

Original scientific article

Impact of information technology supported serious leisure gardening on the wellbeing of older adults : The Turntable project

István Vassányi, Benedek Szakonyi, Daniela Loi, ... Ferenc Rárosi István Vassányi, Benedek Szakonyi, Daniela Loi, Angelika Mantur-Vierendeel, João Quintas, Antonio Solinas, Bojan Blažica, Luigi Raffo, Marco Guicciardi, Andrea Manca, Balázs Gaál, Ferenc Rárosi Show all authors Show fewer authors
Show abstract Hide abstract

Objective. The study presented in this paper aimed to assess the effect of an Information Technology enabled community gardening program for older adults, developed by an international consortium. Methods. We have executed a quantitative, pre- and post-test field trial with older adult volunteers to test the proposed programme in two European countries, Italy and Belgium (n=98). We used standardized and ad hoc questionnaires to measure changes in the volunteers’ mental and psychological state during the trial. The statistical data analysis sought for differences in the pre- and post-test values of the key scores related to the perceived quality of life and benefits of gardening via paired-samples t-tests, and also tried to identify the important factors of significant changes via logistic regression. Results. We found significant improvements in the perceived benefits of gardening and also in the scores computed from the WHO Quality of Life instruments, especially in the social sub-domains. The improvements were associated with the country, age, marital state and education of the volunteers. Higher age or being widow, divorced or single increased the odds of a significant improvement in the scores in more than one sub-domains. Conclusion. Though the two trial settings were different in some aspects, the observed significant improvements generally confirmed the positive effects of gardening concerning the perceived quality of life and benefits of gardening.

Conference proceedings placeholder cover
2024
Published scientific conference contribution

IPM adviser : spletno orodje za iskanje in primerjavo sistemov za podporo pri odločanju za integrirano varstvo rastlin

Jurij Marinko, Bojan Blažica, Marko Debeljak