Fant 9831 publikasjoner. Viser side 388 av 394:
Potato plant disease detection: leveraging hybrid deep learning models
Agriculture, a crucial sector for global economic development and sustainable food production, faces significant challenges in detecting and managing crop diseases. These diseases can greatly impact yield and productivity, making early and accurate detection vital, especially in staple crops like potatoes. Traditional manual methods, as well as some existing machine learning and deep learning techniques, often lack accuracy and generalizability due to factors such as variability in real-world conditions. This study proposes a novel approach to improve potato plant disease detection and identification using a hybrid deep-learning model, EfficientNetV2B3+ViT. This model combines the strengths of a Convolutional Neural Network - EfficientNetV2B3 and a Vision Transformer (ViT). It has been trained on a diverse potato leaf image dataset, the “Potato Leaf Disease Dataset”, which reflects real-world agricultural conditions. The proposed model achieved an accuracy of 85.06, representing an 11.43 improvement over the results of the previous study. These results highlight the effectiveness of the hybrid model in complex agricultural settings and its potential to improve potato plant disease detection and identification.
BioMed Central (BMC)
2025
2025
IEEE (Institute of Electrical and Electronics Engineers)
2025
Stress management with HRV following AI, semantic ontology, genetic algorithm and tree explainer
Heart Rate Variability (HRV) serves as a vital marker of stress levels, with lower HRV indicating higher stress. It measures the variation in the time between heartbeats and offers insights into health. Artificial intelligence (AI) research aims to use HRV data for accurate stress level classification, aiding early detection and well-being approaches. This study’s objective is to create a semantic model of HRV features in a knowledge graph and develop an accurate, reliable, explainable, and ethical AI model for predictive HRV analysis. The SWELL-KW dataset, containing labeled HRV data for stress conditions, is examined. Various techniques like feature selection and dimensionality reduction are explored to improve classification accuracy while minimizing bias. Different machine learning (ML) algorithms, including traditional and ensemble methods, are employed for analyzing both imbalanced and balanced HRV datasets. To address imbalances, various data formats and oversampling techniques such as SMOTE and ADASYN are experimented with. Additionally, a Tree-Explainer, specifically SHAP, is used to interpret and explain the models’ classifications. The combination of genetic algorithm-based feature selection and classification using a Random Forest Classifier yields effective results for both imbalanced and balanced datasets, especially in analyzing non-linear HRV features. These optimized features play a crucial role in developing a stress management system within a Semantic framework. Introducing domain ontology enhances data representation and knowledge acquisition. The consistency and reliability of the Ontology model are assessed using Hermit reasoners, with reasoning time as a performance measure. HRV serves as a significant indicator of stress, offering insights into its correlation with mental well-being. While HRV is non-invasive, its interpretation must integrate other stress assessments for a holistic understanding of an individual’s stress response. Monitoring HRV can help evaluate stress management strategies and interventions, aiding individuals in maintaining well-being.
Nature Portfolio
2025
The apportionment of equivalent black carbon (eBC) to combustion sources from liquid fuels (mainly fossil; eBCLF) and solid fuels (mainly non-fossil; eBCSF) is commonly performed using data from Aethalometer instruments (AE approach). This study evaluates the feasibility of using AE data to determine the absorption Ångström exponents (AAEs) for liquid fuels (AAELF) and solid fuels (AAESF), which are fundamental parameters in the AE approach. AAEs were derived from Aethalometer data as the fit in a logarithmic space of the six absorption coefficients (470–950 nm) versus the corresponding wavelengths. The findings indicate that AAELF can be robustly determined as the 1st percentile (PC1) of AAE values from fits with R2 > 0.99. This R2-filtering was necessary to remove extremely low and noisy-driven AAE values commonly observed under clean atmospheric conditions (i.e., low absorption coefficients). Conversely, AAESF can be obtained from the 99th percentile (PC99) of unfiltered AAE values. To optimize the signal from solid fuel sources, winter data should be used to calculate PC99, whereas summer data should be employed for calculating PC1 to maximize the signal from liquid fuel sources. The derived PC1 (AAELF) and PC99 (AAESF) values ranged from 0.79 to 1.08, and 1.45 to 1.84, respectively. The AAESF values were further compared with those constrained using the signal at mass-to-charge 60 (m/z 60), a tracer for fresh biomass combustion, measured using aerosol chemical speciation monitor (ACSM) and aerosol mass spectrometry (AMS) instruments deployed at 16 sites. Overall, the AAESF values obtained from the two methods showed strong agreement, with a coefficient of determination (R2) of 0.78. However, uncertainties in both approaches may vary due to site-specific sources, and in certain environments, such as traffic-dominated sites, neither approach may be fully applicable.
Elsevier
2025
Global greenhouse gas reconciliation 2022
n this study, we provide an update on the methodology and data used by Deng et al. (2022) to compare the national greenhouse gas inventories (NGHGIs) and atmospheric inversion model ensembles contributed by international research teams coordinated by the Global Carbon Project. The comparison framework uses transparent processing of the net ecosystem exchange fluxes of carbon dioxide (CO2) from inversions to provide estimates of terrestrial carbon stock changes over managed land that can be used to evaluate NGHGIs. For methane (CH4), and nitrous oxide (N2O), we separate anthropogenic emissions from natural sources based directly on the inversion results to make them compatible with NGHGIs. Our global harmonized NGHGI database was updated with inventory data until February 2023 by compiling data from periodical United Nations Framework Convention on Climate Change (UNFCCC) inventories by Annex I countries and sporadic and less detailed emissions reports by non-Annex I countries given by national communications and biennial update reports. For the inversion data, we used an ensemble of 22 global inversions produced for the most recent assessments of the global budgets of CO2, CH4, and N2O coordinated by the Global Carbon Project with ancillary data. The CO2 inversion ensemble in this study goes through 2021, building on our previous report from 1990 to 2019, and includes three new satellite inversions compared to the previous study and an improved managed-land mask. As a result, although significant differences exist between the CO2 inversion estimates, both satellite and in situ inversions over managed lands indicate that Russia and Canada had a larger land carbon sink in recent years than reported in their NGHGIs, while the NGHGIs reported a significant upward trend of carbon sink in Russia but a downward trend in Canada. For CH4 and N2O, the results of the new inversion ensembles are extended to 2020. Rapid increases in anthropogenic CH4 emissions were observed in developing countries, with varying levels of agreement between NGHGIs and inversion results, while developed countries showed a slowly declining or stable trend in emissions. Much denser sampling of atmospheric CO2 and CH4 concentrations by different satellites, coordinated into a global constellation, is expected in the coming years. The methodology proposed here to compare inversion results with NGHGIs can be applied regularly for monitoring the effectiveness of mitigation policy and progress by countries to meet the objectives of their pledges. The dataset constructed for this study is publicly available at https://doi.org/10.5281/zenodo.13887128 (Deng et al., 2024).
2025
2025
Aerosol hygroscopicity influenced by seasonal chemical composition variations in the Arctic region
In this study, we quantified aerosol hygroscopicity parameter using aerosol microphysical observation data (κphy), analyzing monthly and seasonal trends in κphy by correlating it with aerosol chemical composition over 6 years from April 2007 to March 2013 at the Zeppelin Observatory in Svalbard, Arctic region. The monthly mean κphy value exhibited distinct seasonal variations, remaining high from winter to spring, reaching its minimum in summer, followed by an increase in fall, and maintaining elevated levels in winter. To verify the reliability of κphy, we employed the hygroscopicity parameter calculated from chemical composition data (κchem). The chemical composition and PM2.5 mass concentration required to calculate κchem was obtained through Modern-Era Retrospective Analysis for Research and Applications, version 2 (MERRA-2) reanalysis data and the calculation of κchem assumed that Arctic aerosols comprise only five species: black carbon (BC), organic matter (OM), ammonium sulfate (AS), sea salt aerosol less than a diameter of 2.5 μm (SSA2.5), and dust aerosol less than a diameter of 2.5 μm (Dust2.5). The κchem had no distinct correlation but had a similar seasonal trend compared to κphy. The κchem value followed a trend of SSA2.5 and was much higher by a factor of 1.6 ± 0.3 than κphy on average, due to a large proportion of SSA2.5 mass concentration in MERRA-2 reanalysis data. This may be due to the overestimation of sea salt aerosols in MERRA-2 reanalysis. The relationship between monthly mean κphy and the chemical composition used to calculate κchem was also analyzed. The elevated κphy from October to February resulted from the dominant influence of SSA2.5, while the maximum κphy in March was concurrently influenced by increasing AS and Dust2.5 associated with long-range transport from mid-latitude regions during Arctic haze periods and by SSA mass concentration obtained from in-situ sampling, which remained high from the preceding winter. The relatively low κphy from April to September can be attributed to low SSA2.5 and the dominance of organic compounds in the Arctic summer. Either natural sources such as those of marine and terrestrial biogenic origin or long-range-transported aerosols may contribute to the increase in organic aerosols in summer, potentially influencing the reduction in κphy of atmospheric aerosols. To our knowledge, this is the first study to analyze the monthly and seasonal variation of aerosol hygroscopicity calculated using long-term microphysical data, and this result provides evidence that changes in monthly and seasonal hygroscopicity variation occur depending on chemical composition.
Elsevier
2025
2025
We have used the NASA Goddard Institute for Space Studies (GISS) Earth system model GISS-E2.1 to study the future budgets and trends of global and regional CH4 under different emission scenarios, using both the prescribed GHG concentrations as well as the interactive CH4 sources and sinks setup of the model, to quantify the model performance and its sensitivity to CH4 sources and sinks. We have used the Current Legislation (CLE) and the maximum feasible reduction (MFR) emission scenarios from the ECLIPSE V6b emission database to simulate the future evolution of CH4 sources, sinks, and levels from 2015 to 2050. Results show that the prescribed GHG version underestimates the observed surface CH4 concentrations during the period between 1995 and 2023 by 1%, with the largest underestimations over the continental emission regions, while the interactive simulation underestimates the observations by 2%, with the biases largest over oceans and smaller over the continents. For the future, the MFR scenario simulates lower global surface CH4 concentrations and burdens compared to the CLE scenario, however in both cases, global surface CH4 and burden continue to increase through 2050 compared to present day. In addition, the interactive simulation calculates slightly larger O3 and OH mixing ratios, in particular over the northern hemisphere, leading to slightly decreased CH4 lifetime in the present day. The CH4 forcing is projected to increase in both scenarios, in particular in the CLE scenario, from 0.53 W m−2 in the present day to 0.73 W m−2 in 2050. In addition, the interactive simulations estimate slightly higher tropospheric O3 forcing compared to prescribed simulations, due to slightly higher O3 mixing ratios simulated by the interactive models. While in the CLE, tropospheric O3 forcing continues to increase, the MFR scenario leads to a decrease in tropospheric O3 forcing, leading to a climate benefit. Our results highlight that in the interactive models, the response of concentrations are not necessarily linear with the changes in emissions as the chemistry is non-linear, and dependent on the oxidative capacity of the atmosphere. Therefore, it is important to have the CH4 sources and chemical sinks to be represented comprehensively in climate models.
IOP Publishing
2025
This document provides technical details and support for the implementation of air quality monitoring under the Directive (EU) 2024/2881 of the European Parliament and of the Council of 23 October 2024 on ambient air quality and cleaner air for Europe (recast) (AAQD, Directive (EU) 2024/2881). It presents an overview of current knowledge and best practices, signposting to existing technical guidance on air quality monitoring and to sources of ongoing technical guidance development. This document does not formulate any legal provisions and as such, it does not have a legally binding value.
Publications Office of the European Union/European Commission. Directorate-General for Environment
2025
Supervised Anomaly Detection in Univariate Time-Series Using 1D Convolutional Siamese Networks
In time-series data analysis, identifying anomalies is crucial for maintaining data integrity and ensuring accurate analyses and decision-making. Anomalies can compromise data quality and operational efficiency. The complexity of time-series data, with its temporal dependencies and potential non-stationarity, makes anomaly detection challenging but essential. Our research introduces ADSiamNet, a 1D Convolutional Neural Network-based Siamese network model for anomaly detection and rectification. ADSiamNet effectively identifies localized patterns in time-series data and smooths detected anomalies using a quantile-based technique. In tests with physical activity data from Actigraph watches and MOX2-5 sensors, ADSiamNet achieved accuracies of 98.65% and 85.0%, respectively, outperforming other supervised anomaly detection methods. The model uses a contrastive loss function to compare input sequences and adjusts network weights iteratively during training to recognize intricate patterns. Additionally, we evaluated various univariate time-series forecasting algorithms on datasets with and without anomalies. Results show that anomaly-smoothed data reduces forecasting errors, highlighting our approach’s effectiveness in enhancing time-series data analysis’s integrity and reliability. Future research will focus on multivariate time-series datasets.
IEEE (Institute of Electrical and Electronics Engineers)
2025
Using a citizen science approach to assess nanoplastics pollution in remote high-altitude glaciers
Nature Portfolio
2025
Per- and polyfluoroalkyl substances (PFAS) have gained significant global attention due to their extensive industrial use and harmful effects on various organisms. Among these, perfluoroalkyl acids (PFAAs) are well-studied, but their diverse precursors remain challenging to monitor. The Total Oxidizable Precursor (TOP) assay offers a powerful approach to converting these precursors into detectable PFAAs. In this study, the TOP assay was applied to samples from the East Asian-Australian Flyway, a critical migratory route for millions of shorebirds. Samples included shellfish from China's coastal mudflats, key stopover sites for these birds, and blood and liver samples from shorebirds overwintering in Australia. The results showed a substantial increase in perfluorocarboxylic acids (PFCAs) across all sample types following the TOP assay, with the most significant increases in shorebird livers (Sum PFCAs increased by 18,156 %). Intriguingly, the assay also revealed unexpected increases in perfluorosulfonic acids (PFSAs), suggesting the presence of unidentified precursors. These findings highlight the need for further research into these unknown precursors, their sources, and their ecological impacts on shorebirds, other wildlife, and potential human exposure. This study also provides crucial insights into the TOP assay’s strengths and limitations in studying PFAS precursor dynamics in biological matrices.
Elsevier
2025
Recommendation technologies are widespread in streaming services, e-commerce, social media, news, and content management. Besides recommendation generation, its presentation is also important. Most research and development focus on the technical aspects of recommendation generation; therefore, a gap exists between recommendation generation and its effective presentation and user interaction. This study focuses on how personalized recommendations can be presented and interacted with in a music recommendation system using interactive visual interfaces. Interactive interface modeling with User-Centered Design (UCD) in a recommendation system is essential for creating a user-friendly, engaging, and personalized experience. By involving users in the recommendation process and considering their feedback, the system can deliver more relevant content, foster user trust, and improve overall user satisfaction and engagement. In this study, the visual interface design and development of a personalized music recommendation prototype (MusicReco) are presented using an iterative UCD approach, involving twenty end-users, one researcher, three academic professionals, and four experts. As the study is more inclined toward the recommendation presentation and visual modeling, we used a standard content-based filtering algorithm on the publicly available Spotify dataset for music recommendation generation. End-users helped to mature the MusicReco prototype to a basic working version through continuous feedback and design inputs on their needs, context, preferences, personalization, and effective visualization. Moreover, MusicReco captures the idea of mood-based tailored recommendations to encourage end-users. Overall, this study demonstrates how UCD can enhance the presentation and interaction of mood-based music recommendations, effectively engaging users with advancements in recommendation algorithms as a future focus.
IEEE (Institute of Electrical and Electronics Engineers)
2025
Status report of air quality in Europe for year 2023, using validated data
This report presents summarised information on the status of air quality in Europe in 2023, based on validated air quality monitoring data officially reported by the member and cooperating countries of the EEA. It aims at informing on the status of ambient air quality in Europe in 2023 and on the progress towards meeting the European air quality standards for the protection of health, as well as the WHO air quality guidelines. The report also compares the air quality status in 2023 with the previous years. The pollutants covered in this report are particulate matter (PM10 and PM2.5), tropospheric ozone (O3), nitrogen dioxide (NO2), benzo(a)pyrene (BaP), sulphur dioxide (SO2), carbon monoxide (CO), benzene (C6H6) and toxic metals (As, Cd, Ni, Pb). Measured concentrations above the European air quality standards for PM10, PM2.5, O3, and NO2 were reported by 18, 6, 20, and 9 reporting countries for 2022, respectively. Exceedances of the air quality standards for BaP, SO2, CO, and benzene were measured in, respectively, 9, 2, 2, and 0 reporting countries in 2023. Exceedances of European standards for toxic metals were reported by 5 stations for As, none for Cd, 1 for Pb and 2 for Ni.
ETC/HE
2025
2025