Fant 9758 publikasjoner. Viser side 75 av 391:
2019
Rapid growth in urbanization and industrialization leads to an increase in air pollution and poor air quality. Because of its adverse effects on the natural environment and human health, it’s been declared a “silent public health emergency”. To deal with this global challenge, accurate prediction of air pollution is important for stakeholders to take required actions. In recent years, deep learning-based forecasting models show promise for more effective and efficient forecasting of air quality than other approaches. In this study, we made a comparative analysis of various deep learning-based single-step forecasting models such as long short term memory (LSTM), gated recurrent unit (GRU), and a statistical model to predict five air pollutants namely Nitrogen Dioxide (NO 2 ), Ozone (O 3 ), Sulphur Dioxide (SO 2 ), and Particulate Matter (PM2.5, and PM10). For empirical evaluation, we used a publicly available dataset collected in Northern Ireland, using an air quality monitoring station situated in Belfast city centre. It measures the concentration of air pollutants. The performance of forecasting models is evaluated based on three performance metrics: (a) root mean square error (RMSE), (b) mean absolute error (MAE) and (c) R-squared ( R2 ). The result shows that deep learning models consistently achieved the least RMSE compared to the statistical models with a value of 0.59. In addition, the deep learning model is also found to have the highest R2 score of 0.856.
IEEE (Institute of Electrical and Electronics Engineers)
2023
2006
2008
1999
2019
2019
2016
2004
2021
In support of the global stocktake of the Paris Agreement on climate change, this study presents a comprehensive framework to process the results of an ensemble of atmospheric inversions in order to make their net ecosystem exchange (NEE) carbon dioxide (CO2) flux suitable for evaluating national greenhouse gas inventories (NGHGIs) submitted by countries to the United Nations Framework Convention on Climate Change (UNFCCC). From inversions we also deduced anthropogenic methane (CH4) emissions regrouped into fossil and agriculture and waste emissions, as well as anthropogenic nitrous oxide (N2O) emissions. To compare inversion results with national reports, we compiled a new global harmonized database of emissions and removals from periodical UNFCCC inventories by Annex I countries, and from sporadic and less detailed emissions reports by non-Annex I countries, given by national communications and biennial update reports. No gap filling was applied. The method to reconcile inversions with inventories is applied to selected large countries covering ∼90 % of the global land carbon uptake for CO2 and top emitters of CH4 and N2O. Our method uses results from an ensemble of global inversions produced by the Global Carbon Project for the three greenhouse gases, with ancillary data. We examine the role of CO2 fluxes caused by lateral transfer processes from rivers and from trade in crop and wood products and the role of carbon uptake in unmanaged lands, both not accounted for by NGHGIs. Here we show that, despite a large spread across the inversions, the median of available inversion models points to a larger terrestrial carbon sink than inventories over temperate countries or groups of countries of the Northern Hemisphere like Russia, Canada and the European Union. For CH4, we find good consistency between the inversions assimilating only data from the global in situ network and those using satellite CH4 retrievals and a tendency for inversions to diagnose higher CH4 emission estimates than reported by NGHGIs. In particular, oil- and gas-extracting countries in central Asia and the Persian Gulf region tend to systematically report lower emissions compared to those estimated by inversions. For N2O, inversions tend to produce higher anthropogenic emissions than inventories for tropical countries, even when attempting to consider only managed land emissions. In the inventories of many non-Annex I countries, this can be tentatively attributed to a lack of reporting indirect N2O emissions from atmospheric deposition and from leaching to rivers, to the existence of natural sources intertwined with managed lands, or to an underestimation of N2O emission factors for direct agricultural soil emissions. Inversions provide insights into seasonal and interannual greenhouse gas fluxes anomalies, e.g., during extreme events such as drought or abnormal fire episodes, whereas inventory methods are established to estimate trends and multi-annual changes. As a 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 inventory reports (e.g., NGHGIs) could be applied regularly for monitoring the effectiveness of mitigation policy and progress by countries to meet the objective of their pledges. The dataset constructed by this study is publicly available at https://doi.org/10.5281/zenodo.5089799 (Deng et al., 2021).
2022
2009
2008
2010
2018
2016
2024
2021
2008
Comparison of data assimilation methods for assessing PM10 exceedances on the European scale. NATO science for peace and security series
2008