Fant 10273 publikasjoner. Viser side 76 av 411:
2010
2019
2012
2012
2009
2016
2019
2014
2014
Spatial and temporal assessment of soil degradation risk in Europe
Soil degradation threatens agricultural productivity and ecosystem resilience across Europe, yet spatially consistent assessments of its intensity and drivers remain limited. In this study, we used Soil Degradation Proxy (SDP), that integrates four key indicators of soil degradation, including erosion rate, soil pH, electrical conductivity, and organic carbon content, to quantify soil degradation risk. Using over 38,000 LUCAS topsoil observations and a machine learning model trained on climate, land cover, topographic, soil parent material properties, and spectral variables, we map annual SDP values between years 2000 to 2022 across Europe. Results show soil degradation risk is highest in southern Europe, especially in intensively managed and sparsely vegetated landscapes. Over the past two decades, approximately 7.1% of land area across the EU and the UK has experienced increasing degradation risk (most notably across Eastern Europe), with rainfed croplands emerging as the most affected land cover type. Land cover is the most influential driver, modulating effects of climatic variables such as precipitation and temperature on SDP. This data-driven framework provides a consistent and scalable approach for monitoring soil degradation risk and offers actionable insights to support targeted conservation and EU-wide policy implementation.
2025
2006
2009
2011
Intrusion Detection Systems (IDS) are critical in safeguarding network infrastructures against malicious attacks. Traditional IDSs often struggle with knowledge representation, real-time detection, and accuracy, especially when dealing with high-throughput data. This paper proposes a novel IDS framework that leverages machine learning models, streaming data, and semantic knowledge representation to enhance intrusion detection accuracy and scalability. Additionally, the study incorporates the concept of Digital Sovereignty, ensuring that data control, security, and privacy are maintained according to national and regional regulations. The proposed system integrates Apache Kafka for real-time data processing, an automatic machine learning pipeline (e.g., Tree-based Pipeline Optimization Tool (TPOT)) for classifying network traffic, and OWL-based semantic reasoning for advanced threat detection. The proposed system, evaluated on NSL-KDD and CIC-IDS-2017 datasets, demonstrated qualitative outcomes such as local compliance, reduced data storage needs due to real-time processing, and improved adaptability to local data laws. Experimental results reveal significant improvements in detection accuracy, processing efficiency, and Sovereignty alignment.
2025
Personalized approaches are required for stroke management due to the variability in symptoms, triggers, and patient characteristics. An innovative stroke recommendation system that integrates automatic predictive analysis with semantic knowledge to provide personalized recommendations for stroke management is proposed by this paper. Stroke exacerbation are predicted and the recommendations are enhanced by the system, which leverages automatic Tree-based Pipeline Optimization Tool (TPOT) and semantic knowledge represented in an OWL Ontology (StrokeOnto). Digital sovereignty is addressed by ensuring the secure and autonomous control over patient data, supporting data sovereignty and compliance with jurisdictional data privacy laws. Furthermore, classifications are explained with Local Interpretable Model-Agnostic Explanations (LIME) to identify feature importance. Tailored interventions based on individual patient profiles are provided by this conceptual model, aiming to improve stroke management. The proposed model has been verified using public stroke dataset, and the same dataset has been utilized to support ontology development and verification. In TPOT, the best Variance Threshold + DecisionTree Classifier pipeline has outperformed other supervised machine learning models with an accuracy of 95.2%, for the used datasets. The Variance Threshold method reduces feature dimensionality with variance below a specified threshold of 0.1 to enhance predictive accuracy. To implement and evaluate the proposed model in clinical settings, further development and validation with more diverse and robust datasets are required.
2025
South Durban Basin multi-point plan. Case study report. A Governance Information Publication, Series C, Book 12
2007
South Asia Basins: LOICZ global change assessment and synthesis of river catchment - coastal sea interaction and human dimensions. LOICZ Reseach and Studies, 32
2009
2003
2009
Sources of uncertainty and their assessment in spatial mapping. ETC/ACC Technical paper, 2008/20
2009
Sources of ultrafine particles at a rural midland site in Switzerland
Ultrafine particles (UFPs; i.e., atmospheric aerosol particles smaller than 100 nm in diameter) are known to be responsible for a series of adverse health effects as they can deposit in humans' bodies. So far, most field campaigns studying the sources of UFPs have focused on urban environments. This study investigates the outdoor sources of UFPs at the atmospheric monitoring station in Payerne, which represents a typical rural location in Switzerland. We aim to quantify the primary and secondary fractions of UFPs based on specific measurements between July 2020 and July 2021 complementing a series of operational meteorological, trace gas and in situ aerosol observations. To distinguish between primary and secondary contributions, we use a method that relies on measuring the fraction of non-volatile particles as a proxy for primary particles. We further compare our measurement results to previously established methods. We find that primary particles resulting from traffic and residential wood burning (direct emissions – mostly non-volatile BC-rich) contribute less than 40 % to the total number of UFPs, mostly in the Aitken mode. On the other hand, we observe local new particle formation (NPF) events (observed from ∼ 1 nm) evident from the increase in cluster ions (1.5–3 nm) and nucleation-mode particle (2.5–25 nm) concentrations, especially in spring and summer. These events, mediated by sulfuric acid, contribute to increasing the UFP number concentration, especially in the nucleation mode. Besides NPF, the chemical processing of particles emitted from multiple sources (including traffic and residential wood burning) contributes substantially to the nucleation-mode particle concentration. Under the present conditions investigated here, we find that secondary processes mediate the increase in UFP concentration to levels equivalent to those in urban locations, affecting both air quality and human health.
2025
2010