Fant 10464 publikasjoner. Viser side 6 av 419:
Abstract Potato plants are highly vulnerable to numerous diseases that can substantially affect both yield and quality. Conventional approaches for detecting these diseases are often labor-intensive, slow, and prone to inaccuracies, particularly under variable environmental conditions. This study presents a hybrid deep learning architecture, termed potato leaf diseases DenseNet (PLDNet) , which integrates a DenseNet-based convolutional neural network with a Transformer-based attention module to accurately classify potato leaf diseases. Furthermore, an adaptive parametric activation function, referred to as Adaptive Flatten p-Mish (AFpM) , is proposed to enhance the model’s learning flexibility and representational capacity. When evaluated on the PlantVillage and Mendeley datasets, PLDNet attains classification accuracies of 99.54% and 87.50%, respectively, surpassing contemporary state-of-the-art models and activation techniques. The proposed framework exhibits strong generalization performance and offers a scalable, efficient approach for automated plant disease identification. To highlight the novelty, the proposed AFpM activation function introduces a learnable parameter enabling adaptive nonlinearity, improving over Mish, Swish, and PFpM activation functions through dynamic gradient control. AFpM improves accuracy by 2.52% on Mendeley dataset, and 1.93% on PlantVillage dataset compared to PFpM, and by more than 3% compared to Swish and Mish.
2026
2023
2005
2009
A large eddy simulation study of mean dispersion and concentration fluctuations from a point source.
2017
A life cycle perspective on the benefits of renewable electricity generation
In this report, the benefits of the use of RES to produce electricity are investigated from a life cycle perspective. Six different impact indicators for the production of electricity are estimated for all Member States in the period 2005 to 2018 for a total of sixteen different renewable and non-RES. Results show variability in impact intensities across Member States and years, depending among others on fuel conversion efficiency (for electricity produced using combustion processes) and capacity utilization (for electricity producing from non-combustion processes, such as wind power). Finally, an estimate is given on gross avoided impact by comparing historic values to a counterfactual scenario where the level of electricity production from RES is frozen at 2005 level. Results show that the increased use of photovoltaic and wind power have contributed significantly to gross avoided impacts across the investigated impact indicators. A trade-off is that the increased use of PV appears to have increased potential ecotoxicity related impacts of the European electricity production system. The increased use of solid biomass for the generation of electricity and heat generally has a positive effect on avoided impacts, at the cost of increased potential land occupation. Overall, these finding can aid policy makers and private actors direct efforts towards specific areas which offer opportunities to decrease the impacts.
ETC/CME
2020
This report details the methodology and assumptions for the ETC/CME report: A life cycle perspective on the benefits of renewable electricity generation. In that report, gross avoided potential environmental impacts are estimated for electricity production in the EU-27 in the period 2005-2018. Avoided potential impacts are calculated by comparing the actual data with a counterfactual scenario where electricity production from Renewable Energy Sources is frozen at 2005 levels.
The overall methodological approach to the study is described in this report together with a short mathematical treatment of the calculation of life cycle indicators and subsequent scaling up to produce the two scenarios required to estimate gross avoided potential impacts. A short overview of data sources used in the study is included as well as a discussion and recommendations for the future.
ETC/CME
2020
2023
2007
Abstract The International Cooperative Programme on Integrated Monitoring of Air Pollution Effects on Ecosystems (ICP IM) presents a comprehensive long-term dataset of ongoing integrated ecosystem monitoring from European forested catchments. The dataset encompasses measurements from 46 monitoring stations across 14 European countries, with temporal coverage mostly extending from the early 1990s to 2020 (48 sites are currently active). The integrated monitoring approach applies over 20 monitoring subprogrammes to simultaneously measure physical, chemical, and biological properties across multiple ecosystem compartments including atmosphere, precipitation, throughfall, soil water, groundwater, runoff water, soil, vegetation, and biota. All measurements follow standardised protocols detailed in the ICP IM Manual, ensuring data quality and comparability across sites and time periods. The dataset supports research on ecosystem responses to air pollution, climate change impacts, and biogeochemical cycling. Data are available under a Creative Commons By Attribution (CC BY) licence, providing valuable long-term environmental monitoring data for the scientific community.
2026
2024
2006
A Machine Learning Approach to Retrieving Aerosol Optical Depth Using Solar Radiation Measurements
Aerosol optical depth (AOD) constitutes a key parameter of aerosols, providing vital information for quantifying the aerosol burden and air quality at global and regional levels. This study demonstrates a machine learning strategy for retrieving AOD under cloud-free conditions based on the synergy of machine learning algorithms (MLAs) and ground-based solar irradiance data. The performance of the proposed methodology was investigated by applying different components of solar irradiance. In particular, the use of direct instead of global irradiance as a model feature led to better performance. The MLA-based AODs were compared to reference AERONET retrievals, which encompassed RMSE values between 0.01 and 0.15, regardless of the underlying climate and aerosol environments. Among the MLAs, artificial neural networks outperformed the other algorithms in terms of RMSE at 54% of the measurement sites. The overall performance of MLA-based AODs against AERONET revealed a high coefficient of determination (R2 = 0.97), MAE of 0.01, and RMSE of 0.02. Compared to satellite (MODIS) and reanalysis (MERRA-2 and CAMSRA) data, the MLA-AOD retrievals revealed the highest accuracy at all stations. The ML-AOD retrievals have the potential to expand and complement the AOD information in non-existing timeframes when solar irradiances are available.
2024
The Filter Inlet for Gases and AEROsols coupled to a Chemical Ionization Mass Spectrometer (FIGAERO–CIMS) can be used to derive volatility of atmospheric aerosol by using the temperature at thermogram maximum signal (Tmax). For complex ambient particle matrices, Tmax of an individual compound often varies, for reasons not fully elucidated. Here, we apply machine learning to study the relation between Tmax of levoglucosan (C6H10O5), a common tracer to identify the influence of biomass burning (BB) in ambient air, and a set of atmospheric and instrumental parameters for an ambient year-long FIGAERO–CIMS data set measured in the Arctic. Using three different modeling approaches, namely, multiple linear regression (MLR), random forest (RF) regressor, and XGBoost regressor, we find that the mass loading on the FIGAERO filter has the highest relevance for variation in Tmax of levoglucosan. On the basis of these results, we suggest controlling the mass collected on the filter for continuous online measurement with the FIGAERO–CIMS if quantitative volatility information is to be gained. More generally, we demonstrate the usefulness of machine learning approaches for characterization of instrumental backgrounds in complex ambient or laboratory data.
2026
A machine learning method for estimating atmospheric trace gas concentration baselines
Estimates of trace gas baseline mole fractions in high-frequency atmospheric measurement records are crucial for analysing long-term changes in atmospheric composition. Baseline mole fractions are those that would be observed far from emission sources (and hence are representative of background conditions). Previous methods for inferring baseline mole fractions have used statistical or meteorological approaches, or, if available, co-measured tracer species thought only to be emitted from non-baseline wind sectors. Combinations of these techniques have also been employed in some applications. Statistical methods typically fit a baseline to the observations themselves, while meteorological methods use atmospheric models of varying complexity to categorise air mass origins. In this paper, we present a novel machine learning method for estimating trace gas baseline mole fractions, which benefits from the physical basis of model-based filtering without the need for running an expensive simulator. Our approach offers the accessibility and computational cost-effectiveness of statistical models, without the associated smoothing or difficulty in identifying rapid baseline variations. By training on historical Lagrangian particle dispersion model outputs, our model learns to predict baseline mole fractions directly from meteorological fields. This advancement opens new avenues for low-latency trace gas time series data analysis, reconstruction of historical baseline trends, and improved utilisation of tracer measurement air mass classification methods.
2026
2024
2001
2012
2015
2005
2001
2015